agentleFS
Sign inStart free
d-o-hubd-o-hub/github-template-ai-agents/.agents/skills/learn/SKILL.md

learn

Skill2 starsChanged 10 days agoMITView on GitHub

Extract non-obvious session learnings, patterns, and discoveries into scoped AGENTS.md files. Use this skill when the user wants to extract learnings after completing non-trivial tasks, or when they say "extract learnings", "save patterns", "update AGENTS.md", or whenever the session has produced insights that should be captured for future reference — even if they just say "what did we learn" or "save this for later". Not for agents-md, skill-creator.

195 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

5 rules. 0 are common, 2 are distinctive, and 3 are very specific to this project.

  • 0

    Common

    Most of the 170 edited versions we read keep these.

  • 2

    Distinctive

    This author's own choices. Worth a look.

  • 3

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Place learnings in the most specific file:

    line 38
  2. Distinctive:

    Every new non-obvious insight must be recorded in three places:

    line 47
  3. Very specific:

    Verbose Log: Add a full LESSON-NNN entry to agents-docs/LESSONS.md with Issue/Root Cause/Solution.

    line 48
  4. Very specific:

    Distilled Note (scoped): Add a 1–3 line note to the nearest AGENTS.md (this is what learn automates).

    line 49
  5. Very specific:

    Distilled Note (project-wide): Add a 1–3 line note to agents-docs/self-learning-rules.md under ## Recent Project-Wide Learnings.

    line 50

“Common” is measured: kept by at least 6 in 10 of the 170 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

Extract non-obvious session learnings into scoped AGENTS.md files to preserve knowledge across sessions.

When to Use

Activate after completing a non-trivial task to capture insights that would otherwise be lost.

Instructions

What to Capture (Non-Obvious Only)

  • Hidden relationships between files or scripts not obvious from code.
  • Execution paths that differ from what the code appears to do.
  • Non-obvious config, env vars, or flags (see agents-docs/ENVIRONMENT_VARIABLES.md).
  • Debugging breakthroughs where error messages were misleading.
  • Files that must change together (e.g., AGENTS.md + agents-docs/AVAILABLE_SKILLS.md when adding skills).
  • Build/test commands not documented in README.
  • Architectural constraints discovered at runtime.

What NOT to Capture

  • Obvious documentation or standard behavior.
  • Duplicates of existing entries.
  • Verbose explanations or session-specific notes.

Scoping Rules

Place learnings in the most specific file:

  • Project-wide: agents-docs/self-learning-rules.md (under ## Recent Project-Wide Learnings).
  • Script-specific: scripts/AGENTS.md.
  • Skill-specific: .agents/skills/<name>/AGENTS.md.

Also write a fuller LESSON-NNN entry to agents-docs/LESSONS.md for archival.

Triple-Write Requirement

Every new non-obvious insight must be recorded in three places:

  1. Verbose Log: Add a full LESSON-NNN entry to agents-docs/LESSONS.md with Issue/Root Cause/Solution.
  2. Distilled Note (scoped): Add a 1–3 line note to the nearest AGENTS.md (this is what learn automates).
  3. Distilled Note (project-wide): Add a 1–3 line note to agents-docs/self-learning-rules.md under ## Recent Project-Wide Learnings.

Format

  • 1–3 lines per insight in AGENTS.md.
  • Fits within MAX_LINES_AGENTS_MD=200 constraint.
  • Bulleted list under a "Learnings" or "Context" section.

See Also

  • agents-md — AGENTS.md best practices
  • skill-creator — Create and improve skills

Rationalizations

RationalizationReality
"This is obvious, no need to record it"What seems obvious today becomes non-obvious in a new session; document runtime discoveries.
"I'll remember this later"Session context is lost on termination; if it's not written down, it's gone.

Red Flags

  • Capturing obvious or already-documented behavior as a new learning
  • Placing learnings in the wrong scope (project-wide for script-specific insights)
  • Skipping the dual-write to LESSONS.md for non-obvious findings

References

  • agents-docs/LESSONS.md - Legacy project-wide lessons.
  • AGENTS.md - Root agent guidance and constraints.

Voice & Context

  • Default: professional + blog
  • Reference: voice-profiles skill for definitions and auto-detection.

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.

Check your setup, free