agentleFS
jcurbelojcurbelo/agent-seed/.claude/skills/learn/SKILL.md

learn

Skill8 starsChanged 8 months agoMITView on GitHub

Self-improvement routine. Review memory, prune stale entries, identify gaps, evolve agents. Run weekly or after significant sessions.

194 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use add-anydoc, add-clidash and 10 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • TomGranotSkill

    add-anydoc

    Add local office-document-to-Markdown conversion to NanoClaw agent containers with the pinned Firecrawl AnyDoc CLI. Use when agents need to read attached Word, PowerPoint, Excel, OpenDocument, RTF, EPUB, CSV, or text-based PDF files without uploading them to a hosted parser.

    Also in 5 projects that use this

  • TomGranotSkill

    add-clidash

    Add clidash — a zero-dependency, read-only web dashboard that derives its tabs and tables at runtime from any CLI that lists resources as JSON. Ships pre-wired for NanoClaw's ncl CLI (agent groups, sessions, channels, users, roles), plus message-activity charts, a log tail, and a read-only file viewer for group skills/CLAUDE.md/profiles.

    Also in 5 projects that use this

  • seek888Skill

    open-gstack-browser

    Launch GStack Browser — AI-controlled Chromium with the sidebar extension baked in. Opens a visible browser window where you can watch every action in real time. The sidebar shows a live activity feed and chat. Anti-bot stealth built in. Use when asked to "open gstack browser", "launch browser", "connect chrome", "open chrome", "real browser", "launch chrome", "side panel", or "control my browser". Voice triggers (speech-to-text aliases): "show me the browser".

    Also in 11 projects that use this

  • Saqlain-811Skill

    ios-sync

    Regenerate the iOS debug bridge against the latest upstream gstack templates. (gstack)

    Also in 6 projects that use this

  • MicrosoftSkill

    add-codex

    Use Codex (CLI + AppServer) as the full agent provider — planning, tool orchestration, native compaction, MCP tools, session resume — in place of the Claude Agent SDK. ChatGPT subscription or OPENAI_API_KEY. Per-group via agent_provider. Distinct from using OpenAI as an MCP tool (where Claude remains the planner).

    Also in 6 projects that use this

  • MicrosoftSkill

    add-deltachat

    Add DeltaChat channel integration via @deltachat/stdio-rpc-server. Native adapter — no Chat SDK bridge. Email-based messaging with end-to-end encryption.

    Also in 6 projects that use this

  • +5 more from TomGranot
  • +1 more from microsoft

The file

We split this skill into the rules it gives an agent

11 rules. 0 are common, 4 are distinctive, and 7 are very specific to this project.

  • 0

    Common

    Most of the 169 edited versions we read keep these.

  • 4

    Distinctive

    This author's own choices. Worth a look.

  • 7

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    All memory files: memory/

    line 9
  2. Very specific:

    All context files: context/

    line 10
  3. Very specific:

    All agent definitions: .claude/agents/

    line 11
  4. Very specific:

    All scoped rules: .claude/rules/

    line 12
  5. Very specific:

    Read memory/improvements.md.

    line 17
  6. Distinctive:

    Do agent definitions match what the user actually asks for?

    line 24
  7. Distinctive:

    Remove stale entries (30+ days, never referenced)

    line 32
  8. Very specific:

    Keep files under their max_lines limit

    line 34
  9. Distinctive:

    Verify every page is linked from its parent index

    line 35
  10. Very specific:

    When the gap calls for a brand-new skill (recurring user request with no matching slash command), invoke /write-a-skill to scaffold it with …

    line 46
  11. Distinctive:

    Commit with a clear message describing what was improved

    line 52

“Common” is measured: kept by at least 6 in 10 of the 169 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.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

/learn - Self-Improvement

Step 1: Read Everything (in parallel)

  1. All memory files: memory/
  2. All context files: context/
  3. All agent definitions: .claude/agents/
  4. All scoped rules: .claude/rules/
  5. All skills: .claude/skills/

Step 2: Check Improvements Backlog

Read memory/improvements.md. Act on anything pending:

  • Missing agents -> create them
  • Incorrect context -> fix it
  • Stale rules -> update them

Step 3: Cross-Reference

  • Do agent definitions match what the user actually asks for?
  • Are there gaps? (recurring requests with no matching agent)
  • Are rules covering the right paths?
  • Are skills working correctly?
  • Is the voice profile accurate?

Step 4: Prune Memory

  • Remove stale entries (30+ days, never referenced)
  • Merge duplicate entries
  • Keep files under their max_lines limit
  • Verify every page is linked from its parent index

Step 5: Apply Updates

Make any warranted changes to:

  • Agent definitions (new agents, updated routing)
  • Context files (voice, work)
  • Rules (new scopes, updated constraints)
  • Skills (improved workflows)
  • CLAUDE.md (if rules need updating)

When the gap calls for a brand-new skill (recurring user request with no matching slash command), invoke /write-a-skill to scaffold it with the right frontmatter, size limits, and README registration — don't hand-roll the SKILL.md.

Step 6: Commit

  1. Create branch: feat/learn-YYYY-MM-DD
  2. Stage all changes
  3. Commit with a clear message describing what was improved
  4. Push and create PR (if gh is available)

Report: what you updated, what you pruned, what gaps remain.

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.