メニュー
Teach a concept, solution, or pattern one layer at a time with grounded examples. Uses the attention contract and avoids dumping full derivations unless requested.
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
| name | teach |
| description | Teach a concept, solution, or pattern one layer at a time with grounded examples. Uses the attention contract and avoids dumping full derivations unless requested. |
Read the shared contracts before output: ../_shared/operator-output.md, ../_shared/attention-budget.md, ../_shared/evidence-record.md, ../_shared/state.md, ../_shared/cognitive-load.md, ../_shared/collaboration.md.
Make one concept usable without overwhelming the learner.
Named concept, recent architecture/fix/design, repo code, library/API question, or user request to learn.
Actual repo code for repo topics, official docs/context7/package source for library/API behavior, and .context/ artifacts when teaching a recent workflow result.
.context/teach.md when the explanation depends on evidence or should persist.context/session-state.md for substantial teaching sessions.context/teach.md when needed.Use compact teaching prose, not the workflow Decision template unless a decision is being taught. Include one concrete example and the next learning step.
Stop if the topic is ambiguous and cannot be inferred, or if deeper layers require user choice.
Apply Emil Kowalski-style UI polish: interaction details, component feel, animation restraint, and invisible product quality. Uses progressive disclosure instead of long design essays.
Apply Emil Kowalski-style animation guidance for web interfaces: purposeful motion, correct easing, interruptibility, performance, reduced motion, and interaction feel.
Implement the requested change on the current branch using the best available contract: issue, architecture, user request, or repo evidence. Does not require /architect or /review to have run. Hands naturally to /test.
Triage and address PR review comments. Uses available issue/architecture/context when present, keeps evidence in .context/address.md, and does not require prior workflow phases.
Derive the smallest correct architecture from user intent, repo facts, and available workflow evidence. Writes the full architecture to .context/architecture.md and returns only the decision, tradeoff, risk, and next action.
Review the current PR for correctness, tests, maintainability, security, standards, and prior-findings risk. Keeps reviewer detail in .context/code-review.md and posts concise actionable GitHub review comments.