Turn friction you just hit into a concrete change to the workflow, so the same problem doesn't recur.
The English summary is being prepared. Showing the original description.
See how to installReview the instructions the agent will receive before you install.
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 the user 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.
No reviews yet. Tell others what you thought.
No login needed. Share how it worked for you, ask a question, or note where it did not run.
No comments yet. Be the first to write one.
Branch and commit conventions that keep an agent's work reviewable — one branch per task, main stays clean, nothing force-pushed.
The English summary is being prepared. Showing the original description.
Look up how Claude Code itself works — hooks, skills, subagents, MCP, plugins, settings — from the official docs, so answers come from the current spec instead of memory.
The English summary is being prepared. Showing the original description.
Design better agents, skills and hooks for Claude Code, checking the current spec instead of guessing at fields.
The English summary is being prepared. Showing the original description.
Run a feature end to end — scout the code, plan it, build it, and keep a session file so a closed terminal doesn't lose the thread.
The English summary is being prepared. Showing the original description.
Close out a session — summarise what changed, capture what was learned, and prepare the commit.
The English summary is being prepared. Showing the original description.
Hand over a spec and walk away — plans, builds, tests and audits on its own, stopping only at a real blocker.
The English summary is being prepared. Showing the original description.