メニュー
Self-improvement skill for evolving Claude Code configuration. Use when you notice repeated mistakes, want to add new workflows, or optimize the development experience.
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
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.
Inspect repository layout with tree and find, compare to AGENTS.md conventions, and fix misplaced or overly flat generated files. Use when auditing folder structure, after scaffolding or bulk file generation, when output looks flat, or when asked where code/tests/docs should live. Supports inspecting the repository root or a specified subdirectory.
Run CodeQL security/quality analysis and fix findings. Use when the user asks to run CodeQL, security scan, static analysis, or fix CodeQL findings.
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.
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.
| name | improve-claude-config |
| description | Self-improvement skill for evolving Claude Code configuration. Use when you notice repeated mistakes, want to add new workflows, or optimize the development experience. |
This skill enables Claude Code to evolve and improve its own configuration based on observed patterns, user feedback, and development needs.
Invoke this skill when:
Read and understand the current configuration:
# Shared instructions (all agents)
read_file AGENTS.md
# Claude-only tail (skills, agents, learnings)
read_file CLAUDE.md
# List all skills
list_dir .claude/skills/
# List all agents
list_dir .claude/agents/
# View current hooks
read_file .claude/settings.json
| Pattern | Action |
|---|---|
| Repeated explanation | Add to AGENTS.md or create a skill |
| Recurring mistake | Add rule to AGENTS.md (shared) or create a skill |
| Manual repetitive task | Create a hook |
| Complex workflow | Create a skill |
| Specialized task delegation | Create an agent |
For repo-wide conventions or gotchas every agent should follow, edit AGENTS.md.
For Claude-only notes (slash commands, hook behavior), append under ## Claude Code or Recent learnings in CLAUDE.md.
.claude/skills/<skill-name>/SKILL.md with standard structure.Add to .claude/settings.json and create the corresponding script in .claude/hooks/.
settings.json.