claude-mdlisted

How to write and update the repository's CLAUDE.md (commands, architecture map, conventions, Definition of Done, forbidden actions) and its template. Load at kickoff, legacy assessment, when a retro adds a rule, or when CLAUDE.md is missing or its commands no longer match reality.
jaewhi-park/GARAGISTE · ★ 1 · AI & Automation · score 75

Install: claude install-skill jaewhi-park/GARAGISTE

# CLAUDE.md CLAUDE.md is injected into every session and every subagent. It must be short and true. ## Principles - Under 300 lines. Procedures go in skills; facts go here. - List only commands that were actually run and passed (confirmed by team-verifier). - Add rules only when something actually went wrong (retro output). No generalities. - Always separate quick verification (under one minute) from full verification. ## Template ```` # <Project> One-line summary (details: docs/CHARTER.md · legacy: docs/ASSESSMENT.md, docs/REBUILD_PLAN.md) ## Language - <ko | en | ...> (responses, questions and documents; set with /lang; agents mirror the CEO's language when unset) ## Commands - setup: - quick verification (under one minute — relevant tests, lint, typecheck): - full verification: - parity harness (legacy): - build/run: ## Architecture map - <directory> — responsibility, entry points ## Conventions - naming, error handling, logging, configuration, commit messages ## Definition of Done - quick verification passes; new logic has tests - a logic-change step diff is 300 lines or less (state the split reason if exceeded) - mechanical changes (scaffold/gen/mechanical/deps) are separate commits with kind and reproduction command; regeneration diff is zero - docs, ADRs and docs/DECISIONS.md updated - review APPROVE (lenses scale with risk: default correctness+security; 4 lenses for risk:high, large or integration diffs) ## Operating profile - (filled by /hire: budget tier /