Agent skill

Course Generator

by cat-xierluo in cat-xierluo/legal-skills

将课程转录稿、逐字稿、讲稿或文献整理为可独立阅读的 Markdown 课程,并通过来源索引、素材账本和确定性验收保留关键案例、操作步骤与专业判断。用户要求从一份或多份现有文本生成课程总览、章节或完整课程时使用。

MITAuto-check: notes

Install Course Generator

skills CLI
$ npx skills add cat-xierluo/legal-skills --skill course-generator -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install cat-xierluo/legal-skills course-generator --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/cat-xierluo/legal-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/course-generator .claude/skills/course-generator && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
course-generator
GitHub stars
717
Token cost
~874 tokens
SKILL.md length
143 words
Files
31 (incl. scripts, references)
Skills in repo
62
Repo updated
First seen
Licence
MIT

At a glance

将课程转录稿、逐字稿、讲稿或文献整理为可独立阅读的 Markdown 课程,并通过来源索引、素材账本和确定性验收保留关键案例、操作步骤与专业判断。用户要求从一份或多份现有文本生成课程总览、章节或完整课程时使用。

  • Works in 6 steps: 忠实来源:数字、动作、结果、建议和专有名称必须能回到来源;原文没有的能力、流程、案… → 保留精华:每个有效来源块都要进入素材账本或使用受控理由跳过。案例、操作、踩坑、取舍… → 遵守现行口径:来源存在明确修订时,以控制文档为准;旧口径只进入审计记录,不得重新出… → …
  • SKILL.md covers 任务目标, 输入与交付, 核心要求 and 工作流程, plus 4 more sections
  • Calls python3, brew and apt-get

What it does

Course Generator is an agent skill from cat-xierluo/legal-skills. 将课程转录稿、逐字稿、讲稿或文献整理为可独立阅读的 Markdown 课程,并通过来源索引、素材账本和确定性验收保留关键案例、操作步骤与专业判断。用户要求从一份或多份现有文本生成课程总览、章节或完整课程时使用。

Its SKILL.md is about 870 tokens, which your agent loads only when the skill is triggered. The skill folder holds 32 other files, including scripts and reference files (for example `CHANGELOG.md`, `DECISIONS.md` and `TASKS.md`).

The licence is MIT.

Example prompts

  • “/course-generator”

Requirements

  • Python 3

Workflow steps

6 steps, taken from the first numbered list in SKILL.md.

  1. 忠实来源:数字、动作、结果、建议和专有名称必须能回到来源;原文没有的能力、流程、案例和结论不得用常识补齐。
  2. 保留精华:每个有效来源块都要进入素材账本或使用受控理由跳过。案例、操作、踩坑、取舍和判断技巧不得被压成一句摘要。
  3. 遵守现行口径:来源存在明确修订时,以控制文档为准;旧口径只进入审计记录,不得重新出现在读者正文。
  4. 证据跟随章节:每个二级标题必须有绑定素材,素材正文证据只能来自自己的目标小节,不跨节借用。
  5. 书面化而不扩写:删除逐字稿框架和口语赘词,但保留原文的不确定、举例和设想语气;单一样本不得扩成普遍规律或行业惯例。
  6. 生产与验收分离:生成者完成正文,脚本检查客观约束,最后再由独立审阅者检查素材守恒、事实忠实和阅读质量。

What it can do on your machine

Read from SKILL.md and the folder at commit c077fcc. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Ships 1 file in scripts/, which the agent can run.

    Shell commands in SKILL.md call:

    • python3
    • brew
    • apt-get

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Course Generator loads about 874 tokens when it runs, and up to ~24k if it reads all its reference files. Until then it costs about 31 tokens; SKILL.md has 143 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~31
When it runs · the whole SKILL.md, loaded when a task matches
~874
With references · SKILL.md plus every file in references/, read only if the agent opens them
~24k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check: notes

The automated check noted patterns worth knowing about, such as sudo or a known installer.

  • NoteRuns commands with sudoSKILL.md:87
    macOS: `brew install python`<br>Linux: `sudo apt-get install python3` |

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.

SKILL.md

The full file from cat-xierluo/legal-skills at commit c077fcc, republished under its MIT licence (© cat-xierluo). 143 words, ~874 tokens.

Download SKILL.mdSave it as .claude/skills/course-generator/SKILL.md (or your agent's skills folder). This skill also uses 30 other files; get the full folder from GitHub.
name
course-generator
description
将课程转录稿、逐字稿、讲稿或文献整理为可独立阅读的 Markdown 课程,并通过来源索引、素材账本和确定性验收保留关键案例、操作步骤与专业判断。用户要求从一份或多份现有文本生成课程总览、章节或完整课程时使用。
homepage
https://github.com/cat-xierluo/legal-skills
author
杨卫薪律师(微信ywxlaw)
version
2.10.2
license
MIT

课程内容整理

任务目标

把现有文本整理成读者无需接触原始转录稿也能理解和使用的课程。正文应完整保留来源中的重要观点、案例、操作过程、失败修正和判断方法,同时去除现场口语、会务信息和转录噪声。

本技能默认生成课程,不自动归档、移动原文件或改造成其他内容产品。用户明确要求生成后的归档或培训方案提取时,再读取 post-generation-actions.md。

输入与交付

开始前确认:

  • 一份来源文件或一个来源目录;优先处理 .md、.txt。
  • 课程输出目录;未指定时在来源旁建立新的课程目录,并在写入前说明位置。
  • 是否存在勘误、编校说明或指定的现行口径文件。
  • 是否需要使用用户词典纠正专名或固定术语;需要时从 config/user_dictionary.example.yaml 复制为 config/user_dictionary.yaml,只登记能够确认的替换。
  • 目标目录是否已有内容;不得静默覆盖。

默认交付包括:

  • 00 <课程名称> - 总览.md
  • 按阅读顺序编号的课程章节
  • source-index.json
  • course-manifest.json

原始材料保持只读。临时计划、批次文件、辅助脚本和缓存放在课程目录之外。

核心要求

  1. 忠实来源:数字、动作、结果、建议和专有名称必须能回到来源;原文没有的能力、流程、案例和结论不得用常识补齐。
  2. 保留精华:每个有效来源块都要进入素材账本或使用受控理由跳过。案例、操作、踩坑、取舍和判断技巧不得被压成一句摘要。
  3. 遵守现行口径:来源存在明确修订时,以控制文档为准;旧口径只进入审计记录,不得重新出现在读者正文。
  4. 证据跟随章节:每个二级标题必须有绑定素材,素材正文证据只能来自自己的目标小节,不跨节借用。
  5. 书面化而不扩写:删除逐字稿框架和口语赘词,但保留原文的不确定、举例和设想语气;单一样本不得扩成普遍规律或行业惯例。
  6. 生产与验收分离:生成者完成正文,脚本检查客观约束,最后再由独立审阅者检查素材守恒、事实忠实和阅读质量。

冲突时依次保护:事实忠实与现行口径、核心素材完整、章节证据边界、读者可读性、审计便利。

工作流程

生成任务开始后,先完整读取 generation-workflow.md,再按以下顺序执行;不得跳过账本预检直接写正文。

  1. 运行 index_sources.py 建立确定性来源索引。
  2. 用 ledger_tool.py init 初始化 manifest,确认权威声明并冻结章、节计划。
  3. 按 status 返回的来源块分批建立素材账本,运行 ledger 阶段自动收口和预检。
  4. 选择少量有教学价值的代表图,由工具生成章节标题和修订句脚手架。
  5. 读取 overview_prompt.md 和 chapter_prompt.md,先写总览,再逐章生成;每章通过 check-chapter 后才进入下一章。
  6. 运行 final 阶段自动收口和 verify.sh,再完成人工语义复核。

大纲和素材判断规则见 outline_prompt.md。机器字段及 JSON 示例见 course-manifest.md。默认最多 8 章;只有用户明确要求超过 8 章时才读取 advanced-overrides.md。

完成标准

只有同时满足以下条件,才可交付:

  • 总览、manifest 声明的全部章节和两份强制 JSON 均存在。
  • 素材账本覆盖全部有效来源块,跳过项有受控理由,高价值内容没有无理由净丢失。
  • 每章 check-chapter 通过,最终 verify.sh 退出码为 0。
  • 独立审阅者读取 quality-evaluation.md,按证据完成语义验收;人工抽查确认数字、动作链、建议、结果和专名可回溯,修订口径无冲突,章节之间没有明显重复。
  • 读者正文不出现 SRC/BLK/MAT/IMG、门禁解释、生成日志、临时文件或来源没有讨论的内部术语。

脚本通过只证明客观契约成立,不等于语义质量已经通过。交付时分别报告脚本结果、人工复核范围和未验证部分。

配额、网络或平台异常时保留现场并报告,不从头重跑,不把半成品或执行者自报记为成功。

权限与隐私

  • 只读取用户指定的来源,只向已说明的课程目录写入。
  • 脚本不联网、不安装依赖、不修改原始材料;init/plan/merge/select-images 原子更新索引或 manifest,scaffold 只创建缺失的标题脚手架,finalize_manifest.py --write 只更新 manifest。
  • 未脱敏转录稿和课程材料按最小必要原则处理,不写入公开示例、变更记录或配置模板。

依赖

系统依赖
依赖用途安装方式
python3 >= 3.10运行来源索引、账本和验收脚本macOS: brew install python<br>Linux: sudo apt-get install python3
Python 包

无需第三方 Python 包,全部脚本只使用标准库。

资源索引

  • generation-workflow.md:完整生成步骤、命令顺序和失败处理;每次生成课程时读取。
  • outline_prompt.md:素材分类、章节规划和图片判断;建立计划与账本时读取。
  • overview_prompt.md:总览写作要求;生成总览时读取。
  • chapter_prompt.md:章节写作和单章自检;逐章生成时读取。
  • course-manifest.md:manifest 字段和 JSON 示例;准备计划、批次或图片选择文件时按需查询。
  • quality-evaluation.md:课程成品的语义硬失败、质量评分和版本晋级标准;独立验收或回归比较时读取,不提供给生成者作为写作提纲。
  • post-generation-actions.md:归档和培训方案提取;仅在用户明确要求时读取。
  • verify.sh:最终确定性验收入口。

© cat-xierluo, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 30 other files (scripts, references) in skills/course-generator of cat-xierluo/legal-skills.

  • SKILL.md
  • CHANGELOG.md
  • DECISIONS.md
  • LICENSE.txt
  • TASKS.md
  • config/.gitignore
  • config/course-manifest.schema.json
  • config/paths.example.yaml
  • config/source-index.schema.json
  • config/user_dictionary.example.yaml
  • references/advanced-overrides.md
  • references/chapter_prompt.md
  • references/course-manifest.md
  • references/extract_prompt.md
  • references/generation-workflow.md
  • references/outline_prompt.md
  • references/overview_prompt.md
  • references/post-generation-actions.md
  • references/quality-evaluation.md
  • … and 12 more

Open the folder on GitHubat commit c077fcc

Compare with similar skills

Course Generator next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Course Generator compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Course Generator this skillcat-xierluo/legal-skills717—~874Automated safety check: NotesMIT
Generatealirezarezvani/claude-skills28k1 repos~1.1kAutomated safety check: PassMIT
Fal Generatenexu-io/open-design100k—~306Automated safety check: PassApache-2.0
Video Generationbytedance/deer-flow84k3 repos~1.4kAutomated safety check: PassMIT
Image Generationonyx-dot-app/onyx32k1 repos~1.7kAutomated safety check: PassCustom licence
Structured Image Generationbytedance/deer-flow84k4 repos~2.9kAutomated safety check: PassMIT

Similar skills

  • Generate

    alirezarezvani/claude-skills

    Generate Playwright tests. An agent skill from alirezarezvani/claude-skills.

    28k GitHub starsUsed in 1 repo~1.1k tokens
    Testing & QAAuto-check passed
  • Fal Generate

    nexu-io/open-design

    Generate images and videos using fal.ai AI models. An agent skill from nexu-io/open-design.

    100k GitHub stars~306 tokensUpdated today
    Media & CreativeAuto-check passed
  • Video Generation

    bytedance/deer-flow

    Generates short videos from a structured JSON prompt, optionally guided by a reference image used as the first or last frame.

    84k GitHub starsUsed in 3 repos~1.4k tokens
    Media & CreativeAuto-check passed
  • Image Generation

    onyx-dot-app/onyx

    Generate or edit raster images (photos, illustrations, textures, sprites, mockups, logos, infographics) using the workspace's configured image-generation provider via onyx-cli image.

    32k GitHub starsUsed in 1 repo~1.7k tokens
    Media & CreativeAuto-check passed
  • Structured Image Generation

    bytedance/deer-flow

    Turns an image request into a structured JSON prompt and runs a bundled Python script to generate the picture, optionally guided by reference images.

    84k GitHub starsUsed in 4 repos~2.9k tokens
    Media & CreativeAuto-check passed
  • Generate Nanobanana

    sickn33/agentic-awesome-skills

    Generate and edit images/video with Google's Gemini media models (Nano Banana 2/Pro, Gemini Omni Flash), with cost-approval gates, reference-image support, and a prompt/output log per call.

    47k GitHub starsUsed in 1 repo~2.8k tokens
    Media & CreativeAuto-check: notes

More from cat-xierluo/legal-skills

All 62 skills in this repo
  • Elements-Style Complaint Generator

    cat-xierluo/legal-skills

    Converts a lawyer's ordinary complaint or a described case into the Supreme People's Court's elements-style Word template, with layout checks on the result.

    717 GitHub stars~2.5k tokensUpdated yesterday
    Auto-check: notes
  • Lecture Performance Review

    cat-xierluo/legal-skills

    Analyzes raw lecture transcripts for verbal tics, pacing, time use and promise follow-through, with optional slide-by-slide comparison and cross-session tracking.

    717 GitHub stars~2.2k tokensUpdated yesterday
    Auto-check passed
  • De-AI Polish for Chinese Articles

    cat-xierluo/legal-skills

    Detects and rewrites machine-sounding patterns in the body text of Chinese articles while keeping the author's facts, headings and legal terms intact.

    717 GitHub stars~2.9k tokensUpdated yesterday
    Auto-check passed
  • GitHub Star Manager

    cat-xierluo/legal-skills

    Finds GitHub projects mentioned in articles or screenshots and stars them, tracks updates to your starred repos, and builds an HTML dashboard to browse them.

    717 GitHub stars~2k tokensUpdated yesterday
    Auto-check: notes
  • Legal Harness Initializer

    cat-xierluo/legal-skills

    Sets up or incrementally updates AGENTS.md and CLAUDE.md for legal professionals, with a minimal safety baseline and a check that a new session loads and follows the rules.

    717 GitHub stars~2.3k tokensUpdated yesterday
    Auto-check passed
  • Moot Court Simulation Builder

    cat-xierluo/legal-skills

    Chinese-language skill that organizes a case file into a multi-role mock trial with judge, parties and clerk, producing a transcript, issue review and a to-strengthen list.

    717 GitHub stars~1.4k tokensUpdated yesterday
    Auto-check passed

Questions about Course Generator

What does Course Generator do?

将课程转录稿、逐字稿、讲稿或文献整理为可独立阅读的 Markdown 课程,并通过来源索引、素材账本和确定性验收保留关键案例、操作步骤与专业判断。用户要求从一份或多份现有文本生成课程总览、章节或完整课程时使用。. Course Generator is an agent skill from cat-xierluo/legal-skills.

How do I install Course Generator in Claude Code?

Run `npx skills add cat-xierluo/legal-skills --skill course-generator -a claude-code`. Or copy the skill folder (skills/course-generator in cat-xierluo/legal-skills) into .claude/skills/course-generator in your project. Claude Code loads it when a task matches its description.

How do I install Course Generator in Codex?

Run `npx skills add cat-xierluo/legal-skills --skill course-generator -a codex`. Or copy the skill folder (skills/course-generator in cat-xierluo/legal-skills) into .agents/skills/course-generator in your project. Codex loads it when a task matches its description.

Can I use Course Generator in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add cat-xierluo/legal-skills --skill course-generator -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/course-generator, .gemini/skills/course-generator, .github/skills/course-generator and .opencode/skills/course-generator in your project.

What does Course Generator need to run?

Going by SKILL.md and its folder, Course Generator needs the command-line tools its instructions call (python3, brew and apt-get). Our summary lists: Python 3.

Does Course Generator access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Course Generator safe to install?

Our automated static check of SKILL.md found notes only (runs commands with sudo), nothing it rates as a warning. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does Course Generator use?

Course Generator is published under the MIT licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Course Generator use?

About 874 tokens (SKILL.md is roughly 3.5k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 23k tokens, read only when the agent opens those files.

What are the alternatives to Course Generator?

Skills that share tags, products or a category with Course Generator: Generate (alirezarezvani/claude-skills, 28k stars), Fal Generate (nexu-io/open-design, 100k stars), Video Generation (bytedance/deer-flow, 84k stars) and Image Generation (onyx-dot-app/onyx, 32k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Course Generator?

cat-xierluo (a GitHub user) maintains it in cat-xierluo/legal-skills, which has 717 GitHub stars. The repository holds 62 skills in this directory. The repository was last updated on October 8, 2026.

Source: cat-xierluo/legal-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.