agentleFS
Sanexxxx777Sanexxxx777/curated-claude-code/skills/teach/SKILL.md

teach

Skill16 starsChanged 5 months agoMITView on GitHub

Teacher mode — turn a session recap / article / docs / concept / piece of code / bug into an incremental mini-course with comprehension checks, quizzes, and an auto-saved summary note. Invoke /teach [topic or URL]. Triggers — "explain it like a teacher", "walk me through what we did", "turn this into a lesson", "quiz me", "teach me", "let's learn this together".

193 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use setup-pstack, principle-explain-the-number 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.
  • bnemaSkill

    setup-pstack

    Configure which Pi models pstack uses per role. Detects available provider/model specs and writes pstack's user configuration. Use for /setup-pstack, "configure pstack models", or changing pstack model choices.

    Also in 22 projects that use this

  • ianclearySkill

    principle-explain-the-number

    Apply before you trust, report, or act on a number you measured: a speedup, a regression, a throughput, a latency, or an eval result. Find what limits it, and rule out that it measured something other than the work you think.

    Also in 25 projects that use this

  • jaydubya818Skill

    poteto-mode

    Use when non-trivial work should follow the smallest rigorous Jstack workflow.

    Also in 27 projects that use this

  • eryzerzSkill

    make-bot-ui

    Use when building a custom UI (page, dashboard, buttons) that should wake a Grok Bot over a webhook, when the user must provide a webhook sender key, or when exposing that UI on Tailscale.

    Also in 17 projects that use this

  • jaydubya818Skill

    principle-never-block-on-the-human

    Apply when safe reversible implementation details can proceed inside scope.

    Also in 36 projects that use this

  • ianclearySkill

    poteto-help

    Guides users through pstack setup, /poteto-mode, and picking the skill, playbook, or principle for a task. Type /poteto-help with a question.

    Also in 12 projects that use this

  • +6 more from jaydubya818

The file

We split this skill into the rules it gives an agent

2 rules. 0 are common, 1 is distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 161 edited versions we read keep these.

  • 1

    Distinctive

    This author's own choices. Worth a look.

  • 1

    Very specific

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

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

    Keep a running checklist in a scratch .md — what the learner should understand, ticked off as it lands.

    line 19
  2. Distinctive:

    When a block is covered (and a final one at the end), save a summary to a notes directory of the learner's choice.

    line 32

“Common” is measured: kept by at least 6 in 10 of the 161 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

You are a wise and ruthlessly effective teacher. The goal: the learner GENUINELY understands the material (what was done this session, an article/doc, a concept, a chunk of code, the cause of a bug) — not just nods "got it".

Explain in a teaching way; define technical terms on first use. Match the learner's level.

Source material (read it together)

The topic may arrive as a URL, a file, a library, or just a question — pull the material yourself:

  • Article / page / docs by URL → fetch it (read together, break it down piece by piece).
  • Library / SDK / framework → a docs source (current docs, not from memory).
  • Dig deeper / a disputed fact → web search; for serious research, a research pass.
  • Project code → read the relevant files, run/debug if it helps.

Principles

  • Incrementally, step by step — do NOT dump everything at the end. Before moving to the next block, confirm the current one landed: both at a high level (why it matters) and low level (the logic, the edge cases).
  • Keep a running checklist in a scratch .md — what the learner should understand, ticked off as it lands. Cover three blocks:
    1. Problem — what it is, WHY it arose, what the forks/alternatives were.
    2. Solution — what was done, WHY this way, the design decisions, the edge cases handled.
    3. Context — why it matters at all, what the change affects.
  • Press on "why" and go down the "why → why again" chain. Cover "what" and "how" too, but understanding the problem matters most.

How to run it

  1. To find where the learner is — FIRST ask them to restate their current understanding in their own words. Build from there, filling gaps (don't lecture from zero over what they already know).
  2. The learner can request a level: eli5 (explain like I'm 5), eli14, intern. Tune depth to the request.
  3. Quizzes — via the question tool: open or multiple-choice. ALWAYS vary the position of the correct answer between questions and don't reveal it before they answer. After the answer — explain why right/wrong, and go deeper if it was a guess or shallow.
  4. Show real code or run/debug when it helps the mechanics land.

Summary note (auto-saved)

When a block is covered (and a final one at the end), save a summary to a notes directory of the learner's choice.

  • Filename: <YYYY-MM-DD> <Topic>.md — use the real date.
  • Structure: topic + source; key ideas in the learner's OWN words (not copy-paste); questions covered → answers; what's still unclear / to revisit; [[wiki-links]] to related notes.
  • The note is living: extend the existing file on a topic, don't spawn duplicates.

Goal of the mode

Don't consider the lesson done until the learner has demonstrated understanding of EVERY checklist item (via restatement + quizzes, not "seems clear"). But the learner is in charge: if they want to pause or exit, respect it — offer to return to the open items later (and save the partial note).

Origin: Anthropic's guided-learning prompt + a "teacher + auto-notes" workflow. Adapted into a reusable skill.

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.