learning
Skill1 starsChanged 10 months agoMITView on GitHub
Self-improving agent patterns. Use when detecting corrections, proposing rules, or managing learned behaviors.
8 other projects use a version of this.
Adopted by
Most recently taken up by
- DaraBoth/skilljmskilltheir own version, first seen Nov 8, 2026
- HsuanYuLee/polaristheir own version, first seen Nov 5, 2026
- akumidv/ai_akmontheir own version, first seen Nov 1, 2026
- marco-souza/skillstheir own version, first seen Jun 13, 2026
- qkitzero/kage-bunshintheir own version, first seen Apr 5, 2026
- zinan92/skills-repotheir own version, first seen Mar 15, 2026
Other versions8 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 8
- alxyrgin/secondbrain_ai★ 17same name
- HsuanYuLee/polaris★ 5same name
- marco-souza/skills★ 3same name
- amoraleda/skills★ 2same name
- DaraBoth/skilljmskill★ 2same name
- akumidv/ai_akmon★ 1same name
- qkitzero/kage-bunshin★ 1same name
- zinan92/skills-repo★ 1same 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.
The file
We split this skill into the rules it gives an agent
5 rules. 0 are common, 4 are distinctive, and 1 is very specific to this project.
0
Common
Most of the 5 edited versions we read keep these.
4
Distinctive
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 33
If MCP is connected, you have these tools:
- Distinctive: line 45
Detect corrections automatically: - When user says "actually...", "no, use...", "don't do X", log it
- Distinctive: line 46
Propose rules for patterns: - If you see repeated corrections, propose a rule
- Very specific: line 47
Check rules periodically: - Use get_rules to remind yourself of learned behaviors
- Distinctive: line 48
Don't over-rule: - Not every correction needs a permanent rule
“Common” is measured: kept by at least 6 in 10 of the 5 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
Claude Learner - Self-Improvement Skill
You have access to claude-learner, a system that turns corrections into permanent rules.
When to Use
- User corrects you ("No, don't do X, do Y instead")
- You make a repeated mistake
- User expresses a preference
- A better pattern is discovered
Available Commands
| Command | What It Does |
/learner:status | Check daemon and rules status |
/learner:rules | List all rules |
/learner:approve <id> | Approve a pending rule |
/learner:reject <id> | Reject a pending rule |
/learner:start | Start the learning daemon |
/learner:stop | Stop the learning daemon |
MCP Tools
If MCP is connected, you have these tools:
log_correction- Log a correction eventpropose_rule- Propose a new ruleget_rules- Get active rulesget_pending_rules- Get rules awaiting approvalapprove_rule- Approve a rulereject_rule- Reject a ruleget_stats- Get learning statistics
Best Practices
- Detect corrections automatically - When user says "actually...", "no, use...", "don't do X", log it
- Propose rules for patterns - If you see repeated corrections, propose a rule
- Check rules periodically - Use
get_rulesto remind yourself of learned behaviors - Don't over-rule - Not every correction needs a permanent rule
Example Flow
User: "Don't use rm, use trash instead"
1. Log correction: log_correction({
pattern: "using rm command",
correction: "use trash instead of rm",
context: "file deletion"
})
2. If pattern repeats, propose rule: propose_rule({
content: "Always use `trash` instead of `rm` for file deletion",
trigger: "rm command usage"
})
3. Rule goes to pending → user approves → permanently activeDoes 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.

