菜单
Teach with adaptive guidance, retrieval practice, and Socratic questioning. Use when the user wants to study a topic, build durable understanding, practice, or be coached. Do not use for one-off factual answers, quick explanations, or ordinary task guidance.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Use this skill whenever code-review feedback already exists and may affect a code decision or change. This includes PR comments, findings returned by invoke or any external model or review tool, and delegated-review results—even when the user simply says to fix, address, apply, or resolve them. Do not use to perform a new review, diagnose an unrelated bug, implement a new requirement, or merely summarize or explain feedback without deciding about code.
Interview the user to resolve material branches of a decision tree and converge on a shared plan before acting. Use when multiple reasonable choices would materially change scope, cost, reversibility, or outcome, or when the user asks to brainstorm, shape, or grill an idea. Do not use when facts can resolve the ambiguity or a reversible assumption would not materially affect the result.
Draft or review minimal, testable goals. Use only when the user explicitly asks to write, revise, or review a goal.
Create or improve agent skills from concrete behavior and evidence. Use when building or revising SKILL.md, or testing whether a skill earns its context. Do not use for ordinary documentation or one-off prompts.
Diagnose and fix bugs, failures, and performance regressions. Read this skill BEFORE touching any code whenever the user reports a bug, broken behavior, a crash, wrong output, or a regression — even when the cause looks obvious and the user only asked for a fix. Do not use for a simple explanation of a known error when no diagnosis is requested.
Research with parallel agents, independent evidence angles, and cross-validation. Use when the user explicitly asks for parallel or delegated research, or when a high-cost question materially benefits from independent evidence.
| name | learn-anything |
| description | Teach with adaptive guidance, retrieval practice, and Socratic questioning. Use when the user wants to study a topic, build durable understanding, practice, or be coached. Do not use for one-off factual answers, quick explanations, or ordinary task guidance. |
Help the learner build usable understanding in a single session, not merely recognize an explanation. Let them do the reasoning and retrieval. Add tacit knowledge only when it changes how the idea is understood or applied.
If the goal or prior knowledge is unclear, ask one structured question covering both. Use the environment's question tool for every learner-facing question: Codex request_user_input, Claude Code AskUserQuestion, or Pi/OpenCode question. Use plain text only when no such tool is available or it is rejected.
Ask one question at a time. Use clickable choices for calibration, navigation, and hints. For retrieval, explanation, and application, use the question tool's free-text input; never expose the answer in its choices. If it supports choices only, offer navigation or hint choices and leave the free-form response for the learner's answer.
If the user asks for the answer, wants to skip questions, or exits coaching, answer normally at once.
If the learner mistakes effort for failure, explain once that active retrieval should feel harder than rereading. Do not turn this into a fixed motivational speech.
Weave in expert judgment, common traps, and unwritten constraints where relevant. Do not turn them into a generic tips list. After at least two concepts have closed, periodically bring back an earlier one as a short free-text retrieval question. Repair a faded concept before moving on.
Ask for a free-text teach-back of the whole idea. Find the weakest gap, ask one targeted repair question, then have the learner re-explain that piece. Stop when they can explain the idea and apply it or handle its main counterexample.
Briefly identify anything that still requires real practice or external verification. A single session cannot provide cross-session spacing: suggest a later self-test only when useful, and offer study cards only if the user asks.
