跳到正文
cccskills
免费在 GitHub 公开

teacher-style-clone

Use a teacher's recordings or lecture materials to identify evidenced teaching habits, including phrasing, examples, pacing, and visual presentation. Apply those habits to a course on a requested topic, keeping its subject facts separate from the source lesson.

中文简介正在准备中。当前显示英语简介。

原文查看原文说明

工作台会话挂载了教师课堂录像/讲义材料时使用。

查看安装方法

适用场景

  • Creating a new lesson with a familiar teaching style
  • Analyzing recurring phrases and explanation patterns
  • Studying how speech and on-screen visuals work together
  • Applying an evidenced teaching profile to each course page

包含的文件(2)

  • SKILL.md3.9 KB
  • outline-constraints.json349 B

SKILL.md(原文)

安装前可以查看交给 AI 代理的指令内容。

Teacher style extraction and transfer

Extract how the teacher teaches, then teach the user's requested topic in that style. The source material is evidence about delivery and presentation; it is not automatically factual source material for the new course.

The learner-facing name for this mode is 「名师风格」. Never expose the words "clone" or "style transfer" to the learner. The result should simply feel like a lesson taught in the evidenced style.

Step 1 — confirm every derivative is ready

Call list_materials before drawing conclusions. Identify the attached source materials and confirm extraction is complete. For recordings, verify that the session exposes the transcript and keyframe derivatives. If extraction is idle, call extract_material first; if it is pending or running, call wait_for_materials and list again; if it failed, tell the user what failed instead of inventing a profile from incomplete evidence.

Step 2 — read the whole transcript in order

Use read_material to page through every transcript derivative from offset 0 to the final page. Do not sample only the beginning. As you read, build a compact style profile in your reasoning covering:

  • openings and transitions;
  • catchphrases, address terms, and sentence rhythm;
  • concrete-versus-abstract example habits;
  • pacing, recaps, rhetorical questions, pauses, and humor;
  • what is said aloud versus emphasized visually.

Support each claim with short transcript evidence and its timestamp. Frequency and distribution matter: distinguish a repeated habit from a phrase used once.

Step 3 — inspect keyframes for visual style

When the transcript contains a [keyframe@mm:ss](mat_xxx) marker, sample the referenced frame with read_material. Use frames across the recording rather than adjacent duplicates. Record visual evidence such as board-writing density, slide composition, hierarchy, color use, teacher position, gestures, and the relationship between speech and what remains on screen.

Do not infer visual style when the recording has no readable keyframes.

Step 4 — verify hypotheses with search

Use search_material to test specific transcript hypotheses after the full read. Search catchphrases and recurring sentence forms, compare their frequency, and revisit the surrounding snippets. Search verifies a proposed pattern; it never replaces reading the transcript in order.

Treat unsupported or contradicted hypotheses as absent from the final profile.

Step 5 — transfer the profile into generation inputs

Plan the course in the conversation, then create_stage and call generate_scene once per page with an explicit brief. Put the complete, evidence-backed style profile into each page's brief under a ## 讲课风格 section, alongside any independently verified subject facts the requested course needs. Include the load-bearing instructions: opening ritual, phrasing habits, example pattern, pacing, interaction rhythm, and visual presentation.

For every page, put the relevant evidence and concrete style directions in generate_scene.materialFacts. Examples: 「以复习上节课的问题开场」、「先用一个具体例子建立 直觉,再给出公式」、「页尾用已核验的口头禅式小结」。Do not merely refer to a profile by name: the page generator only receives the text placed in each page's brief and materialFacts.

Hard rules

  • Clone the evidenced style, not the teacher's identity. Never fabricate biography, opinions, endorsements, or personal claims.
  • Keep the requested topic factually correct on its own terms. Do not import unrelated claims from the lecture just because they appear in the transcript.
  • The source topic appears in the learner-facing course only when the user asks for that topic.
  • Every style claim needs transcript or keyframe evidence. Omit guesses.

评价

还没有评价。欢迎分享你的使用感受。

评论

无需登录即可发表。欢迎分享使用感受、提问,或说明在哪些环境下无法运行。

还没有评论。来写第一条吧。

提交后会立即公开。请勿填写邮箱、电话等个人信息。URL 最多 2 个。

0 / 1000 字

此表单受 reCAPTCHA 保护,适用 Google 的隐私权政策和服务条款。

同一仓库的技能

Turn past classrooms and chat history into a reusable personal skill for course creation. It examines varied examples, checks recurring patterns and exceptions, and asks for corrections before saving instructions that reflect the user's workflow and quality expectations.

中文简介正在准备中。当前显示英语简介。

  • Reviewing patterns across past course creation
  • Turning preferred workflows into reusable instructions
  • Checking inferred preferences against examples
THU-MAIC/OpenMAIC4.1万2026年10月19日 更新

Plan and build a connected series of lessons around learners’ experience and goals. After the user approves the complete lesson list, it creates lessons in order, checks continuity, and organizes them in one folder.

中文简介正在准备中。当前显示英语简介。

  • Building a seven-day introductory Python course
  • Creating a four-week onboarding program
  • Turning book chapters into separate lessons
THU-MAIC/OpenMAIC4.1万2026年10月19日 更新

Design courses where learners explore ideas by changing parameters, following diagrams, running code, playing games, or inspecting 3D scenes. Each main page focuses on one mechanism or structure, with opening and closing pages framing the learning.

中文简介正在准备中。当前显示英语简介。

  • Exploring how changing a parameter affects a system
  • Following a diagram to understand structure or flow
  • Learning an idea by modifying and running code
THU-MAIC/OpenMAIC4.1万2026年10月19日 更新

Create courses grounded in verified external facts, including recent developments, market data, product details, and scientific findings. It researches sources, records which evidence supports each claim, and carries those findings and uncertainties into page plans and content.

中文简介正在准备中。当前显示英语简介。

  • Creating a course about recent events or industry developments
  • Building lessons around verified market or policy data
  • Teaching product details or scientific findings with sources
THU-MAIC/OpenMAIC4.1万2026年10月19日 更新

Check important factual claims in courses or supplied content against available materials and authoritative sources. Review numbers, definitions, and contradictions, then receive a concise report with evidence and suggested corrections, or have generated course pages checked before delivery.

中文简介正在准备中。当前显示英语简介。

  • Checking facts in a completed course
  • Verifying important numbers and technical definitions
  • Finding contradictions between course pages
THU-MAIC/OpenMAIC4.1万2026年10月19日 更新

Build learning activities where learners explain an idea first, then improve their explanation through focused questions. Include plain language, checks on analogies, application to unfamiliar situations, and a record of remaining gaps and next goals.

中文简介正在准备中。当前显示英语简介。

  • Learn a concept by explaining it in your own words
  • Turn existing materials into explanation-based activities
  • Test explanations without relying on technical terms
THU-MAIC/OpenMAIC4.1万2026年10月19日 更新

查看 THU-MAIC 的全部技能

报告此技能的问题