ravenclaude

Blue-team DFIR / SOC team — 2 agents (dfir-response-lead, detection-and-forensics-engineer) for running a security incident end to end: the incident lifecycle per NIST SP 800-61r2 (preparation -> detection & analysis -> containment/eradication/recovery -> post-incident), triage & severity classification, containment strategy, breach coordination + comms + regulatory notification (GDPR 72h), tabletops; and detection engineering (SIEM/Sigma rules mapped to MITRE ATT&CK, alert tuning), hypothesis-driven threat hunting, evidence acquisition & forensics (order of volatility per RFC 3227, chain of custody), and malware triage. 5 skills, a knowledge bank with two Mermaid decision trees + a dated 2026 DFIR tooling map, 5 best-practices, 3 templates, 1 advisory hook. Seams: appsec/secure-coding -> security-engineering; governance/risk/audit -> cybersecurity-grc; reliability incidents -> observability-sre; platform abuse -> trust-and-safety. Requires ravenclaude-core@>=0.7.0.

Network-engineering team — 2 agents (network-architect, network-operations-engineer) for the ENTERPRISE network layer below the cloud VPC: campus/datacenter/WAN topology, routing (OSPF/BGP/EIGRP/static) and switching (VLANs, STP, LACP, VXLAN/EVPN), IP addressing/IPAM and DNS/DHCP, segmentation + zero-trust network access (microsegmentation, NAC, SASE/SD-WAN), load balancing, redundancy/HA (HSRP/VRRP, dual-homing), and day-2 ops (change windows, troubleshooting the OSI stack, observability/NetFlow). Knowledge bank with Mermaid decision trees (topology, routing-protocol selection, segmentation) + a dated 2026 capability map, 5 skills, best-practices, 4 templates, 1 advisory hook (any/any rules, telnet, no change window). Design-before-config; protocol-before-vendor-CLI. Seams: cloud VPC networking -> aws/azure/gcp-cloud; service mesh / k8s networking -> cloud-native-kubernetes; security verdicts -> security-engineering; IaC for network config -> terraform-iac. Requires ravenclaude-core@>=0.7.0.

Open-source maintenance team — 2 agents (oss-maintainer-strategist, release-and-versioning-engineer) for running a public project people can use, trust, and contribute to: license choice (permissive vs copyleft, dependency compatibility, CLA vs DCO), governance & community-health (CONTRIBUTING / CODE_OF_CONDUCT / GOVERNANCE / SECURITY.md, issue & PR triage + SLAs, the contributor funnel, bus factor, funding), semver + changelogs (Keep a Changelog / Conventional Commits), release automation (release-please / semantic-release / Changesets), deprecation windows, coordinated security releases (private report -> CVE/GHSA -> disclosure), and supply-chain provenance (SLSA, Sigstore). 5 skills, a knowledge bank with two Mermaid decision trees + a dated 2026 tooling map, 8 best-practices, 4 templates, 1 advisory hook. Seams: release pipelines -> devops-cicd; vuln analysis -> security-engineering; community growth -> developer-relations; docs -> technical-writing-docs. Requires ravenclaude-core@>=0.7.0.

Developer-tooling team — the BUILD-TOOLING layer for monorepo & build-systems engineering. 2 agents (build-systems-architect, monorepo-engineer) covering monorepo tooling (Nx, Turborepo, Bazel/Buck2, Moon, pnpm/yarn/npm workspaces, Lerna), build performance & remote/content-addressable caching, task graphs and affected/since-only builds, dependency & package management (version policy, lockfile hygiene, renovate/dependabot, supply-chain hygiene: SBOM/provenance/pinning), and code-generation/scaffolding. 3 skills (choose-monorepo-tooling, optimize-build-and-cache, manage-dependencies), 2 Mermaid-backed knowledge docs, and 2 runbook templates. Seams: CI/CD pipelines → devops-cicd; service code → backend/frontend-engineering; containers/IaC → the cloud plugins. Requires ravenclaude-core@>=0.7.0.

Data-orchestration team — 2 agents (orchestration-architect, pipeline-orchestration-engineer) for the layer that RUNS and SCHEDULES data pipelines: orchestrator selection (Airflow, Dagster, Prefect, Mage, Temporal-for-data; cloud-native MWAA/Step Functions, Azure Data Factory, Cloud Composer/Workflows), DAG and software-defined-asset design, scheduling/triggers (cron, sensor, data-aware), backfills and catchup, idempotency and retries with exponential backoff, partitioning, freshness SLAs and alerting, and lineage. 3 skills (choose-orchestrator, design-dag-and-dependencies, handle-backfills-and-retries), a 2-doc knowledge bank (a Mermaid selection tree + a 2026 patterns reference), and 2 templates. Distinct from data-platform (ELT/warehouse/BI), analytics-engineering (dbt), and data-streaming-engineering (real-time) — this is the scheduling/run layer they plug into. Requires ravenclaude-core@>=0.7.0.

Startup-fundraising team — 2 agents (fundraising-strategist + pitch-and-narrative-coach) and 3 skills for founders/operators raising venture capital: round strategy (pre-seed/seed/Series A; SAFE vs priced round; how much to raise and runway math), the pitch narrative and deck (problem/solution/market/traction/team/ask), the fundraising financial model, cap-table and dilution math (option pools, pro-rata, post-money SAFE conversion, the post-money cap dilution gotcha), term-sheet and SAFE essentials (valuation cap, discount, liquidation preference, board, pro-rata — ESSENTIALS not legal advice), investor pipeline/CRM and outreach, the data room, and investor updates. Founder-side literacy only. Seams: financial-model mechanics to finance; product what/why to product-management; binding term-sheet legal review to legal-ops-clm. Requires ravenclaude-core@>=0.7.0.

IT Service Management (ITIL 4) team — 4 agents (service-management-lead, incident-and-problem-manager, change-and-release-manager, service-desk-and-request-manager) for running IT as a service: the ITIL 4 service value system and practice selection, incident vs problem vs major-incident handling, change enablement (standard/normal/emergency + the CAB) and release management, and the service desk — request fulfillment, SLAs/OLAs, knowledge management, the service catalog, and the CMDB/configuration management. 5 skills, a knowledge bank with Mermaid decision trees + a dated 2026 ITSM tooling map + an ITIL 4 practice reference, 8 best-practices, 4 templates, 4 commands, 1 advisory hook. Seams: engineering incident response/SRE/observability -> observability-sre, CI/CD release automation -> devops-cicd, security incidents/GRC -> cybersecurity-grc, cloud cost/asset -> finops-cloud-cost. Inherits ravenclaude-core protocols.

Legacy modernization team — 4 agents (modernization-strategist, codebase-archaeologist, refactoring-engineer, migration-engineer) for safely changing a working-but-aging system: assess the estate and choose among the 6 R's (retain/rehost/replatform/refactor/rearchitect/replace), understand undocumented code and find its seams, characterize behavior before touching it, strangle the monolith incrementally behind an anti-corruption layer, migrate data with dual-write/parallel-run, and cut over with a tested rollback. 5 skills, a knowledge bank with Mermaid decision trees + a dated 2026 capability map, 8 best-practices, 4 templates, 4 commands, 1 advisory hook. Seams: backend redesign -> backend-engineering, schema migration mechanics -> database-engineering, deploy/cutover automation -> devops-cicd, test-suite buildout -> qa-test-automation. Inherits ravenclaude-core protocols.

Email-engineering team — 2 agents (email-deliverability-architect, email-sending-engineer) for getting legitimate mail to the inbox: domain authentication (SPF, DKIM, DMARC alignment + a staged p=none -> quarantine -> reject rollout, BIMI), transport security (MTA-STS RFC 8461 + TLS-RPT RFC 8460), deliverability (subdomain stream separation, domain/IP warm-up, reputation, Gmail/Yahoo bulk-sender rules), ESP integration (SES/SendGrid/Postmark/Resend) with idempotent sends + verified webhook handling, MJML templates, and the feedback loop (bounce/complaint classification, ARF, suppression lists, one-click unsubscribe per RFC 8058). 5 skills, a 4-doc knowledge bank (Mermaid auth + diagnosis trees + dated 2026 ESP map + transport security), 9 best-practices, 3 templates, 4 commands, a scenarios bank, a stdlib auth-record linter, and 1 advisory hook. Seams: strategy -> marketing-operations, infra -> backend-engineering, DNS -> cloud plugins, security -> security-engineering. Requires ravenclaude-core@>=0.7.0.

Browser-extension-engineering team — 2 agents (extension-architect, extension-implementation-engineer) for building, shipping, and maintaining cross-browser extensions on Manifest V3: the service-worker background model (and the MV2->MV3 lifecycle trap), content-script isolation + message passing, the permissions / host-permissions model and least-privilege posture, storage, the Chrome Web Store / Edge Add-ons / Firefox AMO review pipelines, and the WebExtensions cross-browser delta (Chrome callback vs Firefox browser.* promises). The extension runtime + manifest + store surface — distinct from frontend-engineering (app-grade React UI) and desktop-app-engineering (Electron/Tauri). 3 skills (manifest-permissions-audit, store-submission-readiness), a knowledge bank (MV3 architecture + a permissions-minimization decision tree + a dated cross-browser capability note), best-practices. Security verdicts escalate to security-engineering. Requires ravenclaude-core@>=0.7.0.

Engineering Management specialist team — 4 agents (engineering-manager-lead, people-and-growth-manager, delivery-and-execution-manager, technical-health-manager), 5 skills, 5 commands, 4 templates, 1 advisory hook, 8 best-practice rules, and a 4-file research-grounded knowledge bank. The craft of leading engineers for an EM, team lead, or director accountable for a team's people, throughput, and codebase health — it treats a claim about a person as a hypothesis not a verdict, runs 1:1s as the engineer's meeting, uses DORA as a system signal never an individual stack-rank, hires through a structured loop, and sizes tech-debt as a carrying cost traded against the roadmap. Domain-neutral; deepens (does not replace) people-operations-hr and project-management. Inherits ravenclaude-core protocols.

Domain-neutral Claude Code foundation: 15 specialist agents, 46 skills, gates, hooks, rules, templates. Capability Grounding Protocol, Structured Output Protocol, Researcher meta-skill, comfort-posture dashboard, opt-in command-review tribunal (the Thing), WebFetch sanitizer, branch-archive escape hatch, brand-extraction (homepage → brand kit), Problems & Resolutions view, declarative-visualization (Vega-Lite/Deneb/SVG, Gate 101 + Gate 103 svg-report-lint, viz-spec-reviewer), and Claude orchestrator escape hatch (/claude-orchestrate). Slash commands: /init-agent-ready, /wrap, /set-posture, /dashboard, /forge, /reset-plugin-cache.

Power Platform specialist team — 11 agents (incl. power-platform-tester, power-bi-engineer) and 23 skills, with strong ALM/git coverage for solutions, flows, and PBIP. A house-opinions hook flags 8 §3/§4 violations; the knowledge bank carries production decision trees (PA-flow recovery, Dataverse token-acquisition, PCF React surface, PBI deploy/refresh, custom-connector build-path, PBIR Enhanced infinite-spinner debug + full build reference, DAX silent-zero scoring via the `Domain` pattern, sempy.fabric notebook reference, Power BI Copilot report-readiness, Code Apps connector gotchas, PBIP deployment variables + #839, PBIR reference enrichment, PBIP report fast-solve triage router [MCP-optional], main-forms-are-Web-API-authorable grounding) plus a real-engagement scenarios bank. Bundles the community pbix-mcp server (d0nk3yhm/pbix-mcp, MIT) for .pbix/.pbit read/write/DAX-eval (`pip install pbix-mcp`); documents (not bundles) the official Microsoft Dataverse MCP (CLAUDE.md §9a). Extends ravenclaude-core.

Corporate finance & FP&A specialist team — FP&A analyst (budgets, forecasts, variance commentary), financial modeler (3-statement, DCF, scenarios), controller (close, JEs, reconciliations), treasury analyst (cash, covenants, FX), valuation analyst (DCF + comps + precedent), audit-prep specialist (PBC, walkthroughs, SOC1/2 narratives), and board-pack composer. 9 skills, 8 templates, 12 knowledge-bank docs (ASC 805 / 718 / 740, accrual-cutoff, WACC, cost accounting, FP&A operating model + decision support), 1 advisory hook (hardcoded rates, plaintext PII, missing Sources / Assumptions). Inherits ravenclaude-core protocols.

Financial-regulatory & compliance specialist team — 6 function agents (AML/KYC, regulatory-reporting, risk-and-controls, policy & procedure, examination-prep, Bermuda-insurance) PLUS 6 jurisdiction/regulator specialists: BMA financial-institutions (banking, trust, corporate-services, fund-admin, investment-business, money-service, digital-assets — the primary build-out, with deep AML/ATF + supervision/fees + licensing-classification trees), CIMA (Cayman), Bahamas, Channel Islands (Jersey JFSC + Guernsey GFSC), UK PRA, and US federal+state. 19 primary-source-cited regulator knowledge files, 37 best-practice rules, 10 skills, 11 templates, 1 defensive PreToolUse hook (PII scrub — SSN/IBAN/credit-card/Bermuda TIN/wire instructions). Positioning reflects field experience inside a Tier-1 financial regulator (BMA). Inherits ravenclaude-core protocols.

Web design & build specialist team — web architect (IA, stack, hosting), UX designer (wireframes, flows, conversion), visual designer (brand, typography, tokens), frontend implementer (HTML/CSS/JS, React, Astro, Next), content strategist (copy, microcopy, SEO content), accessibility auditor (WCAG 2.2 AA/AAA), and performance engineer (Core Web Vitals, image/font optimization). 11 skills (design-system audit, card/tile UI, accessibility review, Core Web Vitals tuning, technical SEO audit, information architecture, conversion design, content audit, design-tokens scaffolding, third-party hygiene, Fluent UI v9 + React implementation), 8 templates, 1 advisory hook, and a knowledge bank seeded with a curated 2026 reference set of "cutting edge yet simple" marketing-site donors (Linear, Vercel, Raycast, Resend, Cursor, v0, Tldraw, Cal.com) — visual-designer / ux-designer / frontend-implementer / web-architect all carry compact inline priors plus a pointer to the full brief. Inherits ravenclaude-core protocols.

EdTech-flavored Partner Success Manager team — 6 specialist agents anchored on the PSM lane, with 16 skills, 16 templates, 1 advisory hook, a knowledge bank with Mermaid decision trees, a 4-scenario engagement bank, and a stdlib psm_calc.py calculator (seat-utilization / renewal-NRR-forecast / time-to-value). Covers QBRs, success plans, health scores, a self-contained Power-BI-style partner-health report, onboarding, touchpoint logs, adoption sequencing, 90-day implementation arcs, train-the-trainer curricula, advocacy/reference pipelines, renewal decision memos, and the integration contract for a centralized CS dashboard (Planhat + Salesforce + Snowflake + Zapier + Granola). Team growth ships as skills + knowledge + templates, not parallel agents. Primary-source citations with retrieval dates. Vertical-explicit but segment-agnostic — fits K-12, higher-ed, corporate L&D, or mixed EdTech books. Inherits ravenclaude-core protocols including the alternate-methods Capability Grounding Protocol.

Data-platform team — 4 agents (database-setup-guide, etl-pipeline-engineer, dashboard-builder, connector-developer) for cloud DBs, ELT (Airbyte / Fivetran / n8n) with connectors for QuickBooks / Stripe / Salesforce / HubSpot / GA4 / Shopify / HRIS / Planhat / Intercom / Slack-as-source plus 8-vendor support-tool integration coverage (Zendesk, Freshdesk, Intercom Conv+Tkt, SFDC Service Cloud, JSM, HubSpot Service, Help Scout, Front + 2026 Fivetran connector-MAR build-vs-buy math), and embedded dashboards (Evidence.dev / Superset / Metabase / Cube + Tremor). 13 skills (incl. support-ticket-normalization — conformed fct_ticket / fct_conversation_event over 8 vendors; cross-system-identity-resolution — the Salesforce↔Planhat↔Intercom↔Slack account spine), 12 templates, a 24-doc knowledge bank, 21 best-practices. Opinionated against per-viewer-priced BI for greenfield SMB. Requires ravenclaude-core@>=0.7.0.

Customer-Success analytics team — 2 specialist agents (cs-analytics-architect, churn-signal-analyst) that own the DOMAIN layer of a CS-health analytics build: the conformed account / health-snapshot / renewal data model, which signals compose the health view, and the transparent rule-based Green/Yellow/Red risk tier (every Red shows why) — no black-box ML in phase one. Domain-neutral: it sits on top of data-platform's pipeline/warehouse/connector layer (which it routes all plumbing to) rather than duplicating it. 5 skills (health-tier-design, renewal-workflow-design — generalized from the EdTech PSM lane into vertical-neutral form), a 2-doc knowledge bank (CS-health metrics + churn-leading indicators, renewal & account lifecycle), and a code-fenced cs-health-data-model template whose identity-resolution spine points at data-platform. Pairs with data-platform; seams to salesforce / tableau / edtech-partner-success. Requires ravenclaude-core@>=0.7.0.

End-user authentication & identity team — 2 agents (auth-architect, auth-implementation-engineer) for adding login to a web app (React/Next), an API, and an analytics dashboard. A variety of methods: Google, Apple, Microsoft, GitHub social SSO plus magic link, passkeys/WebAuthn, and email+password — via managed auth (leaning Supabase Auth, so adding a provider is config not architecture). 7 skills, 4 templates, 5 best-practices, and a 4-doc web-verified knowledge bank with 5 Mermaid decision trees (build-vs-buy, which-providers, OAuth-flow, token-storage, gate-the-dashboard). House rules: Authorization Code + PKCE never Implicit; never store tokens in localStorage; validate ID tokens server-side. The boundary: this plugin AUTHENTICATES the person; data-platform AUTHORIZES the data (RLS / embed-JWT); Microsoft/enterprise Entra seams to azure-cloud, concrete auth code to security-reviewer. Requires ravenclaude-core@>=0.7.0.

Applied-statistics team — 1 specialist agent (applied-statistician) that answers 'is this difference/trend statistically REAL?' for SMB consulting: which test to use (decision-tree-driven), A/B-test and experiment design (power/MDE, primary + guardrail metrics, pre-registered analysis plans), regression and time-series forecasting review, a causal-inference primer, and statistical QA of dashboard metrics. 5 skills, a 5-doc knowledge bank (a Mermaid test-selection decision tree, a 9-item pitfalls guardrail, experiment-design best practice, 2026 tooling tiers, a causal-inference primer), 4 templates, and 1 advisory anti-pattern hook. Python-first (scipy.stats / statsmodels / pingouin Tier 1; PyMC / bambi / linearmodels Tier 2). Seams cleanly with data-platform: data-platform answers 'is this number correct?'; this plugin answers 'is it real?'. Method-before-library; always report effect size + CI. Requires ravenclaude-core@>=0.7.0.

Lean Six Sigma process-improvement team — 2 specialist agents (lean-six-sigma-blackbelt, process-analyst) that analyze a team's operational processes and improve them with Black-Belt rigor: DMAIC, Lean waste removal (the 8 wastes / DOWNTIME), data-proven root-cause analysis, statistical process control, and control plans that make the gain stick. Domain-neutral (support, onboarding, billing, deployment, hiring — any process). 6 skills (dmaic-project-charter, process-mapping, root-cause-analysis, process-capability-and-spc, lean-waste-analysis, control-plan-and-sustain), 5 templates (charter, SIPOC, fishbone+5-Whys, FMEA, control-plan), 7 best-practices, and a 3-doc knowledge bank with 6 web-verified Mermaid decision trees (sigma/DPMO, Cp/Cpk, control-chart selection, Western-Electric/Nelson rules). The inferential statistics seam (hypothesis tests, DOE, regression, Gage R&R) routes to applied-statistics; DMAIC project delivery routes to project-management. Requires ravenclaude-core@>=0.7.0.

Microsoft Fabric specialist team — 7 agents (fabric-architect, lakehouse-engineer, warehouse-engineer, data-factory-engineer, realtime-intelligence-engineer, fabric-semantic-model-engineer, fabric-admin) covering OneLake, Lakehouse (Spark/Delta/medallion/materialized lake views), Warehouse (T-SQL/ACID), Data Factory (mirroring/copy-job/dataflow-gen2/pipelines), Real-Time Intelligence (Eventstream/Eventhouse/KQL/Activator), Direct Lake semantic models, and platform admin (capacity FinOps, OneLake security, domains, Purview, ALM). 13-doc citation-grounded knowledge bank (two Mermaid decision trees + a dated 2026 capability map), 6 templates, 1 advisory hook (14 house opinions). Seams: enterprise Microsoft/Fabric here vs non-Microsoft/SMB embedded to data-platform; Fabric storage + Direct Lake here vs standalone Power BI/.pbix to power-platform/power-bi-engineer. Requires ravenclaude-core@>=0.7.0.

Claude app-engineering specialist team — 6 agents (claude-solution-architect, prompt-and-context-engineer, mcp-and-server-tools-engineer, agent-sdk-engineer, eval-engineer, claude-app-ops-engineer) for building production applications on the Claude API, the Claude Agent SDK, and MCP. Covers the build-surface decision (Messages API / Agent SDK / Managed Agents), model right-sizing (Opus 4.8 / Sonnet 4.6 / Haiku 4.5, 1M context), prompt caching, tool use + structured output, MCP server authoring + Anthropic-hosted server tools (computer use, code execution, Files API, memory, advisor tool), evals (golden sets, LLM-as-judge), and FinOps + reliability (batch, model routing, backoff, observability). 15-doc dated-and-cited knowledge bank, 6 templates, 1 advisory hook (14 house opinions). Seams: prompt-as-artifact, security, and cross-domain architecture escalate to ravenclaude-core. Requires ravenclaude-core@>=0.7.0.

Azure cloud infrastructure & platform specialist team — 7 agents (azure-architect, bicep-iac-engineer, entra-identity-engineer, network-engineer, app-platform-engineer, integration-engineer, azure-ops-engineer) for the Azure layer under the Microsoft stack: landing zones / CAF, IaC (Bicep + Terraform + Azure Verified Modules + Deployment Stacks), Entra identity (managed identity, workload identity federation, RBAC, PIM, External ID), networking (Private Endpoints, hub-spoke, Front Door, WAF), compute selection (App Service / Container Apps / Functions / AKS), integration (Logic Apps, Service Bus, Event Grid, APIM), and observability + FinOps + governance. 12-doc dated knowledge bank (two Mermaid decision trees + a 2026 capability map), 6 templates, 1 advisory hook (16 house opinions). Seams: Logic Apps here vs Power Automate to power-platform; Fabric data to microsoft-fabric; Azure host here vs Claude app to claude-app-engineering. Requires ravenclaude-core@>=0.7.0.

Salesforce practitioner team — 5 agents (apex-engineer, flow-automation-architect, agentforce-architect, salesforce-platform-architect, salesforce-reviewer) covering governor-safe bulkified Apex (triggers/async/services), declarative automation by density (Flow vs Apex), Agentforce agent design (topics/subagents, Agent Script determinism, RAG grounding, Trust Layer), org architecture (data model, OWD→role→sharing→Apex security model, 2GP packaging/DevOps, LDV), and a forked review rubric (the 15 house opinions as pass/fail). 9-doc citation-grounded knowledge bank (9 Mermaid decision trees, dated 2026-05-30), 5 skills, 5 templates, 1 advisory hook (grep-able anti-patterns: SOQL/DML-in-loop, hard-coded IDs, SeeAllData=true, missing with-sharing). Seams: integration→azure-cloud, analytics→data-platform/microsoft-fabric, LWC styling→web-design, methodology/DevOps/security-review→ravenclaude-core. Requires ravenclaude-core@>=0.7.0.

Microsoft 365 Copilot extensibility & administration team — 6 agents (copilot-extensibility-architect, declarative-agent-engineer, graph-connector-engineer, api-plugin-engineer, agents-sdk-engineer, copilot-admin-governance) covering declarative agents (pinned manifest schema + the 50/25/4096/45s hard-limit wall), custom-engine agents on the M365 Agents SDK/Toolkit, Copilot (Graph) connectors (synced vs federated/MCP, semantic labels, ACL trimming), API plugins (OpenAPI + Entra/OAuth2), the app-package publish lifecycle, and M365 Agent Registry + Purview DLP-for-Copilot governance. 9-doc citation-grounded knowledge bank (two Mermaid decision trees), 5 skills, 5 templates, 1 advisory hook (15 house opinions). Disjoint from power-platform's Copilot Studio low-code coverage (cross-linked). Seams: Copilot Studio → power-platform; CEA engine → claude-app-engineering; Entra/hosting → azure-cloud; security → ravenclaude-core. Requires ravenclaude-core@>=0.7.0.

Tableau analytics team — specialist agents for Tableau Desktop/Cloud/Server, Tableau Prep, and the developer surface: VizQL and chart-type selection, calculations (LOD expressions, table calcs, FIXED/INCLUDE/EXCLUDE), data modeling (relationships vs joins vs blends, extracts vs live), workbook/extract performance, Server/Cloud governance and permissions, content/ALM promotion, embedding (Embedding API v3, Connected Apps/JWT), and the next-gen surface (Tableau Pulse, Tableau Next, CRM Analytics, Einstein/Agent). Citation-grounded knowledge bank with Mermaid decision trees + a best-practices library. Seams: Salesforce platform data → salesforce; warehouse/semantic modeling → data-platform/microsoft-fabric; Power BI comparison → power-platform; methodology/security-review → ravenclaude-core. Requires ravenclaude-core@>=0.7.0.

Microsoft Graph developer team — specialist agents for the Graph API surface: querying (OData $select/$filter/$expand/$search, paging, $batch, change tracking via delta), throttling/429 + retry discipline, the Graph SDKs; identity & authorization on Entra (app registration, delegated vs application permissions, scopes/consent, least-privilege, auth-code/client-credentials/OBO flows, certificate creds); and the workloads (users/groups, mail/calendar, Teams, SharePoint/OneDrive files, change notifications/subscriptions + lifecycle, Graph connectors). Citation-grounded knowledge bank with Mermaid decision trees + a best-practices library. Seams: Copilot Graph connectors → microsoft-365-copilot; Entra tenant/identity infrastructure → azure-cloud; Power Platform Dataverse → power-platform; methodology/security-review → ravenclaude-core. Requires ravenclaude-core@>=0.7.0.

Cross-tool AI-coding model guidance — three strategist agents that help you reason about model selection in the non-Claude coding ecosystems: GitHub Copilot's model picker (completions / chat / coding agent / cloud agent + org model rules), OpenAI Codex (CLI + cloud model lineup, reasoning levels, /model), and xAI Grok (Grok 4.x lineup + the coding-tool surface). Teaches the DURABLE reasoning — task-complexity → reasoning-level → cost-tier → surface — over a single citation-grounded, dated lineup that is the marketplace's freshness anchor for non-Claude model facts. Volatile specifics (prices, context windows, picker availability) carry retrieval dates + a re-verify-at-use rider, and the agents fetch live before quoting. Seam: when the answer is a CLAUDE model or a Claude-app build, escalate to claude-app-engineering/claude-solution-architect — this plugin owns the non-Claude tools. Requires ravenclaude-core@>=0.7.0.

Project & delivery management team — four specialists across the predictive (PMBOK/PMP) and agile (Scrum/Kanban) tracks and the hybrid between: delivery-lead (charter, schedule, scope/change control, earned value), scrum-master (backlog, sprints, ceremonies, velocity, impediments), risk-and-raid-analyst (scored qual+quant risk, RAID depth, mitigation/contingency, issue triage), and stakeholder-comms-lead (stakeholder register, comms plan, status/exec reporting, escalation memos, steering packs). Deepens — does NOT replace — ravenclaude-core's domain-neutral project-manager (the lightweight RAID/status-hygiene default every plugin routes to); this is the deep PM craft layer. Knowledge: a predictive-vs-agile-vs-hybrid decision tree + a best-practices library. Seams: prose polish → ravenclaude-core/documentarian; system design → architect. Requires ravenclaude-core@>=0.7.0.

Centralized multi-repo, multi-person activity & project tracking. Aggregates commits, pull requests, and issues across many GitHub repositories from the GitHub API and rolls them up by person, by repo, and by cross-repo project — so a team working in sibling repos has one place to see who did what, and a supervisor gets a manage-the-team view no single-repo activity log can provide. Ships a stdlib-only collector (GitHub REST API → normalized activity JSON), a markdown report generator (weekly tracker + rolling activity roll-up + per-project status), a self-contained HTML dashboard generator, a copy-in GitHub Action template for scheduled refresh, an on-demand /portfolio-refresh command, an optional hand-maintained narrative layer, and 5 skills (portfolio-setup, cross-repo-project-tracking). Secrets stay in env/secrets, never in config. Requires ravenclaude-core@>=0.7.0.

API engineering specialist team — 5 agents (api-design-architect, api-implementation-engineer, api-security-engineer, api-testing-engineer, api-platform-engineer) for the full lifecycle of an API you produce: paradigm choice (REST/GraphQL/gRPC/webhooks/AsyncAPI), contract-first design (OpenAPI 3.1/3.2, AsyncAPI 3.0, Arazzo), versioning & deprecation; the build craft (RFC 9457 Problem Details, cursor pagination, Idempotency-Key, ETag concurrency, HTTP semantics, 202+polling, RateLimit headers); security (OWASP API Security Top 10 2023 — BOLA/BOPLA/BFLA, token/scope validation, consumption limits, SSRF); and testing & operations (contract tests, Spectral lint in CI, Prism/Postman mocks, k6 load, gateway design, dev portal + SDK codegen, sunset rollout). Knowledge bank with 10 Mermaid decision trees + a dated 2026 capability map, 22 best-practices, 6 templates, 6 commands, 1 advisory hook. Security verdicts escalate to ravenclaude-core/security-reviewer. Requires ravenclaude-core@>=0.7.0.

Healthcare + education staffing operations & analytics consulting team — 6 specialist agents (engagement-lead, operations-analyst, recruiting-funnel-strategist, healthcare-staffing-specialist, education/school-based-specialist, workforce-market-analyst), 10 skills, 10 templates, 5 commands, 1 advisory hook, 7 best-practice rules, and an 8-file research-grounded knowledge bank: a staffing KPI glossary (funnel/financial/quality metrics with formulas + benchmarks), healthcare-staffing economics (travel/locum/allied/per-diem, bill-pay-burden, rate cycle), credentialing & IDEA/IEP compliance, K-12 school-based fundamentals (academic-calendar seasonality, teletherapy, ESSER cliff), 2023-2026 market trends + SIA-anchored sizing, a competitor landscape map, and a Soliant Health employer profile. Every external figure carries a source + date; advisory numbers marked [ESTIMATE]. Requires ravenclaude-core@>=0.7.0.

International freight-forwarding sales team — 6 agents (freight-rate-quoter, rfq-tender-strategist, key-account-manager, pipeline-forecast-coach, prospecting-outreach-strategist, trade-lane-compliance-advisor) for a global-forwarding sales / business-development manager: all-in ocean + air quotes (chargeable weight, BAF/CAF/THC/LSS surcharge stack, margin, validity), RFQ/RFP/tender response (qualify-or-decline + lane rate matrix + bid narrative), QBRs + account plans, pipeline + forecast hygiene (coverage, velocity, weighted/commit), multi-channel prospecting, and Incoterms 2020 + customs basics. 6 skills, 6 commands, a 2-doc knowledge bank with 4 Mermaid decision trees, and a runnable chargeable-weight / quote-margin calculator (scripts/freight_calc.py). Carrier-neutral; public industry-standard practice, no confidential method. Requires ravenclaude-core@>=0.7.0.

Database-engineering team — 4 agents (schema-architect, query-performance-engineer, migration-engineer, db-reliability-engineer) for the OPERATIONAL/transactional data layer (OLTP): relational schema design and normalization (and when to denormalize), indexing strategy and query/EXPLAIN-plan tuning, safe zero-downtime schema migrations (expand/contract), and connection-pooling, transactions/isolation, replication, and backup/restore reliability. Postgres-leaning, principles portable to MySQL/SQL Server; NoSQL access-pattern guidance where it fits. 5 skills, a decision-tree knowledge bank (index-choice + migration-safety trees + a dated 2026 capability map), 12 best-practices, 4 templates, 4 commands, 1 advisory hook. Distinct from data-platform (analytics/ELT/warehouse) and analytics-engineering (dbt). Seams: ELT/warehouse -> data-platform, ORM/app data-access -> backend-engineering, managed DB infra -> cloud plugins. Requires ravenclaude-core@>=0.7.0.

Backend-engineering team — 4 agents (backend-architect, service-implementation-engineer, backend-data-access-engineer, backend-reliability-engineer) for the application/service layer behind an API: domain modeling and service boundaries (monolith vs services, where to split), business-logic implementation and error handling, the data-access layer (repository pattern, ORM use, transaction boundaries, killing N+1), caching strategy (cache-aside, invalidation, stampede), background jobs and async messaging (idempotent workers, outbox, DLQs), and backend reliability (timeouts, retries with backoff + jitter, circuit breakers, graceful degradation). Language-agnostic (examples in Node/Python/Go). 6 skills, a decision-tree knowledge bank (service-boundary + cache trees + a dated map), 12 best-practices, 4 templates, 4 commands, 1 advisory hook. Seams: the contract -> api-engineering, the schema/index -> database-engineering, deploy -> devops-cicd. Requires ravenclaude-core@>=0.7.0.

Frontend-engineering team — 4 agents (frontend-architect, react-implementation-engineer, frontend-state-and-data-engineer, frontend-performance-engineer) for building app-grade frontends (React/Next, TypeScript): component architecture and composition, the rendering-strategy choice (CSR/SSR/SSG/ISR/React Server Components), client state vs server-cache (TanStack Query/RSC) and form/validation, bundle/performance discipline (code-splitting, Core Web Vitals, hydration cost), and accessibility-in-code (semantic HTML, ARIA, keyboard, focus). TypeScript-first. 5 skills, a decision-tree knowledge bank (rendering-strategy + state-location trees + a dated 2026 map), 12 best-practices, 4 templates, 4 commands, 1 advisory hook. Distinct from web-design (brand/UX/marketing sites). Seams: design/brand/WCAG-audit -> web-design, auth UX -> auth-identity, API consumption -> api-engineering, native -> mobile-engineering. Requires ravenclaude-core@>=0.7.0.

Mobile-engineering team — 4 agents (mobile-architect, ios-engineer, android-engineer, cross-platform-engineer) for native and cross-platform mobile apps: the native-vs-React-Native-vs-Flutter decision, iOS craft (Swift/SwiftUI, the app lifecycle, concurrency), Android craft (Kotlin/Jetpack Compose, lifecycle, coroutines), and the cross-cutting mobile concerns (offline-first + sync, secure on-device storage, push notifications/deep links, battery/network constraints, and the App Store / Play Store release pipeline + review). 5 skills, a decision-tree knowledge bank (platform-choice + offline-sync trees + a dated 2026 capability map), 12 best-practices, 4 templates, 4 commands, 1 advisory hook. Seams: shared web patterns -> frontend-engineering, the backend API -> api-engineering/backend-engineering, auth -> auth-identity, CI/CD signing -> devops-cicd. Requires ravenclaude-core@>=0.7.0.

AWS cloud infrastructure & platform team — 5 agents (aws-architect, aws-iam-identity-engineer, aws-network-engineer, aws-compute-platform-engineer, aws-ops-finops-engineer) for the AWS layer of a stack: multi-account landing zones (Organizations, Control Tower, SCPs), least-privilege IAM (roles over keys, IRSA, permission boundaries, Identity Center), VPC networking (subnets, security groups, PrivateLink/endpoints, Transit Gateway), compute selection (Lambda / ECS / EKS / Fargate / App Runner), event-driven integration (SQS/SNS/EventBridge/Step Functions), and observability + FinOps + Well-Architected governance. 6 skills, a decision-tree knowledge bank (compute-selection + account-strategy trees + a dated 2026 capability map), 12 best-practices, 5 templates, 4 commands, 1 advisory hook. Multi-cloud seam to azure-cloud/gcp-cloud; IaC -> terraform-iac; containers -> cloud-native-kubernetes; security verdicts -> ravenclaude-core/security-reviewer. Requires ravenclaude-core@>=0.7.0.

Google Cloud (GCP) infrastructure & platform team — 4 agents (gcp-architect, gcp-iam-engineer, gcp-network-engineer, gcp-data-and-compute-engineer) for the GCP layer of a stack: the resource hierarchy (organization/folders/projects) and org policy constraints, least-privilege IAM (predefined over primitive roles, service accounts + Workload Identity Federation, no key files), VPC networking (Shared VPC, firewall rules, Private Service Connect, Cloud NAT), compute selection (Cloud Run / GKE / Cloud Functions / GCE), and the data services (BigQuery, Pub/Sub, Cloud SQL) at a selection level. 5 skills, a decision-tree knowledge bank (compute-selection + project-hierarchy trees + a dated 2026 capability map), 12 best-practices, 4 templates, 4 commands, 1 advisory hook. Multi-cloud seam to aws-cloud/azure-cloud; IaC -> terraform-iac; BigQuery analytics -> data-platform; security verdicts -> ravenclaude-core/security-reviewer. Requires ravenclaude-core@>=0.7.0.

Technical-writing & docs team — 3 agents (docs-architect, api-reference-writer, docs-site-engineer) for developer and product documentation that people actually use: the Diataxis framework (tutorial / how-to / reference / explanation — and not mixing them), docs-as-code (docs in the repo, reviewed and CI-checked, versioned with the product), accurate API/SDK reference (spec-driven, examples that run, errors documented), and a maintainable docs site (Docusaurus/Mintlify/MkDocs, IA, search, versioning). Deepens ravenclaude-core/documentarian. 5 skills, a decision-tree knowledge bank (doc-type, docs-tooling, Diataxis content-type, lint-in-CI-vs-manual + a dated 2026 map), a 4-scenario bank, 12 best-practices, 4 templates, 4 commands, 1 advisory hook, a prose-linter LSP tier (Vale-LS + Marksman) and a stdlib readability/prose checker. Seams: dev portal/SDK -> api-engineering, site design -> web-design, prose polish -> ravenclaude-core/documentarian. Requires ravenclaude-core@>=0.7.0.

Product-management team — 3 agents (product-strategist, product-discovery-lead, product-metrics-analyst) for deciding WHAT to build and WHY: product strategy and vision (positioning, the strategy stack, opportunity sizing), continuous discovery (customer interviews, opportunity-solution trees, assumption testing, JTBD), evidence-based prioritization (RICE/cost-of-delay over opinion), crisp PRDs/specs framed as problems + outcomes, and product metrics (a North Star + input metrics, not vanity). Distinct from project-management (delivery/schedule/RAID) — this is the what/why, that's the how/when. 5 skills, a decision-tree knowledge bank (build-vs-not + prioritization trees + a dated 2026 map), 12 best-practices, 4 templates, 4 commands, 1 advisory hook. Seams: delivery -> project-management, experiment validity -> applied-statistics, UX -> web-design, A/B+flags infra -> experimentation-growth-engineering. Requires ravenclaude-core@>=0.7.0.

Experimentation & growth-engineering team — 3 agents (experimentation-architect, feature-flag-engineer, product-analytics-instrumentation-engineer) for the APPARATUS that lets a team learn fast and ship safely: feature flags + progressive delivery (kill switches, targeting, flag lifecycle/debt), A/B-test plumbing (assignment, exposure logging, SRM checks, sequential-peeking guards, the results read), and trustworthy event instrumentation (a tracking plan, a consistent event schema, identity stitching, a CDP). The engineering of experimentation — statistical VALIDITY (power/MDE, significance) is applied-statistics'. 5 skills, a decision-tree knowledge bank (flag-vs-config + ship-decision trees + a dated 2026 map), 12 best-practices, 4 templates, 4 commands, 1 advisory hook. Seams: significance -> applied-statistics, hypothesis/outcome -> product-management, rollout -> devops-cicd, pipelines -> data-platform. Requires ravenclaude-core@>=0.7.0.

Fintech & payments-engineering team — 4 agents (payments-architect, payments-integration-engineer, billing-subscriptions-engineer, payments-pci-compliance-advisor) for building payment + billing systems that don't lose or duplicate money: payment-flow architecture (PSP choice, money-as-integer, the double-entry ledger, reconciliation), payment integration (Stripe-style intents, idempotency keys, webhook verification + idempotent handling, 3DS/SCA, retries/dunning), subscription & usage billing (plans, proration, metering, invoicing, revenue events), and PCI-DSS scope minimization (tokenization, never touch raw PAN, SAQ-A posture). The ENGINEERING — accounting/GL routes to finance, financial regulation to regulatory-compliance, security verdicts to ravenclaude-core. 5 skills, a decision-tree knowledge bank (charge-flow + PCI-scope trees + a dated 2026 map), 12 best-practices, 4 templates, 4 commands, 1 advisory hook. Requires ravenclaude-core@>=0.7.0.

Analytics-engineering team — 3 agents (analytics-engineer, semantic-layer-engineer, data-quality-testing-engineer) for the TRANSFORMATION layer in the modern data stack: dbt modeling (staging -> intermediate -> marts, the medallion/Kimball split, incremental models, materializations), a governed semantic/metrics layer (one definition of revenue/active-user, metrics-as-code) so every tool agrees, and data quality (dbt tests, freshness, model contracts, anomaly checks) that gates the warehouse. Warehouse-neutral (Snowflake/BigQuery/Redshift/Databricks). 5 skills, a decision-tree knowledge bank (materialization + model-layer trees + a dated 2026 map), 12 best-practices, 4 templates, 4 commands, 1 advisory hook. Distinct from data-platform (ingestion/warehouse/BI) and database-engineering (OLTP). Seams: ELT/warehouse provisioning -> data-platform, OLTP -> database-engineering, BI -> tableau/data-platform, enterprise lakehouse -> microsoft-fabric. Requires ravenclaude-core@>=0.7.0.

Data-streaming-engineering team — 3 agents (streaming-architect, kafka-pipeline-engineer, stream-processing-engineer) for REAL-TIME data: streaming-vs-batch decision and topology, event streaming + CDC (Kafka/Pulsar/Kinesis, topics/partitioning, schema registry + evolution, the outbox/Debezium CDC pattern), delivery semantics (at-least-once vs exactly-once, idempotency, transactional outbox), and stream processing (Flink/Kafka-Streams: event-time vs processing-time, windowing, watermarks, state, joins, backpressure). 7 skills, a decision-tree knowledge bank (streaming-vs-batch + delivery-semantics trees + a dated 2026 map), 12 best-practices, 4 templates, 4 commands, 1 advisory hook. Distinct from data-platform (batch ELT) and microsoft-fabric (RTI/Eventstream). Seams: batch ELT -> data-platform, AsyncAPI contracts -> api-engineering, Fabric RTI -> microsoft-fabric, app-side messaging -> backend-engineering. Requires ravenclaude-core@>=0.7.0.

ML-engineering (MLOps) team — 4 agents (ml-platform-architect, training-pipeline-engineer, model-serving-engineer, ml-monitoring-engineer) for the PRODUCTION lifecycle of ML models: the platform/architecture (build-vs-buy, the stack, the train->register->serve->monitor loop), reproducible training pipelines + experiment tracking + a model registry, feature stores and train/serve consistency (avoiding training-serving skew and leakage), model serving (online vs batch, the right deployment with shadow/canary), and monitoring (data + concept drift, performance decay, retraining triggers). 6 skills, a decision-tree knowledge bank (serving-pattern + retraining-trigger trees + a dated 2026 map), 12 best-practices, 4 templates, 4 commands, 1 advisory hook. Seams: 'is the result significant?' -> applied-statistics, data pipelines -> data-platform/data-streaming, LLM/agent apps -> claude-app-engineering, deploy infra -> devops-cicd/cloud-native-kubernetes. Requires ravenclaude-core@>=0.7.0.

Data governance & privacy team — 3 agents (data-governance-architect, privacy-compliance-engineer, data-catalog-lineage-engineer) for making data discoverable, trustworthy, and lawfully used: the governance operating model (ownership/stewardship, policies, classification scheme), privacy mechanics (GDPR/CCPA/-style data-subject rights — access/erasure/portability, consent + lawful basis, data minimization, retention, pseudonymization vs anonymization), and a data catalog with lineage + sensitive-data/PII discovery + access governance/DLP. The ENGINEERING of governance, not legal advice. 5 skills, a decision-tree knowledge bank (classification + DSR-handling trees + a dated 2026 map), 12 best-practices, 4 templates, 4 commands, 1 advisory hook. Seams: financial-regulatory -> regulatory-compliance, warehouse RLS -> data-platform, Purview-in-Fabric -> microsoft-fabric, security verdicts -> security-engineering. Requires ravenclaude-core@>=0.7.0.

Observability & SRE team — 3 agents (observability-engineer, sre-reliability-engineer, incident-commander) for making a system observable and keeping it reliable: instrumentation on OpenTelemetry (metrics/logs/traces, semantic conventions, sampling, cardinality control), SLI/SLO and error-budget design, symptom-based alerting (multi-window burn-rate, alert on user pain not causes), incident response (severity, roles, comms, blameless postmortems, action-item follow-through), and proactive resilience verification via chaos engineering (steady-state hypotheses, blast-radius-limited fault injection, game days). 7 skills, a decision-tree knowledge bank (alert-design + SLO-target trees + a chaos-engineering reference + a dated 2026 tooling map), 12 best-practices, 4 templates, 4 commands, 1 advisory hook. Seams: deploy health-gates -> devops-cicd, cluster telemetry -> cloud-native-kubernetes, API SLOs -> api-engineering, cloud-native monitors -> azure/aws/gcp-cloud. Requires ravenclaude-core@>=0.7.0.

Security-engineering (AppSec) team — 4 agents (appsec-engineer, threat-modeler, supply-chain-security-engineer, cloud-security-engineer) for building security INTO software: threat modeling (STRIDE, data-flow diagrams, trust boundaries), application security testing (SAST/DAST/IAST/SCA in CI, OWASP Top 10 web), secrets management (detection, rotation, vaulting, no plaintext), software supply-chain integrity (SBOM consumption, dependency CVEs, SLSA verification, pinning), and cloud security posture (CSPM, IAM least-privilege, network exposure). 5 skills, a decision-tree knowledge bank (vuln-triage + secrets-handling trees + a dated 2026 tooling map), 12 best-practices, 4 templates, 4 commands, 1 advisory hook. **Proposes controls; every ship/no-ship security VERDICT escalates to ravenclaude-core/security-reviewer.** Seams: API OWASP -> api-engineering, identity -> auth-identity, data privacy -> data-governance-privacy. Requires ravenclaude-core@>=0.7.0.

QA & test-automation team — 3 agents (test-strategy-architect, e2e-automation-engineer, test-infrastructure-engineer) for a test suite that catches real defects without becoming a tax: the test pyramid (many fast unit, fewer integration, few E2E), deterministic end-to-end automation (Playwright/Cypress, resilient selectors, no fixed sleeps), test data and ephemeral environments, meaningful coverage (mutation over line %), and flaky-test quarantine. Deepens ravenclaude-core/tester-qa. 5 skills, a decision-tree knowledge bank (test-level + flake-triage trees + a dated 2026 tooling map), 12 best-practices, 4 templates, 4 commands, 1 advisory hook. Seams: contract tests -> api-engineering, CI gating -> devops-cicd, UI under test -> frontend-engineering. Requires ravenclaude-core@>=0.7.0.

DevOps & CI/CD delivery-pipeline team — 4 agents (pipeline-engineer, release-engineer, gitops-engineer, build-and-artifact-engineer) for the path from commit to production: CI design (stages, caching, matrix, fail-fast, required checks), progressive delivery (blue-green, canary, feature-flagged rollouts, automated rollback), GitOps continuous delivery (Argo CD / Flux, desired-state in Git, drift detection), and build/artifact integrity (reproducible builds, semantic versioning, SBOM, provenance/SLSA, registry hygiene). 5 skills, a decision-tree knowledge bank (deploy-strategy + CI-vs-CD-boundary trees + a dated 2026 tooling map), 12 best-practices, 4 templates, 4 commands, 1 advisory hook. Seams: IaC -> terraform-iac, clusters -> cloud-native-kubernetes, telemetry/SLOs -> observability-sre, supply-chain verdicts -> ravenclaude-core/security-reviewer. Requires ravenclaude-core@>=0.7.0.

Cloud-native & Kubernetes team — 4 agents (kubernetes-architect, container-build-engineer, k8s-platform-operator, service-mesh-networking-engineer) for running workloads on Kubernetes well: workload design (Deployment/StatefulSet/Job, probes, requests/limits, PDBs, HPA/VPA), container build hygiene (minimal non-root images, distroless, multi-stage), platform ops (namespaces, RBAC, network policies, resource quotas, admission control, upgrades), and service-mesh networking (ingress/gateway, mTLS, traffic-splitting, observability). Cloud-agnostic. 6 skills, a decision-tree knowledge bank (workload-type + ingress trees + a dated 2026 ecosystem map), 12 best-practices, 4 templates, 4 commands, 1 advisory hook. Seams: managed control plane (AKS/EKS/GKE) -> azure/aws/gcp-cloud, GitOps reconcile -> devops-cicd, telemetry/SLOs -> observability-sre. Requires ravenclaude-core@>=0.7.0.

Terraform & IaC team — 3 agents (iac-architect, terraform-module-engineer, iac-policy-and-state-engineer) for cloud-agnostic infrastructure-as-code: module design (composable, versioned, registry-published, the root-vs-child split), remote state and backend safety (locking, isolation by blast radius, no secrets in state), environment promotion (workspaces vs directories vs Terragrunt), drift detection, and policy-as-code guardrails (OPA/Sentinel/Conftest) in the plan pipeline. Terraform + OpenTofu. 5 skills, a decision-tree knowledge bank (state-isolation + module-boundary trees + a dated 2026 tooling map), 12 best-practices, 4 templates, 4 commands, 1 advisory hook. Seams: per-cloud resources -> azure-cloud (Bicep too)/aws-cloud/gcp-cloud, plan in CI -> devops-cicd, posture verdicts -> security-engineering. Requires ravenclaude-core@>=0.7.0.

Commercial Real Estate specialist team — 4 agents, 5 skills, 4-file cited knowledge bank, 4 templates, 5 commands, 8 best-practice rules, 1 advisory hook. An acquisitions-and-asset-management team for a CRE owner, operator, or advisor — it underwrites a deal to in-place NOI, prices the cap-rate-vs-Treasury spread, reads the bifurcated vacancy, decomposes net effective rent, and stress-tests the debt and refinance wall before a board sees the IC memo. Inherits ravenclaude-core protocols.

Restaurant Operations specialist team — 4 agents, 5 skills, 4-file cited knowledge bank, 3 templates, 5 commands, 8 best-practice rules, 1 advisory hook. An operations-and-unit-economics team for an independent or multi-unit restaurant operator — it manages prime cost (food + labor), engineers the menu by contribution margin and popularity, controls food cost against theoretical, and reads the P&L the way a GM who lives the four-wall margin does. Inherits ravenclaude-core protocols.

Veterinary Practice specialist team — 4 agents, 5 skills, 4-file cited knowledge bank, 3 templates, 5 commands, 8 best-practice rules, 1 advisory hook. A clinical-and-practice-management team for a veterinary hospital owner or medical director — it builds standardized care protocols, runs the practice on production and ACT (average client transaction), manages the appointment-and-doctor capacity that gates revenue, and frames the independent-vs-corporate position in a fast-consolidating market. Inherits ravenclaude-core protocols.

Dental Practice specialist team — 4 agents, 5 skills, 4-file cited knowledge bank, 3 templates, 5 commands, 8 best-practice rules, 1 advisory hook. A treatment-planning-and-revenue-cycle team for a dental practice owner — it controls overhead against the ~62% median, holds collections above 98%, builds case acceptance on the treatment plan rather than the discount, and reads doctor/hygiene production per hour the way a practice that runs on the schedule does. Inherits ravenclaude-core protocols.

Medical Revenue Cycle specialist team — 4 agents, 5 skills, 4-file cited knowledge bank, 3 templates, 5 commands, 8 best-practice rules, 1 advisory hook. A revenue-cycle team for a healthcare provider or RCM operator — it drives the clean-claim rate toward 98%, attacks denials before they happen (initial denials hit ~11.8% in 2024 and trend 12–15%), works the A/R by aging bucket, and reads net collection rate the way a CFO who lives the cash cycle does. Inherits ravenclaude-core protocols.

P&C Insurance specialist team — 4 agents, 5 skills, 4-file cited knowledge bank, 3 templates, 5 commands, 8 best-practice rules, 1 advisory hook. An underwriting-and-claims team for a P&C carrier, MGA, or agency analyst — it reads the combined ratio as loss plus expense, prices risk to the loss ratio rather than the competitor, manages the claims severity-and-frequency story, and reads catastrophe load the way an underwriting result that hit a decade-best ~92 combined in 2025 demands. Inherits ravenclaude-core protocols.

Nonprofit Fundraising specialist team — 4 agents, 6 skills, 4-file cited knowledge bank, 3 templates, 5 commands, 8 best-practice rules, 1 advisory hook. A development team for a nonprofit fundraiser or executive director — it protects donor retention (the cheapest dollar a nonprofit has, at ~$0.20 to keep vs ~$1.50 to acquire), builds the grant pipeline on fit before effort, segments the donor base by value and recency, and reads cost-to-raise-a-dollar honestly across channels. Inherits ravenclaude-core protocols.

Fleet & Logistics specialist team — 4 agents, 5 skills, 4-file cited knowledge bank, 3 templates, 5 commands, 8 best-practice rules, 1 advisory hook. A fleet-operations team for a carrier, private fleet, or last-mile operator — it reads cost-per-mile against the ~$2.26 industry all-in (and the ~$1.78 non-fuel marginal), manages the operating ratio in a market that turned negative-margin in 2024, routes and dispatches to deadhead and utilization, and treats driver turnover (often 90%+ at large truckload carriers) as a unit-economics problem. Inherits ravenclaude-core protocols.

Renewable Energy specialist team — 4 agents, 5 skills, 4-file cited knowledge bank, 3 templates, 5 commands, 8 best-practice rules, 1 advisory hook. A project-development team for a solar/storage developer, EPC, or asset owner — it models LCOE and project IRR against a cost-per-watt that ran ~$2.56 in 2025, navigates the interconnection queue that gates most projects, structures around the post-2025 ITC shift (residential 25D ended; 48E/PPA pathways remain), and reads O&M and degradation the way a 25-year asset demands. Inherits ravenclaude-core protocols.

Clinical Trials specialist team — 4 agents, 5 skills, 4-file cited knowledge bank, 3 templates, 5 commands, 8 best-practice rules, 1 advisory hook. A clinical-operations team for a sponsor, CRO, or site network — it designs feasible protocols (because eligibility criteria drive the enrollment failure that hits two-thirds of sites), plans patient recruitment against a ~$6,533 per-patient cost (and ~$19,533 to replace), manages site activation and the ~30% dropout, and frames the regulatory submission the way a study where 80% run late demands. Inherits ravenclaude-core protocols.

E-commerce & DTC specialist team — 4 agents, 5 skills, 4-file cited knowledge bank, 3 templates, 5 commands, 8 best-practice rules, 1 advisory hook. A growth-and-unit-economics team for a DTC brand operator — it protects the LTV:CAC ratio (the 3:1 line below which a brand bleeds), reads conversion against the 1.4–1.8% average, attacks the retention gap (the average brand keeps just ~28% for a second purchase), and reads contribution margin after the real cost of acquisition and returns. Inherits ravenclaude-core protocols.

Cannabis Operations specialist team — 4 agents, 5 skills, 4-file cited knowledge bank, 3 templates, 5 commands, 8 best-practice rules, 1 advisory hook. A compliance-and-retail-operations team for a licensed cannabis operator — it runs seed-to-sale traceability against the state track-and-trace system (Metrc/BioTrack/LeafData), manages the 280E tax burden that makes COGS allocation existential, runs dispensary retail on margin and basket, and reads a ~$45B U.S. market where the rules change at the state line. Inherits ravenclaude-core protocols.

Procurement & Sourcing specialist team — 4 agents, 5 skills, 4-file cited knowledge bank, 3 templates, 5 commands, 8 best-practice rules, 1 advisory hook. A strategic-sourcing team for a procurement or category lead — it segments spend before it sources (the Kraljic should-cost lens), runs the sourcing event on total cost of ownership rather than unit price, manages supplier risk as a portfolio, and reads the spend cube the way a category manager who owns savings does. Inherits ravenclaude-core protocols.

Skilled Trades Contracting specialist team — 4 agents, 5 skills, 4-file cited knowledge bank, 3 templates, 5 commands, 8 best-practice rules, 1 advisory hook. An estimating-and-field-operations team for an HVAC, electrical, or plumbing contractor — it estimates to a loaded labor rate and true material cost, prices on a flat-rate book rather than guessing hours, runs the field on billable-hour efficiency and callback rate, and reads the trade P&L the way an owner who's also the best technician needs to. Inherits ravenclaude-core protocols.

Precision Agriculture specialist team — 4 agents, 5 skills, 4-file cited knowledge bank, 3 templates, 5 commands, 8 best-practice rules, 1 advisory hook. An agronomy-and-farm-operations team for a grower, farm manager, or ag retailer — it manages inputs to agronomic and economic return (not maximum yield), reads yield by management zone rather than field average, times operations to the agronomic and weather window, and reads the farm P&L per acre the way an operator who lives the margin does. Inherits ravenclaude-core protocols.

Small-Firm Legal Practice specialist team — 4 agents, 5 skills, 4-file cited knowledge bank, 3 templates, 5 commands, 8 best-practice rules, 1 advisory hook. A practice-operations team for a solo or small-firm attorney — it manages matters on realization and the billable-vs-collected gap, drafts and reviews documents as attorney decision-support, runs intake on conflict and fit before the engagement, and reads the practice P&L the way a lawyer who is also the rainmaker and the COO must. Inherits ravenclaude-core protocols.

Game Development specialist team — 4 agents, 5 skills, 4-file cited knowledge bank, 3 templates, 5 commands, 8 best-practice rules, 1 advisory hook. A production-and-design team for a game studio or indie team — it scopes to a vertical slice before a full build, designs core loops and economies that retain, runs production on milestones and risk burn-down, and reads live-ops on retention and monetization the way a team that ships and then operates a game must. Inherits ravenclaude-core protocols.

Film & Video Production specialist team — 4 agents, 5 skills, 4-file cited knowledge bank, 3 templates, 5 commands, 8 best-practice rules, 1 advisory hook. A production-management team for a producer, production company, or post house — it budgets to a defensible top-sheet, schedules to the shoot day rather than the calendar, runs the post pipeline as a dependency chain, and reads production economics the way a line producer who answers for every dollar on the day must. Inherits ravenclaude-core protocols.

Architecture & AEC specialist team — 4 agents, 5 skills, 4-file cited knowledge bank, 3 templates, 5 commands, 8 best-practice rules, 1 advisory hook. A practice-and-project team for an architect or small AEC firm — it manages the project through the design phases on a fee that matches the effort, controls scope and the change/RFI load that erodes margin, reads construction documents for coordination and constructability, and reads the firm P&L on utilization and net multiplier the way a principal who bills time must. Inherits ravenclaude-core protocols.

Senior Care Operations specialist team — 4 agents, 5 skills, 4-file cited knowledge bank, 3 templates, 5 commands, 8 best-practice rules, 1 advisory hook. An operations team for an assisted-living, memory-care, or home-care operator — it manages census and occupancy as the revenue engine, prices to acuity rather than a flat rate, staffs to acuity-based hours-per-resident-day, and reads quality and compliance as the license-and-reputation risk that a community runs on. Inherits ravenclaude-core protocols.

Hospice referral-sales / community-liaison team — 6 agents (referral-development-strategist, hospice-eligibility-educator, referral-account-manager, admissions-conversion-coach, goals-of-care-conversation-coach, hospice-sales-compliance-advisor) for a hospice sales / community-education rep who grows admissions by developing referral sources (hospitals, SNFs, physician practices, ACOs): territory planning, educating clinicians on hospice eligibility (LCD decline criteria by diagnosis — the rep educates, the physician certifies), referral-partner reviews, the referral-to-admission funnel, the goals-of-care 'hospice conversation', and clearing every touch against the Anti-Kickback / HIPAA line. 6 skills, 6 commands, a 4-doc knowledge bank (6 decision trees + glossary + LCD + compliance references), 14 best-practices, scenarios, and a runnable funnel / census / benefit-period calculator. Employer-neutral; public practice + CMS rules. Requires ravenclaude-core@>=0.7.0.

People Operations / HR specialist team — 4 agents (people-ops-lead, talent-acquisition-strategist, total-rewards-comp-analyst, people-analytics-engagement-specialist), 5 skills, 4 templates, 5 commands, 1 advisory hook, 8 best-practice rules, and a 4-file research-grounded knowledge bank. A People-Ops team for an HRBP, People-Ops leader, or founder accountable for headcount, attrition, comp, and engagement — it quantifies attrition cost and cause before acting, pays to a defensible band rather than the counteroffer, treats time-to-fill and quality-of-hire as a hiring system, and reads engagement segmented as a leading indicator of regretted exits. Inherits ravenclaude-core protocols.

Sales & Revenue Operations specialist team — 4 agents (revops-lead, pipeline-forecast-analyst, funnel-conversion-strategist, quota-territory-architect), 5 skills, 4 templates, 5 commands, 1 advisory hook, 8 best-practice rules, and a 4-file research-grounded knowledge bank. A RevOps team for a sales-ops leader or founder accountable for pipeline, forecast accuracy, and quota attainment — it reads pipeline as coverage-against-quota, forecasts from stage-weighted history, designs quota to capacity, and treats win-rate and sales-cycle as a funnel system. Inherits ravenclaude-core protocols.

Accounting & Bookkeeping Practice specialist team — 4 agents (accounting-practice-lead, close-cycle-analyst, ap-ar-cashflow-specialist, reconciliation-controls-specialist), 5 skills, 4 templates, 5 commands, 1 advisory hook, 8 best-practice rules, and a 4-file research-grounded knowledge bank. A practice-ops team for a bookkeeping/accounting practice owner or controller accountable for a timely, clean close — it closes on a cadence and tracks days-to-close, reconciles before reporting, reads AR/AP as working-capital levers, and enforces segregation of duties. Tax and audit opinions route to a licensed CPA. Inherits ravenclaude-core protocols.

Customer Support & CX Operations specialist team — 4 agents (support-ops-lead, ticket-deflection-analyst, queue-staffing-specialist, csat-quality-strategist), 5 skills, 4 templates, 5 commands, 1 advisory hook, 8 best-practice rules, and a 4-file research-grounded knowledge bank. A support-ops team for a head of support, CX manager, or founder accountable for cost-to-serve and SLA attainment — it deflects before hiring, staffs to forecast and occupancy, reads CSAT segmented, and treats backlog as arrivals-against-capacity flow. Inherits ravenclaude-core protocols.

Marketing Operations specialist team — 4 agents (marketing-ops-lead, demand-gen-funnel-analyst, attribution-analytics-specialist, martech-campaign-architect), 6 skills, 4 templates, 5 commands, 1 advisory hook, 8 best-practice rules, and a 4-file research-grounded knowledge bank. A marketing-ops team for a CMO, demand-gen analyst, or founder accountable for pipeline contribution and CAC efficiency — it reads the MQL→SQL→opp→win funnel as a system, states the attribution model before any number, gates spend on LTV:CAC and payback, and reports revenue contribution over lead volume. Inherits ravenclaude-core protocols.

Wealth Management (RIA Practice) specialist team — 4 agents (ria-practice-lead, aum-revenue-analyst, client-segmentation-specialist, compliance-cadence-specialist), 5 skills, 4 templates, 5 commands, 1 advisory hook, 8 best-practice rules, and a 4-file research-grounded knowledge bank. A practice-ops team for an RIA principal, COO, or ops lead accountable for organic growth and advisor capacity — it separates net-new flows from market appreciation, segments clients by profitability, sizes capacity by households, and treats the compliance cadence as non-negotiable. NOT investment advice; fiduciary/SEC determinations route to compliance counsel. Inherits ravenclaude-core protocols.

Accessibility Engineering specialist team — 4 agents (accessibility-lead, wcag-audit-analyst, assistive-tech-testing-specialist, inclusive-design-strategist), 5 skills, 4 templates, 5 commands, 1 advisory hook, 8 best-practice rules, and a 4-file research-grounded knowledge bank. An accessibility team for an a11y lead or product owner accountable for WCAG conformance — it picks a conformance target and measures against it, treats automated scans as a fraction of the picture, holds keyboard and screen-reader parity as the floor, reaches for semantic HTML before ARIA, and verifies contrast ratios. Inherits ravenclaude-core protocols.

Blockchain & Web3 Engineering specialist team — 4 agents (web3-architect-lead, smart-contract-security-analyst, gas-optimization-specialist, protocol-economics-specialist), 5 skills, 4 templates, 5 commands, 1 advisory hook, 8 best-practice rules, and a 4-file research-grounded knowledge bank. A Web3 team for an engineer or protocol architect accountable for a contract system that holds value — it treats deploy as irreversible and audit as the gate, holds reentrancy/access-control/arithmetic as the top vuln classes, reads gas as UX and cost, and tests invariants not just the happy path. Inherits ravenclaude-core protocols.

Embedded & IoT Engineering specialist team — 4 agents (embedded-systems-lead, firmware-rtos-specialist, power-budget-analyst, connectivity-protocol-specialist), 5 skills, 4 templates, 5 commands, 1 advisory hook, 8 best-practice rules, and a 4-file research-grounded knowledge bank. An embedded team for a firmware lead or hardware founder accountable for a fielded device — it treats the power budget as the spec, holds real-time deadlines as hard constraints, budgets flash/RAM like money, favors determinism over throughput, and requires OTA + rollback before fielding. Inherits ravenclaude-core protocols.

AI / RAG Engineering specialist team — 4 agents (rag-architect-lead, retrieval-eval-analyst, ingestion-chunking-specialist, llm-serving-cost-specialist), 5 skills, 4 templates, 5 commands, 1 advisory hook, 8 best-practice rules, and a 4-file research-grounded knowledge bank. A RAG team for an ML engineer or AI product lead accountable for answer quality and serving cost — it fixes retrieval before generation, treats chunking as a retrieval decision, evals before it ships, and reads context-window and token economics. Inherits ravenclaude-core protocols.

Behavioral Health Practice specialist team — 4 agents (behavioral-health-practice-lead, intake-access-analyst, clinical-documentation-compliance-specialist, payer-billing-specialist), 5 skills, 4 templates, 5 commands, 1 advisory hook, 8 best-practice rules, and a 4-file research-grounded knowledge bank. An operations team for a practice administrator or clinical-ops lead accountable for access, utilization, documentation compliance, and margin — it manages no-shows as a flow, reads intake-to-first-appointment access time as the conversion lever, ties documentation to compliance and billing, staffs caseload to demand, and reads payer mix as the margin driver. Inherits ravenclaude-core protocols.

FinOps & Cloud Cost specialist team — 4 agents (finops-lead, cost-allocation-analyst, commitment-planning-specialist, unit-economics-strategist), 5 skills, 4 templates, 5 commands, 1 advisory hook, 8 best-practice rules, and a 4-file research-grounded knowledge bank. A FinOps team for a cost lead or eng-finance partner accountable for cloud spend and unit economics — it allocates spend before optimizing it, reads unit economics over the total bill, treats commitments as a portfolio decision made after rightsizing, and kills waste first. Inherits ravenclaude-core protocols.

Mortgage Lending Operations specialist team — 4 agents (mortgage-lending-lead, pipeline-pullthrough-analyst, processing-cycle-specialist, compliance-quality-specialist), 5 skills, 4 templates, 5 commands, 1 advisory hook, 8 best-practice rules, and a 4-file research-grounded knowledge bank. An operations team for a production or ops leader accountable for pull-through, cycle time, capacity, and cost-to-originate — it reads pull-through as the funnel and fixes the fallout stage, ties cycle time to capacity and satisfaction, manages lock/pipeline risk, holds cost-to-originate as the unit economic, and routes every compliance question to counsel. Inherits ravenclaude-core protocols.

Pharmacy Operations specialist team — 4 agents (pharmacy-operations-lead, fill-workflow-analyst, inventory-reimbursement-specialist, adherence-clinical-specialist), 5 skills, 4 templates, 5 commands, 1 advisory hook, 8 best-practice rules, and a 4-file research-grounded knowledge bank. An operations team for a pharmacy manager or PIC accountable for throughput, safety, inventory, margin, and adherence — it holds fill throughput and verification safety as both the job, reads days-on-hand as tied-up cash and stockout risk, computes real per-script margin net of DIR fees, treats adherence as outcomes and star ratings, and staffs to script volume plus clinical-service time. Inherits ravenclaude-core protocols.

Platform Engineering (IDP) specialist team — 4 agents (platform-eng-lead, golden-path-architect, developer-experience-analyst, platform-reliability-specialist), 5 skills, 4 templates, 5 commands, 1 advisory hook, 8 best-practice rules, and a 4-file research-grounded knowledge bank. A platform-engineering team for a platform lead or eng director accountable for developer productivity and adoption — it treats the platform as a product with developers as customers, paves golden paths over mandates, measures DevEx with DORA and lead time, and runs the platform on SLOs and an error budget. Inherits ravenclaude-core protocols.

Search & Relevance Engineering specialist team — 4 agents (search-relevance-lead, relevance-tuning-analyst, indexing-mapping-specialist, query-performance-specialist), 5 skills, 4 templates, 5 commands, 1 advisory hook, 8 best-practice rules, and a 4-file research-grounded knowledge bank. A search team for a relevance engineer or platform lead accountable for search quality, latency, and conversion — it measures relevance with NDCG/MRR, treats analyzer/mapping decisions as relevance decisions, builds a judgment list before tuning, and validates online with A/B. Inherits ravenclaude-core protocols.

Automotive Dealership Operations specialist team — 4 agents (dealership-operations-lead, sales-desking-analyst, fixed-ops-service-specialist, fi-products-specialist), 5 skills, 4 templates, 5 commands, 1 advisory hook, 8 best-practice rules, and a 4-file research-grounded knowledge bank. An operations team for a dealer principal or GM accountable for total gross, fixed-ops absorption, and inventory turn — it runs the store on fixed-ops not new-car gross, manages days-supply and floorplan as carrying-cost cash, reads total gross per unit as front plus back, and treats absorption as the survival metric. Inherits ravenclaude-core protocols.

Hotel & Hospitality Operations specialist team — 4 agents (hotel-operations-lead, revenue-management-analyst, labor-productivity-specialist, guest-experience-specialist), 5 skills, 4 templates, 5 commands, 1 advisory hook, 8 best-practice rules, and a 4-file research-grounded knowledge bank. A hospitality-operations team for a GM, revenue manager, or owner accountable for RevPAR, GOPPAR, and guest satisfaction — it optimizes RevPAR as the product of ADR and occupancy, manages channel mix at net rate, reads the booking pace curve, staffs labor to occupancy, and scores profit on GOPPAR. Inherits ravenclaude-core protocols.

K-12 School Administration specialist team — 4 agents (school-administration-lead, enrollment-attendance-analyst, staffing-budget-specialist, student-outcomes-specialist), 5 skills, 4 templates, 5 commands, 1 advisory hook, 8 best-practice rules, and a 4-file research-grounded knowledge bank. An administration team for a principal, business manager, or district administrator accountable for enrollment, budget, and student outcomes — it manages enrollment as a funded pipeline, reads attendance/ADA as funding and an outcome signal, fits staffing to the budget envelope, flags chronic absenteeism early, and reads outcomes segmented. Inherits ravenclaude-core protocols.

Property Management Operations specialist team — 4 agents (property-management-lead, occupancy-leasing-analyst, maintenance-operations-specialist, noi-financial-analyst), 5 skills, 4 templates, 5 commands, 1 advisory hook, 8 best-practice rules, and a 4-file research-grounded knowledge bank. A property-operations team for a property/asset manager accountable for occupancy, NOI, and resident retention — it reads occupancy as a leasing funnel plus renewals, treats delinquency as cash with an aging clock, manages unit-turn time as cost and retention, and scores the asset on NOI not gross rent. Inherits ravenclaude-core protocols.

General-contractor project delivery team — 5 agents covering the full GC lifecycle: project P&L/billing/closeout (gc-project-lead), takeoff/bid assembly/markup (estimating-and-takeoff-analyst), CPM scheduling/critical-path/float (scheduling-engineer), submittal log/RFIs/change-order process (submittal-rfi-coordinator), and jobsite safety/JHA/OSHA hazard prevention (jobsite-safety-advisor). Ships 3 skills (estimating-and-bidding, cpm-scheduling, submittals-rfis-change-orders), 3 commands, 2 templates, a decision-tree knowledge bank, 6 best-practices, an advisory anti-pattern hook, and a stdlib calculator. Inherits ravenclaude-core protocols.

Field-service management & dispatch operations specialist team — 4 agents covering the service operating model (SLAs, contracts, dispatch-to-cash), dispatch & scheduling (skill/SLA/geo optimization, emergency vs planned), technician productivity (utilization, first-time-fix, MTTR, callbacks), and parts & inventory (truck stock, service-level tradeoffs, returns). Ships 3 skills (dispatch-and-scheduling, technician-productivity-and-first-time-fix, truck-stock-and-parts), 3 commands, 2 templates, 6 best-practices, a decision-tree knowledge bank, and an advisory hook flagging FSM anti-patterns. Domain: HVAC, plumbing, elevator, medical-device service. Inherits ravenclaude-core protocols.

Internationalization (i18n) and localization (l10n) engineering specialists — 3 agents covering i18n architecture (string externalization, ICU MessageFormat, RTL/bidi, locale data), the l10n pipeline (extraction, TMS handoff, translation memory, continuous localization), and localization QA (pseudo-localization, l10n linting in CI, visual overflow QA, locale-coverage testing). Ships 3 skills, 3 commands, 2 templates, a decision-tree knowledge bank with a 2026 i18n/TMS capability map, 6 best-practice rules, and an advisory hook flagging i18n anti-patterns (hard-coded user-facing strings, string concatenation, if-count-1 plurals, hard-coded date/number formats). Inherits ravenclaude-core protocols (Grounding, Structured Output).

Government and civic-tech delivery specialist team — 4 agents covering digital-service delivery (USDS/18F-style agile in a compliance context), public procurement (RFP/RFI response and structuring for SLED/federal), grants management (lifecycle, restricted-fund tracking, Uniform Guidance/single audit), and Section 508/WCAG accessibility plus FOIA/public-records. Ships 3 skills (public-procurement-and-rfp, grants-management, accessibility-508-and-records), 3 commands, 2 templates, a knowledge bank with bid-no-bid and FedRAMP decision trees, 6 best-practices, and an advisory hook flagging govtech anti-patterns. Inherits ravenclaude-core protocols (Grounding, Structured Output, Cited-Adjudicator).

Brick-and-mortar retail store operations team — 5 agents (store-ops-lead, merchandising-analyst, inventory-and-replenishment-analyst, labor-scheduling-analyst, loss-prevention-advisor) covering four-wall P&L and store KPIs, assortment and planogram compliance, inventory accuracy and replenishment, labor scheduling to traffic, and shrink root-cause and loss prevention. 3 skills, 3 commands, 2 templates, Mermaid decision-tree knowledge bank + 2026 capability map, 6 best-practices, and 1 advisory hook. Seams: online/DTC -> ecommerce-dtc, upstream demand planning -> supply-chain-planning, buying -> procurement-sourcing. Requires ravenclaude-core@>=0.7.0.

Supply-chain planning specialists — the plan layer between buy and move: S&OP/IBP cycle orchestration, demand forecasting (statistical + consensus, MAPE/bias, new-product, seasonality), inventory optimization (safety stock, service-level targets, ABC/XYZ, EOQ, multi-echelon, working-capital tradeoff), and MRP/replenishment. Ships 4 agents (supply-chain-planner, demand-planning-analyst, inventory-optimization-engineer, sop-process-lead), 3 skills (demand-forecasting, inventory-policy-and-safety-stock, sop-process), 3 commands, 2 templates, a decision-tree knowledge bank, 6 best-practices, and an advisory anti-pattern hook. Inherits ravenclaude-core protocols.

Cybersecurity governance, risk & compliance (GRC) team — 3 agents (grc-architect, control-and-evidence-engineer, audit-and-third-party-risk-lead) for the security-compliance program layer: framework selection & scoping (SOC 2 TSC, ISO 27001 + Annex A, NIST CSF 2.0, NIST 800-53), the ISMS, control crosswalk across frameworks, the Statement of Applicability; control implementation & operating effectiveness, policy authoring, evidence collection & continuous control monitoring, Type I vs Type II readiness; audit readiness, gap assessments, and vendor/third-party risk (TPRM tiering, SIG/CAIQ, shared-responsibility, monitoring). Decision-tree bank (5 Mermaid trees), 12 best-practices, 3 skills, 3 commands, 2 templates, 1 hook, a grc_calc.py risk/coverage/readiness calculator, scenarios. Seams: AppSec -> security-engineering; financial-regulator -> regulatory-compliance; privacy mechanics -> data-governance-privacy; cloud config -> aws/azure/gcp-cloud. Requires ravenclaude-core@>=0.7.0.

Corporate ESG & sustainability-disclosure team — 3 agents (esg-reporting-architect, ghg-accounting-analyst, disclosure-and-assurance-lead) for the reporting layer that turns sustainability obligations into a defensible, assurable disclosure: framework selection & scoping (CSRD/ESRS, ISSB IFRS S1/S2, GRI, SEC climate rule), double vs financial materiality, the reporting boundary & governance, the disclosure roadmap; GHG Protocol Scopes 1/2/3 (the 15 Scope-3 categories), emission factors, location- vs market-based Scope 2, base year, data quality; and disclosure drafting, evidence trail, limited vs reasonable assurance readiness, gap assessment. Knowledge bank (5 trees), 12 best-practices, 3 skills, 3 commands, 2 templates, 1 hook, a stdlib GHG calculator (scope2/inventory/intensity), scenarios. Seams: financial reporting -> finance; data lineage -> data-governance-privacy; filing -> regulatory-compliance. NOT a legal or financial-audit opinion. Requires ravenclaude-core@>=0.7.0.

Manufacturing-operations team for discrete and process manufacturing — 3 agents (production-planner, shop-floor-and-oee-analyst, quality-and-capa-lead) for the plan / make / control loop on the factory floor: MRP/MPS and demand-vs-capacity planning, S&OP, BOM management, lot sizing and finite scheduling (production-planner); OEE (availability x performance x quality), throughput, takt vs cycle time, Theory-of-Constraints bottleneck analysis, and MES/shop-floor downtime data (shop-floor-and-oee-analyst); SPC, nonconformance (NCR) and CAPA, inspection plans, FMEA, supplier quality, and control plans (quality-and-capa-lead). 5-tree decision-tree bank, 12 best-practices, 3 skills, 3 commands, 2 templates, 1 advisory hook, a stdlib OEE/takt/capacity calculator, scenarios. Seams: Lean/Six Sigma -> process-improvement; inferential stats / Gage R&R -> applied-statistics; sourcing -> procurement-sourcing; distribution -> fleet-logistics. Requires ravenclaude-core@>=0.7.0.

Performance- and capacity-engineering team — 3 agents (performance-architect, load-testing-engineer, profiling-and-capacity-engineer) for system performance and scalability: performance strategy and budgets, workload modeling, and SLO-linked NFR targets (performance-architect); load/stress/soak/spike testing with k6/Gatling/Locust/JMeter, open- vs closed-model workloads, ramping, think time, and test data (load-testing-engineer); profiling, flame graphs, USE/RED bottleneck triage, capacity and headroom via Little's law, and regression detection (profiling-and-capacity-engineer). Knowledge bank with 5 decision trees, a Little's-law/percentiles capacity calculator, 12 best-practices, 3 skills, 3 commands, 2 templates, 1 advisory hook, scenarios. Distinct from frontend Core Web Vitals and observability-sre SLOs. Seams: web vitals -> frontend-engineering; SLO -> observability-sre; query tuning -> database-engineering; resilience -> backend-engineering. Requires ravenclaude-core@>=0.7.0.

Corporate legal-operations & contract-lifecycle-management (CLM) team — 3 agents (legal-ops-lead, contract-review-specialist, obligations-and-renewals-analyst) for the operational layer of an in-house legal/legal-ops function: legal intake & triage and the request workflow, contract playbooks & matter management, clause libraries & redline review with fallback/standard positions and key-term extraction, and obligation/renewal/auto-renew tracking with a contract repository, metadata model, reporting & alerts. This is operational/process support, NOT legal advice — a lawyer signs off on legal judgement. Decision-tree knowledge bank (5 Mermaid trees + dated CLM map), 12 best-practices, 3 skills, 3 commands, 2 templates, 1 advisory hook, 5 scenarios, a stdlib renewal-window/cycle-time/obligation-aging calc. Seams: a law firm's own business -> legal-small-firm; supplier contracts -> procurement-sourcing; DPA/privacy clauses -> data-governance-privacy. Requires ravenclaude-core@>=0.7.0.

Exploratory data science & reproducible research team — 3 agents (exploratory-data-scientist, feature-and-modeling-engineer, research-reproducibility-engineer) for the analysis layer between raw data and a defensible result: data profiling/cleaning, EDA, hypothesis generation, communicating findings with uncertainty; feature engineering, classical modeling (regression, trees, boosting), model selection, evaluation (cross-validation, metrics) and leakage avoidance; and the reproducibility spine — notebook hygiene, pinned environments, experiment tracking, data/version control, seeds, and reproducible pipelines. 12 best-practices, decision-tree knowledge bank, 3 skills, 3 commands, 2 templates, 1 hook, scenarios bank, and stdlib-only ds_calc.py (classification/regression metrics, split-check). Seams: is-the-result-statistically-real -> applied-statistics; productionize/serve/monitor -> ml-engineering; data pipelines/warehouse -> data-platform. Requires ravenclaude-core@>=0.7.0.

Life, health & employee-benefits insurance team — 3 agents (benefits-advisor, underwriting-and-actuarial-analyst, enrollment-and-compliance-lead) for the group-benefits domain: plan design across medical / dental / vision / life / disability, funding (fully-insured vs self-funded / level-funded), rating basics (manual vs experience rating), loss ratios and the ACA medical-loss-ratio (MLR), renewal projections, and open-enrollment operations (eligibility, COBRA / HIPAA / ACA 1095 & Form 5500 basics, carrier coordination). Decision-tree knowledge bank, 12 best-practices, 3 skills, 3 commands, 2 templates, 1 advisory hook, scenarios, and stdlib-only benefits_calc.py (loss-ratio + ACA MLR flag, contribution split, renewal projection). NOT legal, tax, or actuarial advice — educational scaffolding only; a licensed broker, actuary, or ERISA counsel signs off. Seams: P&C -> insurance-pc; HR admin -> people-ops-hr; provider billing -> medical-revenue-cycle. Requires ravenclaude-core@>=0.7.0.

Pre-sales / sales-engineering team — 3 agents (sales-engineer, poc-evaluation-lead, rfp-security-response-specialist) for the technical side of a B2B sale: value-based technical discovery (MEDDPICC), demo engineering that maps to the buyer's pain (Great Demo! do-it-first), POC/pilot design with written success + exit criteria and an evaluation scorecard, and RFP/RFI plus security-questionnaire response (SIG / CAIQ / VSA, SOC 2 mapping, a reusable trust-answer library). 5 skills, a 4-doc knowledge bank with 4 Mermaid decision trees (qualify-the-deal, RFP go/no-go, build-the-POC?, demo depth), 5 templates, 5 best-practices, a scenarios bank, and 1 advisory anti-pattern hook. Distinct from sales-revops (CRM/forecast/quota ops) and product-management (what to build); security claims route to ravenclaude-core/security-reviewer. Requires ravenclaude-core@>=0.7.0.

Desktop-app-engineering team — 4 agents (desktop-architect, electron-engineer, tauri-engineer, desktop-platform-engineer) for cross-platform desktop apps: the Electron-vs-Tauri-vs-native-vs-PWA decision, a hardened process/security model (Electron contextIsolation + IPC allow-lists; Tauri capabilities/permissions + Rust commands), reproducible packaging, code-signing + notarization on Windows and macOS, safe auto-update, and native OS integration (tray, menus, notifications, file associations, deep links, secure on-device storage). 5 skills, a decision-tree knowledge bank (framework-choice + IPC-security trees + a dated 2026 capability map), 12 best-practices, 4 templates, 4 commands, 1 advisory hook. Seams: renderer UI -> frontend-engineering, the backend/API -> api-engineering/backend-engineering, tokens/OAuth -> auth-identity, signing/notarization in CI -> devops-cicd, the mobile sibling -> mobile-engineering. Requires ravenclaude-core@>=0.7.0.

Technical-program-management team — 3 agents (technical-program-manager, cross-team-dependency-manager, program-launch-coordinator) for delivering a program of projects across teams: program charter + measurable outcomes, dependency mapping and critical-path/integration risk, a RAID-driven program plan, launch-readiness reviews with written go/no-go criteria, staged rollout, and exec status comms that lead with decisions and asks (not activity). 3 skills, a 2-doc knowledge bank with Mermaid decision trees (TPM-vs-PM-vs-EM, escalate-or-not, go/no-go), 4 best-practices, 5 templates, 4 commands, and 1 advisory anti-pattern hook. Distinct from project-management (a single project/plan) and engineering-management (people/teams); execution lands in devops-cicd, observability-sre, and the relevant engineering plugins. Requires ravenclaude-core@>=0.7.0.

Developer-relations / DevRel team — 3 agents (developer-advocate, devrel-content-engineer, developer-community-manager) for the developer experience of a product with an API/SDK: time-to-first-success (getting-started) audits, sample-app and SDK-quickstart design, a DX content strategy, conference talks + CFP abstracts, community health, DX metrics (activation funnel), and the product-feedback loop that fixes the product instead of writing around it. 5 skills, a 2-doc knowledge bank with Mermaid decision trees (advocate-vs-docs-vs-community, fix-the-product-or-document-it, content-format choice), 7 best-practices, 6 templates, 5 commands, and 1 advisory anti-pattern hook. Distinct from technical-writing-docs (reference docs), marketing-operations (demand gen), and product-management (what to build). Requires ravenclaude-core@>=0.7.0.

Trust & Safety team — 2 agents for content-moderation and abuse-detection work. The trust-safety-policy-lead designs the policy taxonomy + enforcement ladder, the human-review operations layer (queue prioritization, reviewer wellness, escalation, appeals/due-process), and the measurement frame (prevalence, enforcement precision/recall, time-to-action SLA, appeal-overturn rate). The abuse-detection-engineer builds the detection stack: signals, rules-vs-ML classifiers, reviewer queues, thresholds tied to precision/recall. 3 skills, a 2-doc knowledge bank (a Mermaid enforcement decision tree + a T&S metrics catalogue with formulas), 2 templates, 3 best-practice rules, and 1 advisory hook. Seams: classifier-eval validity → applied-statistics; PII → data-governance-privacy; account-takeover → security-engineering; LLM-classifier build → claude-app-engineering. Enforcement is proportional; appeals are due process; measure prevalence, not just volume. Requires ravenclaude-core@>=0.7.0.

Geospatial / GIS engineering team — 2 agents for the engineering of location data. The geospatial-data-engineer owns spatial data modeling and storage (PostGIS, GiST/SP-GiST indexes, SRID and projection hygiene — EPSG:4326 vs 3857, geometry vs geography), spatial SQL and analysis (ST_ functions, spatial joins, nearest-neighbor, buffers), and geospatial pipelines (GDAL/OGR, geocoding, routing engines like OSRM/Valhalla). The mapping-visualization-engineer owns the serving and visualization layer (vector tiles/MVT, pg_tileserv/Martin/Tegola, MapLibre/Mapbox GL styling, the GeoJSON-vs-vector-tile tradeoff). 4 skills, a projection decision tree, a dated 2026 stack reference, 2 templates, 3 best-practice rules, and 1 advisory hook that flags geometry-without-SRID and degree-distance smells. Seams: warehouse/ELT → data-platform; OLTP schema → database-engineering; map UI → frontend-engineering. Always store an SRID; index geometry with GiST; vector tiles over GeoJSON at scale. Requires ravenclaude-core@>=0.7.0.

WordPress / CMS engineering team — 3 agents (wordpress-architect, wordpress-developer, wordpress-ops-engineer) for building, extending, and operating WordPress done right: the build-approach decision (classic vs block/FSE theme, plugin vs theme vs must-use, headless/decoupled vs traditional, single vs multisite), secure block & theme & plugin development (block.json, hooks/filters, WP_Query, the REST API, sanitize-in/escape-out, $wpdb->prepare, nonce + capability checks), and operations (page + object cache/Redis, security hardening, safe updates with staging & backups, migrations). 5 skills, a decision-tree knowledge bank (4 Mermaid trees + a dated 2026 stack map), 8 best-practices, 3 templates, 3 commands, 1 advisory hook. Seams: decoupled front-end -> frontend-engineering, non-WP backend/APIs -> backend-engineering, infra perf budget -> performance-engineering, formal security verdict -> security-engineering. Requires ravenclaude-core@>=0.7.0.

Event-management team — 3 agents (event-strategist, event-operations-lead, event-marketing-revenue) for planning and running conferences, webinars, and field/community events across in-person, virtual, and hybrid formats: goals/KPIs and the go/no-go gate, format and audience and budget/break-even model, sponsorship strategy and fulfilled-promise delivery, minute-by-minute run-of-show and show-flow, venue/vendor/AV logistics, registration funnel and attendee ops, contingency and single-point-of-failure plan-Bs, promotion and ticketing funnel, and post-event ROI measured against the goal you set. This is the event craft, distinct from generic delivery — schedule/RAID/stakeholder management lives in project-management. 5 skills, a decision-tree knowledge bank (format + break-even + sponsorship-tier + go/no-go trees, plus a dated 2026 tooling/benchmark map), 8 best-practices, 3 templates, 3 commands, 1 advisory hook. Seams: schedule/RAID -> project-management. Requires ravenclaude-core@>=0.7.0.

Outpatient physical-therapy / rehab clinic operations team — 3 agents (clinic-operations-lead, clinical-documentation-compliance, billing-and-revenue) for the practice-ops + documentation + billing craft of a PT/OT/SLP outpatient clinic: scheduling & capacity and plan-of-care visit cadence, no-show management, defensible POC documentation and medical necessity, certification/recertification timing, the Medicare therapy-threshold + KX concept, CPT timed codes and the 8-minute rule, modifiers (GP/KX/59), and denial prevention. 5 skills, a decision-tree knowledge bank (4 Mermaid trees + a dated 2026 reference), 8 best-practices, 3 templates, 3 commands, 1 advisory hook. ADVISORY only — not medical, legal, or billing advice; every payor/regulatory specific carries a retrieval date + verify-at-use, no patient PII. Seams: medical-revenue-cycle, behavioral-health-practice. Requires ravenclaude-core@>=0.7.0.

Optometry / eye-care practice operations team — 3 agents (practice-operations-lead, optical-dispensary-manager, front-office-billing) for the three engines of an eye-care practice: the clinical exam flow (scheduling, pretesting, lane flow, recall/recare cadence, capacity), the optical dispensary (frames & lens inventory, capture rate, lab orders, managed-vision-care formularies), and the front-office billing split that makes optometry distinct — medical-vs-vision routing, eligibility, CPT/coding for eye exams, payor mix, claims and denial triage. ADVISORY operations knowledge, not medical/legal/coding/billing advice; payor/coding specifics carry a retrieval date + verify-at-use; no PII/PHI. Distinct model from dental-practice and veterinary-practice (cross-linked); shares the revenue-cycle seam with medical-revenue-cycle. 5 skills, a decision-tree knowledge bank (4 Mermaid trees + dated 2026 reference), 8 best-practices, 3 templates, 3 commands, 1 advisory hook. Requires ravenclaude-core@>=0.7.0.

CLI-tooling-engineering team — 4 agents (cli-architect, cli-implementation-engineer, tui-engineer, cli-distribution-engineer) for command-line tools and TUIs that feel native to the shell: the command/subcommand + flag/positional surface, config precedence (flags > env > file > default), the output contract (human by default, --json on demand, exit codes as an API, data->stdout/diagnostics->stderr, NO_COLOR/TTY detection), stdin, signal handling, TUIs (Ink / Bubble Tea / Textual / ratatui) with a non-TTY fallback, shell completions, and distribution (single static binary, Homebrew / Scoop / winget / npm / pipx, --version + update path). 5 skills, a knowledge bank (command-surface + output/exit-code + framework + distribution decision trees + a dated 2026 map), 12 best-practices, 4 templates, 4 commands, 1 advisory hook. Seams: service logic -> backend-engineering, release/signing -> devops-cicd, GUI sibling -> desktop-app-engineering, docs -> technical-writing-docs. Requires ravenclaude-core@>=0.7.0.

Realtime-collaboration-engineering team — 3 agents (collab-architect, sync-engine-engineer, presence-and-transport-engineer) for multiplayer / collaborative-editing systems (Figma/Notion/Docs): the merge model (CRDT vs OT vs last-writer-wins, by data shape), the shared-document model, offline edits + reconnection/merge, presence & awareness kept OUT of the persisted document, transport (WebSocket vs WebRTC, client-server vs SFU vs mesh), and scaling the sync server (doc sharding, snapshots/compaction, access control at the boundary). 5 skills, a knowledge bank (CRDT-vs-OT + transport/topology Mermaid trees, durable consistency concepts, a dated 2026 tooling map), 8 best-practices, 4 templates, 3 commands, 1 advisory hook. Engineering craft, not legal/product advice; library specifics carry a date + verify-at-use. Seams: UI -> frontend-engineering; sync service/store -> backend-engineering; op-log fan-out -> data-streaming-engineering; latency -> performance-engineering. Requires ravenclaude-core@>=0.7.0.

Residential real-estate brokerage operations team — 3 agents (residential-brokerage-lead, listing-and-transaction-coordinator, buyer-agent-advisor) for the engines of a residential brokerage: brokerage/team P&L and the lead-to-close pipeline (commission splits/caps, recruiting & retention, agency/fair-housing compliance, lead-gen), the listing lifecycle plus transaction coordination (CMA, prep, MLS, marketing, contract-to-close timeline, contingencies, deadlines), and buyer representation (needs analysis, showings, offer & negotiation, financing, closing). Ships 4 skills, a decision-tree knowledge bank (4 Mermaid trees + a dated 2026 reference), 5 best-practices, 2 templates, and 2 commands. ADVISORY operations knowledge, not legal/financial/real-estate-license advice; fair-housing sensitive; no client PII; commission norms, contingency periods, and protected-class lists are volatile and jurisdiction-specific — each carries a retrieval date + verify-at-use. Requires ravenclaude-core@>=0.7.0.

Independent auto-repair shop operations team — 3 agents (auto-repair-shop-lead, service-advisor-estimator, technician-workflow-manager) for a repair shop's three engines: shop P&L economics (effective labor rate, tech productivity-efficiency-proficiency, labor + parts gross profit, comeback rate, car count); the service-advisor front counter (write-up, digital vehicle inspection, inspection-to-estimate, approval, declined-work follow-up, ethical upsell); and technician workflow (dispatch, flat-rate vs actual hours, WIP/RO aging, parts staging, comeback control). Ships 4 skills, a decision-tree knowledge bank (4 Mermaid trees + a dated 2026 reference), 5 best-practices, 2 templates, 2 commands. Operations/financial decision-support, not legal/tax/OEM-warranty advice; labor-rate norms, productivity benchmarks, and parts-matrix figures carry a retrieval date + verify-at-use; no customer PII. Seams to automotive-dealership, fleet-logistics, and skilled-trades-contracting. Requires ravenclaude-core@>=0.7.0.

Salon / spa / barbershop operations team — 3 agents (salon-spa-operations-lead, front-desk-booking-manager, stylist-chair-economics-advisor) for the three engines of a service-chair business: the owner-level P&L (chair and room utilization, service mix, retail attach, membership and package revenue, the staffing model), the front desk (online booking, no-show / late-cancel policy and deposits, rebooking at checkout, waitlist, reminders), and provider economics (commission tiers vs booth rent vs hourly, back-bar / product cost, prebooking, clientele building and retention). Operations and financial decision-support, not legal, tax, or employment-classification advice; volatile benchmarks (utilization, retail-attach, no-show norms) carry a retrieval date + verify-at-use; no client PII. Ships 4 skills, a decision-tree knowledge bank (4 Mermaid trees + a dated 2026 reference), 5 best-practices, 2 templates, and 2 commands. Requires ravenclaude-core@>=0.7.0.

Gym / boutique-fitness-studio operations team — 3 agents (fitness-studio-operations-lead, membership-retention-manager, class-schedule-coach-ops) for the three engines of a fitness business: the membership P&L (growth, churn/retention, member LTV, utilization, ancillary revenue from PT, retail, and café), the retention machine (onboarding, attendance triggers, churn prediction and saves, win-back, referral, pricing/tiers), and the class grid (scheduling on demand, instructor utilization and pay, capacity/fill, waitlist, no-show, sub coverage). ADVISORY operations knowledge, not legal/financial/medical advice; volatile specifics (churn norms, LTV math, class-fill and instructor-pay benchmarks) carry a retrieval date + verify-at-use; no member PII. Ships 4 skills, a decision-tree knowledge bank (4 Mermaid trees + a dated 2026 reference), 5 best-practices, 2 templates, 2 commands. Seams to retail-store-operations, restaurant-operations, and people-operations-hr. Requires ravenclaude-core@>=0.7.0.

Title, escrow, and settlement operations team — 3 agents (title-escrow-lead, title-examiner, closing-settlement-coordinator) for the three engines of a settlement operation: the order-to-policy workflow (open->search->exam->clear->close->record->policy) with ALTA/CFPB/TRID coordination and wire-fraud controls; title search and examination (chain of title, liens/encumbrances, the commitment, exceptions/requirements, curative); and escrow settlement (CD/statement coordination, closing/signing, good-funds discipline, disbursement, recording, funding, and trust-account protection). ADVISORY operations knowledge, not legal/title-underwriting/financial advice; jurisdiction- and underwriter-specific rules, ALTA/CFPB/TRID specifics, and recording requirements are volatile and carry a retrieval date + verify-at-use; wire-fraud sensitive; no PII. 4 skills, decision-tree knowledge bank (4 Mermaid trees + dated 2026 reference), 5 best-practices, 2 templates, 2 commands. Requires ravenclaude-core@>=0.7.0.

Childcare / early-education center operations team — 3 agents (childcare-center-lead, enrollment-and-family-manager, classroom-ratio-compliance-advisor) for the three engines of an early-education center: the operations & tuition model (enrollment/waitlist, capacity vs licensed ratios, staffing to ratio, family retention, P&L), the enrollment & family funnel (tour-to-enroll conversion, waitlist, paperwork, family communication, tuition & CCDF/state subsidy billing), and ratio & licensing compliance (ratio and group-size by age, licensing readiness, staff qualifications, health & safety, incident documentation). 4 skills, a decision-tree knowledge bank (4 Mermaid trees + a dated 2026 reference), 5 best-practices, 2 templates, 2 commands. ADVISORY operations knowledge, not legal, licensing, or financial advice; state-specific ratios, group sizes, and subsidy rules are volatile and carry a retrieval date + verify-at-use; no child or family PII. Requires ravenclaude-core@>=0.7.0.

Higher-education administration operations team — 3 agents (higher-ed-administration-lead, enrollment-management-strategist, student-success-advisor) across the three engines of a college/university admin operation: institutional strategy (enrollment strategy, the budget/net-tuition-revenue model, retention/completion, cross-functional coordination, accreditation), enrollment management (the inquiry->apply->admit->yield->melt funnel, yield & discount-rate modeling, financial-aid leveraging), and student success (persistence, early-alert, advising, at-risk intervention, DFW-course analysis). Ships 4 skills, a decision-tree knowledge bank (4 Mermaid trees + a dated 2026 reference), 5 best-practices, 2 templates, 2 commands. ADVISORY operations knowledge, not legal, financial-aid-compliance, or academic-policy advice; volatile specifics (funnel benchmarks, discount-rate norms, metric definitions) carry a retrieval date + verify-at-use; FERPA-aware — no student PII. Requires ravenclaude-core@>=0.7.0.

Travel agency / tour-operator operations team — 3 agents (travel-agency-operations-lead, itinerary-and-booking-specialist, supplier-and-commission-manager) for the three engines of a leisure travel business: agency P&L and revenue model (commission vs service fee vs markup, supplier mix, host splits, E&O risk), itinerary design and multi-supplier booking (FIT vs group, quoting, changes, documentation, service recovery), and supplier + commission management (net vs commissionable, BSP/ARC settlement, commission tracking and recovery, consortia). ADVISORY operations knowledge, not legal, tax, or financial advice; supplier fare rules, commission norms, cancellation penalties, and seller-of-travel requirements are volatile and supplier-/jurisdiction-specific — each carries a retrieval date + verify-at-use; no traveler PII. 4 skills, a decision-tree knowledge bank (4 Mermaid trees + a dated 2026 reference), 5 best-practices, 2 templates, 2 commands. Requires ravenclaude-core@>=0.7.0.

Robotics & autonomous-systems engineering team — 3 agents (robotics-architect-lead, ros-motion-planning-engineer, perception-and-autonomy-engineer) across the three engines of a robot program: system architecture (ROS 2 computation graph & DDS, compute/sensor selection, the real-time vs non-real-time split, safety architecture, sim-to-real), the motion stack (ROS 2 nodes/topics/actions, MoveIt/Nav2 planning, kinematics, PID/MPC control, coordinate frames/TF), and perception & autonomy (sensor fusion, SLAM, EKF state estimation, localization, behavior-tree/state-machine autonomy). Ships 4 skills, a decision-tree knowledge bank (4 Mermaid trees + a dated 2026 reference), 5 best-practices, 2 templates, 2 commands. Engineering decision-support, not functional-safety certification advice: safety-standard pointers (ISO 10218/13849), DDS/distro landscape, and sensor/compute specifics carry a retrieval date + verify-at-use; no PII. Requires ravenclaude-core@>=0.7.0.

AR/VR/XR spatial-computing engineering team — 3 agents (xr-architect-lead, xr-interaction-engineer, spatial-rendering-engineer) for the three engines of an XR build: system architecture (target selection across standalone / PC-VR / WebXR / mobile-AR, engine choice across Unity / Unreal / native / WebXR, OpenXR-first strategy, perf-budget and comfort/safety architecture), interaction (hand / controller / gaze input, sim-sickness-aware locomotion, 3D UI, grab/physics, accessibility), and spatial rendering & performance (frame budget, reprojection, foveated rendering, occlusion/anchors/passthrough for AR, draw-call batching, thermal). Ships 4 skills, a decision-tree knowledge bank (4 Mermaid trees + a dated 2026 reference), 5 best-practices, 2 templates, 2 commands. Engineering judgment, not legal/safety-certification advice; the device/runtime/engine landscape is volatile — every version, headset spec, and per-eye perf number carries a retrieval date + [verify-at-use]; no PII. Requires ravenclaude-core@>=0.7.0.