self-learning
Skill5 starsChanged 29 days agoMITView on GitHub
After an audit/check finds a bug its own checklist should have caught, close that gap in the skill itself — not just fix the code. Run right after reporting/fixing any audit finding.
We split this skill into the rules it gives an agent
4 rules. 0 are common, 4 are distinctive, and 0 are very specific to this project.
0
Common
Most of the 3 edited versions we read keep these.
4
Distinctive
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 12
If an existing bullet already covers this general class of check, sharpen/specialize it with the missed detail — don't add a new bullet …
- Distinctive: line 15
Only add a brand-new bullet if nothing existing is even adjacent.
- Distinctive: line 16
Keep additions to 1-2 lines.
- Distinctive: line 19
If a skill file is drifting toward bloat (bullets turning into short essays), that's a signal to prune/merge, not to keep appending — …
“Common” is measured: kept by at least 6 in 10 of the 3 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Self-learning — close the gap in the skill that missed it
For each confirmed finding from an audit/check pass:
- Identify which skill's checklist should have caught this — don't stop at fixing the code.
- If an existing bullet already covers this general class of check, sharpen/specialize it with the missed detail — don't add a new bullet next to it.
- Only add a brand-new bullet if nothing existing is even adjacent.
- Keep additions to 1-2 lines. No walkthroughs, no multi-sentence examples — these files compound over many passes; a short parenthetical example is fine, a paragraph is not.
- If a skill file is drifting toward bloat (bullets turning into short essays), that's a signal to prune/merge, not to keep appending — periodically re-read the whole file and tighten instead of only adding.
Other versions10 projects use a version of this.
Word for word · 3
- Grinv/steam-games-mcp★ 4100% same
- Grinv/mal-mcp★ 2100% same
- Grinv/anilist-mcp-server★ 1100% same
Edited · 0
None found.
Wrote their own version · 7
- Kulaxyz/self-learning-skills★ 956same name
- ychampion/claude-self-learning★ 8same name
- EvianEvans/rumor-checker★ 2same name
- VibeEngineering-LLC/agent-ops-doctrine★ 1same name
- VodouAI/OS★ 1same name
- Abdox-menara/guard-skills★ 0same name
- viryoke/skills★ 0same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository9 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- changelog-styleSkill
- docs-consistency-checkSkill
- fixture-accuracy-checkSkill
- live-auditSkill
- prompt-checkSkill
- releaseSkill
- tool-description-checkSkill
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.