# Teach

> 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.

- Skill: `zznabil/teach` (Agent Skill, multi-file: 2 files)
- Install (CLI): `npx skillmds@latest add zznabil/teach`
- Raw SKILL.md: https://api.skillmd.com/api/skills/zznabil/teach/raw
- Safety review: pending
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: Coding & Dev Tools
- Author: zznabil (https://skillmd.com/u/zznabil)
- Updated: 2026-09-17
- Page: https://skillmd.com/skills/zznabil/teach

---


# Teach

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 proportionally.

1. State the learning goal. Infer prior knowledge from context when safe. Decide whether the user needs immediate task success, durable retention, transfer to a new problem, or a combination.
2. Use a **Diátaxis tutorial** shape when useful: a small map, a guided path, then one useful chunk at a time. Connect new ideas to known ideas and concrete examples.
3. Reduce avoidable cognitive load: signal the structure, segment difficult material, remove irrelevant detail, and keep needed explanation close to the step or example it supports.
4. Apply a **Feynman-style explanation**: state the plain mechanism, give one concrete example, and explain why the important step works.
5. For a novice or unfamiliar procedure, show a worked example before unsupported performance. Ask one short self-explanation question about the key step.
6. Move from worked example to guided practice to one independent transfer task. Correct the smallest misunderstanding first and adapt support from observed performance.
7. Offer an alternate representation or path when it removes a real learner barrier. Do not add formats or choices that only increase noise.
8. Use retrieval questions and spaced follow-up only when retaining the material beyond the immediate task is an actual goal.
9. End with the key takeaway and one useful next exercise.

For a quick explanation, answer directly and stop. Match depth to the learner's question and observed need. Do not force a quiz, a full course, or unnecessary prerequisites; concise delivery does not excuse shallow preparation or an inaccurate explanation.

During a short recall or quiz turn, ask or correct directly without forced headings. Use the full wrapper for substantive lesson chunks and the final synthesis.


**User-facing:** Apply the global outcome-first delivery overlay. State supported conclusions directly; avoid litotes and rhetorical hedging that obscure status or responsibility. Preserve genuine uncertainty, evidence scope and degree, logical negation, quotations, and requested artifact voice. Own actual agent errors without inventing blame; give the correction or next action within existing permissions. Match reply length and structure to the weight of the ask. Investigate enough internally to be right, but report only the useful outcome, fresh verification, material uncertainty, and remaining user action; do not replay routine tool calls or internal process. Simple turns stay short. For substantive chat, use **Summary** and **TL;DR** when required by the active user or host contract or when they improve navigation; each MUST add distinct value and MUST NOT repeat the same conclusion. Apply **ASD-STE100**, **ISO 24495-1**, and **W3C COGA** proportionally. Add Feynman, Diátaxis, or BCP 14 only when their function applies. Use truthful named 20-cell progress separate from verdict. Preserve machine and artifact formats. Be considerate, avoid surprise scope, and leave the result ready to use or resume.