local

Team sprint execution infrastructure: agents, hooks, protocols, and kanban pipeline

Sprint retrospective infrastructure: agent interviews via SubagentStop hook, session analysis, action cards, and retrospective kanban board

Pre-work ideation with a visual decision canvas. Generates divergent ideas, launches a local web UI for annotation, then synthesizes decisions into a concrete plan

Plugin, agent, and skill management tooling: bump-version, scaffold, new-agent, new-skill, optimize-agents, update-plugins, create-worktree

Drupal-specific development skills and agents (DDEV, Analysis, Validation, Scaffolding)

CLI wrapper skills: Slack, Jira, GitHub, TestRail, vault operations, log analysis, and file utilities

Process automation skills: prioritize, scout, knowledge-check, deploy checklist, Obsidian maintenance, and personal productivity

Automated Drupal error monitoring and self-healing pipeline: watches logs, triages errors into curated Beads tickets, autonomously implements fixes in isolated git worktrees, and notifies on ready-to-review fixes

Knowledge-work verbs as standalone compositional primitives: frame, gather, understand, synthesize, interrogate, experiment, teach. NotebookLM + Workflow fan-out; preflight-first input contracts; no orchestrator

Process engineering methodology: maps process topology, makes directed fixes, runs improvement experiments, and accumulates process lint rules. Domain-agnostic — each plugin owns its own :improve skill.

Passive knowledge capture pipeline — Karpathy-derived LLM Wiki with Monitor-driven multi-domain ingest. Feeds land in raw/, agents compile them into a cross-linked Obsidian wiki, memory evolves via confidence decay and graph-aware consolidation.