agentleFS
ProjectAJ14ProjectAJ14/eklavya/skills/learn/SKILL.md

learn

Skill29 starsChanged 22 days agoMITView on GitHub

Run a structured Eklavya teaching session on a topic, ordered by prerequisites and calibrated to what the developer already knows.

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

6 rules. 0 are common, 3 are distinctive, and 3 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.

  • 3

    Very specific

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

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

    If the topic isn't a known domain, ask which of the existing domains is closest, or teach from first principles and upsert_concepts as you …

    line 15
  2. Distinctive:

    Start from what they already know — the profile tells you what that is.

    line 19
  3. Distinctive:

    If they miss it, that concept is not done.

    line 22
  4. Very specific:

    Stop when you hit five concepts or they've had enough.

    line 24
  5. Very specific:

    If they set focus: "learn" at the top, say so in the closing line, and mention /eklavya:mode as the way back out.

    line 26
  6. Distinctive:

    Never lecture for more than two exchanges without asking something.

    line 28

“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

/eklavya:learn <topic>

Teach $ARGUMENTS properly. This is a lesson, not a quiz — but it is still a conversation, and it still records what was learned.

First, offer to make it stick. A one-off lesson ends when the conversation does. If they want this topic to keep coming back as they work, set_config with focus: "learn" and focus_topic: "$ARGUMENTS" — from then on quizzes plan from this topic, and use their real code as the example wherever the work touches it. Ask once, in one line; if they decline or say nothing, just teach the lesson. Do not set it silently: it changes what every later session asks about.

  1. get_learner_profile for the topic's domain. Note suggested_tier, and note known — those concepts are already theirs. Reference them; do not teach them.
  2. get_concept_graph for that domain — it is required — with include_mastery: true and unmastered_only: true. The order returned is the teaching order: prerequisites come before what depends on them.
  3. If the topic isn't a known domain, ask which of the existing domains is closest, or teach from first principles and upsert_concepts as you go.

Then, for each concept in order, and at most 5 per session:

  • Start from what they already know — the profile tells you what that is. Never re-explain a mastered prerequisite; reference it in a clause and move on.
  • Explain in a short paragraph, then show it in code from this repo if it appears here. Concrete beats general.
  • Ask one question to check it landed, and grade it with record_attempt. For the tier and — crucially — for what has already been asked, call get_session_quiz_plan with slugs: [...] for the concepts in this lesson and ignore_cooldown: true. Its tier_to_ask beats suggested_tier, and its asked_before is what keeps a lesson from re-asking a question from a past one.
  • If they miss it, that concept is not done. Come at it from a different angle before moving on.

Stop when you hit five concepts or they've had enough. Close with what to review next and when — next_review from the recorded attempts tells you.

If they set focus: "learn" at the top, say so in the closing line, and mention /eklavya:mode as the way back out. A standing setting they forgot they made is a setting that feels like a bug later.

Never lecture for more than two exchanges without asking something.

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.

Reviews can't be read right now.

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.