agentleFS
zznabilzznabil/lean-agent-skill-collection/skills/teach/SKILL.md

teach

Skill1 starsChanged 3 months agoMITView on GitHub

Teach a concept or skill through a plain explanation, worked example, active recall, and bounded practice. Use when the user asks to learn, understand, practise, study, or be quizzed—not for a quick reference answer alone.

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

8 rules. 0 are common, 8 are distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 161 edited versions we read keep these.

  • 8

    Distinctive

    This author's own choices. Worth a look.

  • 0

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Use ASD-STE100-inspired short, active sentences, ISO 704-inspired stable terms and Diátaxis organisation when useful, without claiming …

    line 8
  2. Distinctive:

    Path: Use a Diátaxis tutorial when useful.

    line 12
  3. Distinctive:

    Mechanism: Use a Feynman-style explanation: familiar words, a plain mechanism and one concrete example explaining its key step.

    line 15
  4. Distinctive:

    Example: Before unsupported novice or unfamiliar work, show a worked example.

    line 17
  5. Distinctive:

    Retention: Use retrieval questions and spaced follow-up only when retention beyond the immediate task is a goal.

    line 21
  6. Distinctive:

    When the requested teaching artifact is an agent-facing procedure, apply the same mechanism, chunking, and worked-example methods.

    line 26
  7. Distinctive:

    Use BCP 14 only for normative force.

    line 32
  8. Distinctive:

    Before risky work, warn, add any needed hold point and verify the safe state.

    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

Communication kernel

Number ordered actions; group long lists without hiding required items. After interruption or task change, restore relevant completed/current/pending state, not repetitive status each turn. Preserve language, exact tokens, formats, permissions and evidence. Never invent estimates or diagnose readers. Show verified outcomes and factual errors; give a concrete next action only if work remains. Trusted root AGENTS.md governs when loaded; otherwise use this standalone fallback. Never claim root activation without evidence. Use ASD-STE100-inspired short, active sentences, ISO 704-inspired stable terms and Diátaxis organisation when useful, without claiming formal conformance. Lead with the answer or learning goal. Use only necessary detail. Omit routine Summary headings and closing recaps; place an optional, useful TL;DR first. For substantial learning, apply CAST UDL Guidelines 3.0, the IES Organizing Instruction and Study practice guide, and established cognitive-load, worked-example, self-explanation, and retrieval-practice research in proportion to the task.

  1. Goal. State the learning goal. Infer prior knowledge safely from context. Distinguish immediate success, retention, transfer or their combination.
  2. Path. Use a Diátaxis tutorial when useful. Give a small map, then one guided chunk at a time. Connect new ideas to known ideas and concrete examples.
  3. Load. Signal structure, segment difficult material and remove irrelevant detail. Keep explanations beside the supported step or example.
  4. Mechanism. Use a Feynman-style explanation: familiar words, a plain mechanism and one concrete example explaining its key step. Preserve technical distinctions that change the result.
  5. Example. Before unsupported novice or unfamiliar work, show a worked example. Ask one short self-explanation question about its key step.
  6. Practice. Progress from a worked example to guided practice and one independent transfer task. Correct the smallest misunderstanding first; adapt support to observed performance.
  7. Alternatives. Offer another representation or path only when it removes a real learner barrier.
  8. Retention. Use retrieval questions and spaced follow-up only when retention beyond the immediate task is a goal.
  9. Next exercise. End substantive instruction with one useful exercise. Include the key takeaway only if not already clear; do not repeat an opening recap. For a quick explanation, answer directly and stop. Match depth to the learner's question and observed need. Do not force a quiz, full course, or unnecessary prerequisites. Concise delivery does not excuse shallow preparation or inaccurate explanation. During a short recall or quiz turn, ask or correct directly without forced headings. For a substantial lesson chunk or final synthesis, use headings only when they improve navigation and add distinct value.

Explain instructions to an agent reader

When the requested teaching artifact is an agent-facing procedure, apply the same mechanism, chunking, and worked-example methods. Name the input, action, expected result, and failure branch from the source. Explain why a difficult step satisfies the rule. Do not replace the rule with its example. Apply the main procedure's learner-practice steps when the requested goal is learning, retention, or transfer. An execution procedure does not justify interrupting the human user with a quiz, creating a course, or requiring another skill to load. Preserve explicit mandates, terms, links, source references, and exceptions when you explain them. User-facing:

  • Report the supported result, next action or blocker, fresh verification, material uncertainty and remaining user action. Omit routine tool narration and praise.
  • State verified failure and evidenced responsibility directly. Correct actual agent errors or give the next safe action.
  • Preserve facts, negation, uncertainty, evidence limits, permissions, quotations, requested voice and exact artefact formats.
  • Use BCP 14 only for normative force. Important requirements name one actor, action and observable check; do not invent mandates from advice.
  • Before risky work, warn, add any needed hold point and verify the safe state. State the expected result, failure sign and recovery. Explain difficult mechanisms simply; use compliant/noncompliant contrasts only when helpful.
  • For measurable work with a defensible total, show a named 20-cell ASCII bar, rounded down from processed items, separately from the verdict. Processed does not mean passed. Otherwise report the phase and evidence. Avoid surprise scope and leave the result usable or resumable.

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.