// End-of-session capture of failures, surprises, and lessons so agent behavior and repo config improve. Use after non-trivial work; skip trivial sessions unless something went wrong.
Build the project and automatically fix any build errors, compilation failures, or type mismatches. Use when the project fails to build, shows "broken" states, or after making significant changes.
Run CodeQL security/quality analysis and fix findings. Use when the user asks to run CodeQL, security scan, static analysis, or fix CodeQL findings.
Self-improvement skill for evolving Claude Code configuration. Use when you notice repeated mistakes, want to add new workflows, or optimize the development experience.
Run linters and fix violations, formatting errors, or style mismatches using Trunk. Use when code quality checks fail, before submitting PRs, or to repair "broken" linting states.
Safely upgrade Node.js dependencies in pnpm workspaces. Use when asked to "upgrade dependencies", "update packages", "check for updates", or fix version mismatches.
Scan for vulnerable dependencies and CVEs via pnpm lint:security (Trunk Trivy/OSV-scanner), optional pnpm security:grype or pnpm lint:all (Trunk-all plus Grype). Use for dependency CVE checks, security-scoped lint, or post-bump verification.
| name | postmortem |
| description | End-of-session capture of failures, surprises, and lessons so agent behavior and repo config improve. Use after non-trivial work; skip trivial sessions unless something went wrong. |
Record what broke, what was confusing, and what should change so the same mistake is less likely next time. Prefer small, concrete follow-ups (one rule, one hook, one skill tweak) over large rewrites.
AGENTS.md / .cursor/rules/), hook (.claude/settings.json), skill (.claude/skills/), agent (.claude/agents/), or no change if noise. Prefer one high-value change over a list of maybes.CLAUDE.md when the lesson is stable and repo-wide.Use /improve-claude-config when the follow-up is primarily evolving .claude/ layout or automation.