Self-learning skill for Claude: let the agent capture its own hard-won patterns

kulaxyz1 pts0 comments

GitHub - Kulaxyz/self-learning-skills: A self-improving skill for AI coding agents (Claude Code, Cursor, AGENTS.md): recognize a hard-won golden path in a session and harvest it into a reusable skill/rule for next time. · GitHub

/" data-turbo-transient="true" />

Skip to content

Search or jump to...

Search code, repositories, users, issues, pull requests...

-->

Search

Clear

Search syntax tips

Provide feedback

--><br>We read every piece of feedback, and take your input very seriously.

Include my email address so I can be contacted

Cancel

Submit feedback

Saved searches

Use saved searches to filter your results more quickly

-->

Name

Query

To see all available qualifiers, see our documentation.

Cancel

Create saved search

Sign in

/;ref_cta:Sign up;ref_loc:header logged out"}"<br>Sign up

Appearance settings

Resetting focus

You signed in with another tab or window. Reload to refresh your session.<br>You signed out in another tab or window. Reload to refresh your session.<br>You switched accounts on another tab or window. Reload to refresh your session.

Dismiss alert

{{ message }}

Kulaxyz

self-learning-skills

Public

Notifications<br>You must be signed in to change notification settings

Fork

Star

main

BranchesTags

Go to file

CodeOpen more actions menu

Folders and files<br>NameNameLast commit message<br>Last commit date<br>Latest commit

History<br>2 Commits<br>2 Commits

.claude-plugin

.claude-plugin

.cursor/rules

.cursor/rules

skills/self-learning

skills/self-learning

.gitignore

.gitignore

AGENTS.md

AGENTS.md

LICENSE

LICENSE

README.md

README.md

skills.sh.json

skills.sh.json

View all files

Repository files navigation

self-learning-skills

A self-improving skill for AI coding agents. Works with Claude Code, Cursor,<br>and any agent that reads an AGENTS.md / standing-instructions file.

Every session you do hard debugging or rediscover the same thing — how do I<br>reach the prod DB? where do the creds live? what's the deploy command? how do I<br>verify this live? — and that hard-won knowledge evaporates when the session<br>ends. The next session starts from zero and re-learns it.

self-learning fixes that. It teaches your agent to recognize the moment it<br>has just earned a reusable golden path and persist it where the tool will<br>auto-load it next time — so the next session starts already knowing the route<br>instead of rediscovering it.

It's a meta-skill: it doesn't do the work, it captures how the work got<br>done — including the failures , since skipping a known dead-end next session<br>is often worth more than the win itself.

The loop (same everywhere)

Recognize the moment — a task that only worked after several tries, a<br>non-obvious command, a project fact you didn't know up front, an operational<br>workflow likely to recur, or you simply saying "remember this".

Capture it, no prompt needed — it acts on the cue immediately, picks the<br>scope/name itself, and tells you afterward. The procedure is captured (not<br>a one-off answer), plus a "what didn't work" note.

Reuse — next session the entry loads automatically, by skill/rule<br>description or because the instructions file is always read.

What differs per tool is only where knowledge is persisted and how it's<br>auto-loaded:

Tool<br>Persists golden paths to<br>Auto-loads via

Claude Code / Agent Skills clients<br>a new skills//SKILL.md<br>skill description matching

Cursor<br>a new .cursor/rules/learned/.mdc<br>rule description / globs

Codex, Zed, Aider, …<br>AGENTS.md (or project notes/memory)<br>always-read instructions

Install

npx — recommended (works with 70+ agents)

Uses the community skills CLI, which<br>installs into whatever agents it detects — Claude Code, Cursor, Codex, Cline,<br>OpenCode, and more:

npx skills add kulaxyz/self-learning-skills # this project (auto-detects agents)<br>npx skills add kulaxyz/self-learning-skills -g # global — all your projects<br>npx skills add kulaxyz/self-learning-skills -a claude-code # a specific agent

Try it once without installing:

npx skills use kulaxyz/self-learning-skills --skill self-learning | claude

Claude Code plugin

/plugin marketplace add kulaxyz/self-learning-skills<br>/plugin install self-learning@self-learning-skills

Manual

Copy the files into place yourself<br>> AGENTS.md">git clone https://github.com/kulaxyz/self-learning-skills

# Claude Code — global (or into a project's .claude/skills/ to share via git)<br>cp -R self-learning-skills/skills/self-learning ~/.claude/skills/

# Cursor — auto-loads .cursor/rules/ (harvested rules land in .cursor/rules/learned/)<br>mkdir -p .cursor/rules<br>cp self-learning-skills/.cursor/rules/self-learning.mdc .cursor/rules/

# Any AGENTS.md agent (Codex, Zed, Aider, Gemini CLI, …)<br>curl https://raw.githubusercontent.com/kulaxyz/self-learning-skills/main/AGENTS.md >> AGENTS.md

Triage: skill, memory, or skip?

It won't bloat your config with one-liners. Each lesson is routed:

Lesson<br>Where it goes

A multi-step, reusable procedure/workflow<br>a new skill / rule

A single fact or one-line correction<br>lightweight...

skills self learning agents claude cursor

Related Articles