self-improving-agent
Repo-local meta-skill for improving Xiaobai Skills over time. Use after significant project changes, user feedback, install failures, promotion experiments, or repeated workflow friction to update AGENTS.md, capture project-specific gotchas, or propose new repo-local skills. Do not use globally or after every small task.
npx skills add Tyuts/xiaobai-skills --skill self-improving-agent --agent codex
Same command for any agent — swap --agent for claude-code, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
# Self-Improving Agent This is a repo-local skill for Xiaobai Skills. It helps the project learn from real work without turning every task into expensive reflection. Use it only when one of these happens: - A user reports an install or curation failure. - A promotion experiment teaches something reusable. - The recommended starter stack changes. - The agent repeatedly searches for the same repo knowledge. - A workflow repeats enough to deserve a repo-local skill. - A release reveals missing docs, checks, or restore steps. Do not use it after every small edit. ## Step 1: Diagnose The Learning Ask: 1. Did the repo structure or command flow change? 2. Did the user correct a behavior that should persist? 3. Did an install command fail in a way future agents should know? 4. Did a starter-stack decision prove good or bad? 5. Did a repeated workflow emerge? If the answer is no, make no changes. ## Step 2: Choose The Right Artifact - Update `AGENTS.md` for short repo rules, commands, gotchas, or decision history. - Update `README.md` for user-facing install or positioning changes. - Update `ROADMAP.md` for future work. - Update `docs/promotion-kit.md` for launch and marketing learnings. -
- Step 1: Diagnose The Learning
- Step 2: Choose The Right Artifact
- Step 3: Update AGENTS.md Safely
- Step 4: Create Repo-Local Skills Sparingly
- Step 5: Validate
- Anti-Patterns
What does the self-improving-agent skill do?
Repo-local meta-skill for improving Xiaobai Skills over time. Use after significant project changes, user feedback, install failures, promotion experiments, or repeated workflow friction to update AGENTS.md, capture project-specific gotchas, or propose new repo-local skills. Do not use globally or after every small task.
How do I install it?
Run `npx skills add Tyuts/xiaobai-skills --skill self-improving-agent --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 Tyuts/xiaobai-skills, a repository with 50 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.