agentleFS
TimCodes04TimCodes04/second-brain/.claude/skills/teach/SKILL.md

teach

Skill1 starsChanged 51 days agoMITView on GitHub

Teach a lesson as an adaptive Socratic dialogue instead of static reading — pretest first, build on what the user already knows, and record the session into the lesson note.

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

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

  • 0

    Common

    Most of the 161 edited versions we read keep these.

  • 2

    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. Distinctive:

    Run the worked example as a guided problem: the user attempts each step, you steer with the smallest useful hint.

    line 23
  2. Distinctive:

    Keep it warm, precise, two-way.

    line 25
  3. Very specific:

    If the lesson was unread, set status: read and recompute the course's lessons_done.

    line 33

“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

/teach <lesson or topic> [--course <slug>]

Dialogue is the primary encoding mode; reading is the fallback. Read docs/pedagogy.md and docs/vault-schema.md first. Vault: <vault>.

1. Prepare (silent)

Locate the lesson (full or stub) and read it, its concepts, cited source pages, and the course home. Read Profile.md for at most one honest relevance hook (guardrail in pedagogy.md — seasoning, never steering). Note the lesson's objectives; they define what the dialogue must cover — dialogue changes the delivery, never the coverage.

2. Pretest

3–5 rapid diagnostic questions spanning the objectives, one message, quick answers expected. Tell the user wrong answers are free — pretesting improves the learning that follows even when answers miss. Use the result to set pace: segments the user demonstrably knows get compressed to a confirmation, not a walkthrough.

3. Teach the dialogue

Segment by segment:

  • Open each segment with a prediction question ("what should happen if…?"), let the user commit, then teach from their answer — build on what's right, name precisely what's wrong.
  • Run the worked example as a guided problem: the user attempts each step, you steer with the smallest useful hint.
  • Comprehension-check every few minutes with one-line retrieval questions; adapt live — struggling → smaller steps and a concrete analogy; cruising → compress and pose a transfer question instead.
  • Keep it warm, precise, two-way; never lecture for more than a few paragraphs without handing the turn back.

4. Close the loop

The user summarizes the lesson in their own words; correct the summary. Then write the artifacts:

  • Stub lesson → write the full lesson note now (standard pedagogy structure and full coverage — the note must stand alone for later re-reading), plus its card file if missing.
  • Existing lesson → leave the exposition intact.
  • Either way, append a ## From our session — YYYY-MM-DD section to the lesson note: pretest outcome, 2–6 bullets of this user's wrong turns, aha-moments, and the analogies that landed (these personalized traces are gold for later review).
  • If the lesson was unread, set status: read and recompute the course's lessons_done; a quizzed/mastered lesson keeps its status. Bump updated:. Mastery stays untouched — /quiz owns it; recommend quizzing in 1–3 days, not today (spacing beats immediate testing).

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.