agentleFS
dymchenkkodymchenkko/claude-study-agent/.claude/skills/learn/SKILL.md

learn

Skill2 starsChanged 7 days agoMITView on GitHub

Tutor a specific topic from the course materials with short explanations and practical micro-tasks, then record progress. Use when the user wants to learn, understand or study a named topic.

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, 3 are distinctive, and 2 are very specific to this project.

  • 0

    Common

    Most of the 170 edited versions we read keep these.

  • 3

    Distinctive

    This author's own choices. Worth a look.

  • 2

    Very specific

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

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

    If it has a Diagrams entry, diagram tasks follow the Diagrams rules in ~/Study/CLAUDE.md.

    line 10
  2. Distinctive:

    Diagnose (1 question): ask one quick question to see what I already know.

    line 16
  3. Distinctive:

    Close: ask me to explain the whole topic in 3–4 sentences (teach-back).

    line 22
  4. Very specific:

    Update memory as described in ~/Study/CLAUDE.md (progress, mistakes, session log).

    line 23
  5. Distinctive:

    Stop any time I say stop — but always save memory first.

    line 27

“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 a topic

  1. Resolve subject and topic. Read the subject's CLAUDE.md, progress.md, mistakes.md. If it has a Diagrams entry, diagram tasks follow the Diagrams rules in ~/Study/CLAUDE.md.
  2. Find the topic in my materials. Run ~/Study/.tools/study search <Subject> "<topic in plain words>" -k 6 (meaning-based, works across languages; cite the (file loc) it prints). Then Grep converted/ for exact terms, formulas and names the search missed. Read the matching pages/slides/transcript sections. Open the original in materials/ if diagrams or formulas matter. If the best scores are low (< ~0.6), the topic is probably not in my materials: say so before using general knowledge.
  3. Diagnose (1 question): ask one quick question to see what I already know. Skip what I know.
  4. Break the topic into 3–6 small ideas (show the list as a mini roadmap). For each idea:
    • explain in ≤ 150 words with a concrete example and citation,
    • give ONE micro-task (2–5 min): predict, fill-in, spot-the-error, tiny worked example, explain-back, match/sort, mini calculation — vary the type,
    • grade (✅/⚠️/❌), one-sentence feedback, adapt difficulty.
  5. Close: ask me to explain the whole topic in 3–4 sentences (teach-back). Grade it.
  6. Update memory as described in ~/Study/CLAUDE.md (progress, mistakes, session log). New topic starts at Level from the teach-back (❌→1, ⚠️→2, ✅→3), Interval 1, Next review tomorrow. Then log it with study log … --kind lesson (plus --kind drawing if a diagram was graded), as in the Event log rule.

Stop any time I say stop — but always save memory first.

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.