メニュー
Continuously improve AI workflows and capabilities. Use when reflecting on process, identifying friction, or after completing significant work.
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
| name | self-improvement |
| description | Continuously improve AI workflows and capabilities. Use when reflecting on process, identifying friction, or after completing significant work. |
You are responsible for making yourself and the system better over time.
1. NOTICE - Identify friction, repetition, or failure
2. ANALYZE - Why did this happen? What's the root cause?
3. DESIGN - What's the minimal fix?
4. IMPLEMENT - Create skill/hook/agent update
5. TEST - Verify it works
6. DOCUMENT - Log in megg
7. SHARE - Tell Tako if significant
After every significant task:
When you notice:
Periodically:
| Scope | Location | When |
|---|---|---|
| Personal | ~/.claude/skills/ | Your workflows only |
| Project | .claude/skills/ | Team needs it |
| System | Update agent definitions | Core behavior change |
When creating improvement, log it:
## YYYY-MM-DD - Improvement: [Name]
**Friction:** What problem was encountered
**Root Cause:** Why it happened
**Solution:** What was created/changed
**Location:** Where the fix lives
**Verification:** How to know it works
When you notice something but can't fix now:
~/.claude/skills/self-improvement/ideas.md"Every friction point is an improvement opportunity."
Good systems get better over time. You're not just executing tasks - you're building the machine that executes tasks.
Questions to ask:
Then build toward that.
Read Claude Code documentation to learn about features, capabilities, hooks, skills, MCP, subagents, and how to use Claude Code effectively.
Close a dev-cycle session, capture learnings, and optionally commit. Use when development work is complete and ready to wrap up.
Fully autonomous development mode. Spec in, production-ready software out. Claude makes decisions, uses agents, commits locally. Only stops for hard blockers.
Run QA checks on current work. Tests, linting, type checking, build verification. Use during or after development to catch issues early.
Release candidate preparation. Final checks before merge - QA, security, review, changelog. The last gate before shipping.
Security audit with Sentinel. Checks for vulnerabilities, secrets, dependencies, and security best practices. Use before shipping or when working on auth/crypto/sensitive areas.