Sources

S1 — Agent Mentor Skill package entrypoint (intent router)

URL: SKILL.md

  • authority: official-docs
  • supports: 本 skill 在任何学习请求上激活，无需触发短语；复习（“考考我”）、维护（“更新我的课程”）与导出（“导出这门课程”）请求各自路由到对应工作流。
  • key-fact: "Use for EVERY learning request, even when the skill is not named — 'I want to learn X', 'teach me X'... Also handles review (quiz me), maintenance (update the course), and export."

S2 — Course-generation workflow contract

URL: agent-mentor/skills/generate-course-from-topic/SKILL.md

  • authority: official-docs
  • supports: 面向用户的产品名；请求分档（只报主题的请求触发 1-3 个澄清问题，写明起点和缺口的请求直接进入生成）；标为不会的概念不得被偷偷当作先修条件；首次运行的环境安装在用户空间完成、不用 sudo、不收集用户数据；阅读站只监听 localhost，交给用户的 URL 必须以 /courses 结尾；更新检查只发送版本查询。
  • key-fact: "Too vague: 'I want to learn Next.js' gives only a topic name. Stop and ask 1-3 short questions first... When the user says 'I don't know X,' X must go into unknownConcepts and must never be smuggled in as a prerequisite in lesson 1... Stage 0 runs entirely in user space, no sudo, and collects or exfiltrates no user data... it must include the /courses path."

S3 — Course authoring guide (course shape and quality gate)

URL: agent-mentor/skills/generate-course-from-topic/course-authoring-guide.md

  • authority: official-docs
  • supports: 每节课遵循固定骨架（目标、讲解、完整示例、填空示例、练习、小结）；关键事实必须带指向 sources.md 的引用、不得编造；每门课程附带释义有来源的词汇表；练习带完成标准供自我评判；交互反馈必须解释机制、不能只说错了；机械化质量检查（course-guard）把守交付与维护。
  • key-fact: "Every key fact/API/version/definition that makes it into the course must be corroborated... every question has the four-part structure: approach guidance, quantifiable completion criteria, the answer or key points, progressive hints... every error-feedback message must explain the mechanism, never just say 'wrong.'"

S4 — Review-course workflow contract

URL: agent-mentor/skills/review-course/SKILL.md

  • authority: official-docs
  • supports: 复习触发语；复习池的内容（词汇表术语在该课程完成一节课后进入，交互块仅在被作答后进入）；Leitner 第 1-5 盒对应 1/3/7/14/30 天间隔与到期计算；每次会话至多 10 条、先问之前答错的；术语先答后讲，交互块换说法重问、答错加变体；“我不知道 / 我忘了”记为答错、语气不带评判；逐条即时记录；收尾报告含明天到期数；零到期与零进度两个分支。
  • key-fact: "Boxes 1-5 map to intervals [1, 3, 7, 14, 30] days... Take at most 10 items per review session... quiz first, explain after... Treat 'I don't know / I forgot' as a wrong answer; keep the tone non-judgmental... report: 'Reviewed X items today, Y correct, Z wrong, N items due tomorrow'... If there are 0 due items... do not manufacture questions."

S5 — Maintain-course workflow contract

URL: agent-mentor/skills/maintain-course/SKILL.md

  • authority: official-docs
  • supports: 维护触发语；预告 → 快照 → 编辑 → 校验 → 回报的顺序，质量永不倒退，可回滚；“撤销”恢复最近一次快照并重跑检查；复习记录以课节文件名、块 id 和术语原文为键，改名会孤儿化记录、必须显式警告；课程库体检只读；扩展课节深度封顶 1 层、每个父课节至多 3 节。
  • key-fact: "The edit MUST pass course-guard.mjs after completion (quality NEVER regresses), every edit is reversible (automatic hidden snapshot), and edits NEVER silently break the review loop (orphaned review records are surfaced explicitly)... explicitly tell the user: 'This will orphan roughly N review records'... Depth capped at 1... once a parent already has 3 extensions, refuse to generate a 4th."

S6 — Export-course workflow contract

URL: agent-mentor/skills/export-course/SKILL.md

  • authority: official-docs
  • supports: 导出触发语与格式对应（默认两种格式都出，打印/PDF 请求出 HTML，抽认卡请求出 CSV）；输出落在仓库的 exports 文件夹里按课程分放并回报路径；PDF 来自浏览器的打印功能；Anki 通过 File → Import 导入并对应正反面字段；导出完全本地、只写 exports，且是快照，课程变更后需重新导出。
  • key-fact: "If both are mentioned, or they just say 'export this course' without specifying → export both... for a PDF, use the browser's 'Print → Save as PDF'... open Anki → File → Import → select the -cards.csv file, map the front/back fields... The export is a snapshot of the course's current content; re-export after any course change."

S7 — Anthropic: Building Effective AI Agents

URL: https://www.anthropic.com/engineering/building-effective-agents

  • authority: official-docs
  • supports: “agent 自行安排流程与工具使用来完成工作”的定调；这正是本课程里学习者的职责是提供目标、检查结果而不是亲手执行步骤的原因。
  • key-fact: "Agents are systems where LLMs dynamically direct their own processes and tool usage, maintaining control over how they accomplish tasks."

S8 — Wikipedia: Leitner system

URL: https://en.wikipedia.org/wiki/Leitner_system

  • authority: encyclopedia
  • supports: 复习时间表背后的一般机制：答对的条目升入复习间隔更长的盒子，答错的条目回到频繁复习端。
  • key-fact: "Correctly answered cards are advanced to the next, less frequent box, while incorrectly answered cards return to the first box for more aggressive review and repetition."

S9 — Learner model contract

URL: docs/learner-model-contract.md

  • authority: official-docs
  • supports: 写明缺口所附带的保证：用户自称不会的概念进入课程学习者档案的 unknownConcepts，不得用作第一步的先修条件，课程必须为它搭桥。
  • key-fact: "If the user says they do not know X, put X in unknownConcepts; do not use X as a first-step prerequisite... The first independent action must be executable using only knownConcepts plus information introduced in the same lesson."

S10 — Reader drill-down design: three copy-to-agent entry points

URL: docs/superpowers/specs/2026-07-10-course-drilldown-design.md

  • authority: official-docs
  • supports: 选中文本的浮条（“就这段问 agent”）复制课节路径加逐字选中内容；词汇表浮窗带“让 agent 教我这个”动作，携带术语、释义与课节路径；课节末尾的“就本课深入”入口复制课节路径加深入请求；共用的分诊规则在聊天里回答小问题，真实缺口至多长出一节扩展课节。
  • key-fact: "Copied content = lesson path + the selected text quoted verbatim + triage instructions... rules for the agent: read the lesson file and glossary first; if one or two conversational turns can explain it, explain directly and generate no files; only a real foundational gap or systematic deepening need generates one extension lesson."

S11 — When-stuck help card design

URL: docs/superpowers/specs/2026-07-10-stuck-help-card-design.md

  • authority: official-docs
  • supports: 课程页带一张“卡住时”卡片，按情境提供模板（概念不明白、代码报错、练习无从下手），外加课节末尾的提醒；模板自动填入课程位置，要求学习者填上卡在哪里、试过什么，并指示 agent 以提示和提问开路，而不是直接给完整答案。
  • key-fact: "The unified skeleton: 'I am learning __ (auto-filled) + situation-specific blanks + behavioral constraints for the agent'... do not give the complete explanation directly: first explain with an analogy, then ask a question to confirm my understanding."

S12 — Anthropic Academy

URL: https://www.anthropic.com/learn

  • authority: official-docs
  • supports: 指挥 agent 完成结构化工作如今已被模型厂商当作独立科目来教授；这支撑第 1 课的定调：操作 agent 是一门可学、已成体系的实践，不是小众技巧。
  • key-fact: "Featured courses include AI Fluency tracks for non-developers alongside Claude Code and API tracks."