carl-tools

Consolidate and dedupe contacts across macOS/iCloud/Google/Zoho/VCF into one address book with a provenance-aware review UI. Optional, opt-in Phase B ranks who you talk to from iMessage and builds research dossiers only on people you explicitly name.

Research a real person (friend or colleague) from public sources into a confidence-marked, cross-linked Obsidian People dossier.

Multi-agent project pre-mortem — parallel agents with different failure-finding mandates, synthesized into ranked risks with mitigations.

Build a personal AI profile from your digital footprint — portrait, working-with-me guide, and compact system prompt for any AI assistant.

Get validation from a different AI model before committing major changes — detects available LLM CLIs and routes to the best one.

Run and triage Django/DRF security smoke checks into real risks, hygiene, and false positives using clean-scan discipline.

Autonomously handle GitHub PR review comments — evaluate, implement HIGH/MEDIUM changes, run tests, commit, reply to all threads.

Audit chezmoi dotfiles for drift, unmanaged files, and broken agent skill symlinks across Claude Code, Codex, Gemini, and other harnesses.

Audit whether a product feels trustworthy or unsafe — covering permissions, privacy, billing, file mutation, and silent-failure surfaces.

Simulate the support emails, reviews, and complaints a launch will generate, then identify product fixes that cut maintenance drag.

Red-team a product's onboarding and first-run experience to find where new users get confused, think it's broken, or abandon setup.

Generate a WiFi QR code PNG phones can scan to join a network instantly.

Design parallel isolated test lanes for desktop apps and local tools with shared state — maps collision surfaces and splits non-colliding test lanes.

Review code through four empathy lenses — user, machine, developer, support — to surface quality issues that pure technical review misses.

Multi-model brainstorming room for product strategy and experience design — serious plus whimsical, multi-altitude, multi-round ideation.

Run the full pre-launch gauntlet (first-contact → support-storm → trust-audit → pre-mortem) and get a single GO/CAUTION/NO-GO verdict.

Capture a technical or product decision with chosen option, rejected alternatives, and rationale — in a format a future agent can read to reconstruct context.

Analyze a real failure — reconstruct what happened, find root cause, extract learnings, and feed them back into the skill collection to prevent recurrence.

Ruthlessly compress brainstorm output into a shippable MVP — classify ideas as DELETE / MOCK / ALREADY EXISTS / SHIP and surface the shortest path to launch.

Generate user-facing changelog entries from git history — plain language, audience-segmented, with optional CHANGELOG.md update.

Scan Claude/Codex session logs to find agent behavior patterns, Toolsmith adoption gaps, repeated frustrations, and candidates for new skills/tools.

Verify commands across this machine and named SSH hosts, comparing versions, install paths, config, and behavior with clean local/remote evidence.

Run a CLI/app release end-to-end: verify state, update changelog/version, test packaging, commit, tag, push, publish, and verify installs.

Audit CLI/app status output for confusing, inconsistent, or trust-eroding wording; verify idempotent repeated runs and align labels across clients.

Run a repeatable before/after visual QA loop for local web/app UI changes, using stable screenshots, artifact folders, and concise visual findings.

Repeatable multi-LLM codebase hardening sweeps: map under-reviewed surfaces, patch fixes, document learnings, and loop.