self-improve-prompt-design
Write self-improve prompts that sync expertise files with codebase reality. Use when creating maintenance workflows for agent experts, designing validation logic, or implementing the LEARN step of Act-Learn-Reuse.
npx skills add majiayu000/claude-skill-registry --skill self-improve-prompt-design --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
# Self-Improve Prompt Design Guide for writing self-improve prompts that maintain expertise file accuracy. ## Core Purpose Self-improve prompts teach agents HOW to learn. They: - Validate expertise against actual codebase (source of truth) - Identify drift between mental model and reality - Update expertise files automatically - Enforce line limits to prevent context bloat - Run after every ACT step in Act-Learn-Reuse ## When to Use - Creating maintenance workflows for agent experts - Designing validation logic for expertise files - Implementing the LEARN step of Act-Learn-Reuse - Writing self-improve prompts for new domains - Reviewing or debugging existing self-improve prompts - Setting up git diff conditional checks for efficiency ## Self-Improve Prompt Template ````markdown --- description: Sync {domain} expertise with codebase reality argument-hint: [check-git-diff] --- # Self-Improve: {Domain} Expert Maintain expertise accuracy by validating against codebase implementation. ## Arguments - `$1`: check_git_diff flag (optional, default: "true") - "true": Only check files changed in git diff - "false": Full rescan of all domain files ## Configuration - **EXPERTISE_FILE**: `.claud
- Core Purpose
- When to Use
- Self-Improve Prompt Template
- Self-Improve Complete: {domain}
- Summary
- Changes Made
- Expertise Health
- Recommendations
- Key Design Principles
- 1. Conditional Git Diff Check
- 2. Line Limit Enforcement
- 3. Validation Before Update
- 4. Actionable Output
- Validation Patterns
What does the self-improve-prompt-design skill do?
Write self-improve prompts that sync expertise files with codebase reality. Use when creating maintenance workflows for agent experts, designing validation logic, or implementing the LEARN step of Act-Learn-Reuse.
How do I install it?
Run `npx skills add majiayu000/claude-skill-registry --skill self-improve-prompt-design --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From majiayu000/claude-skill-registry, a repository with 534 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.