CSlawyer1985/legal-skillhub / skills/article2book
article2book
Verified基于现有文章、专栏、课程讲稿、逐字稿、访谈、课件、会议纪要、案例材料、PDF 文本、Word 文档和笔记等内容资产,判断它们最适合转化为书、小册子、课程、系列文章、实务手册或知识库,并输出精简策划意见;用户提到“把现有内容整理成书”“判断素材适合做书还是课程”“把文章/直播稿/课程稿/笔记重组成知识产品”等场景时,应使用本技能。
| File | Kind | Size |
|---|---|---|
| CHANGELOG.md | markdown | 1.0 KB |
| DECISIONS.md | markdown | 24.9 KB |
| LICENSE.txt | markdown | 1.1 KB |
| SKILL.md | skill md | 18.0 KB |
| TASKS.md | markdown | 4.8 KB |
| _meta.json | config | 131 B |
| references/agent-reading-protocol.md | markdown | 3.3 KB |
| references/book-viability-rubric.md | markdown | 3.7 KB |
| references/content-productization-models.md | markdown | 4.2 KB |
| references/content-screening-rubric.md | markdown | 2.6 KB |
| references/output-template.md | markdown | 4.6 KB |
| references/source-type-handling.md | markdown | 4.3 KB |
| scripts/build_article_inventory.py | script | 8.2 KB |
references/agent-reading-protocol.md
View on GitHub# Agent 通读素材协议
本文件用于约束 `article2book` 的主流程:在做内容形态判断和成书判断之前,先让 Agent 尽量通读全部候选文本素材。
## 核心原则
1. 不要只看文件名、标题或脚本摘要就下结论。
2. 最终的主题判断、内容形态判断、成书可行性判断和结构映射,应建立在 Agent 已覆盖全部候选文本素材的前提上。
3. 脚本只能用来补路径、查漏和做基础索引,不能替代阅读理解。
4. 当素材很多时,可以使用 subagent 分批并行通读;但最终的母题判断、筛选结论和统稿建议,必须由主 Agent 统一收束。
## 推荐流程
### 1. 先识别可直接阅读的素材范围
优先纳入:
- `.md`
- `.markdown`
- `.mdx`
- `.txt`
- `.srt`
- `.vtt`
对纯视频、音频、图片、扫描件:
- 先转写或 OCR
- 转为可读文本后再纳入主流程
对 `.docx`、`.pdf`:
- 先标记为需预处理素材
- 能提取正文时再纳入通读
- 无法提取时,不要仅凭文件名判断内容价值
### 2. 分批通读,不要一上来就凭印象聚类
如果素材较多,建议按批次处理:
- `1-20` 份为第一批
- `21-40` 份为第二批
- 依此类推
每批完成后,都要形成阶段性笔记,避免只凭短时记忆做判断。
如果采用 subagent 并行阅读:
- 每个 subagent 只负责一批素材
- 返回的内容应尽量简短,只保留判断所需字段
- 主 Agent 统一汇总,避免不同批次口径不一致
## 每份素材至少记录的内容
建议用如下字段:
| 字段 | 说明 |
|------|------|
| 文件路径 | 便于回溯 |
| 标题 | 可用原标题,也可补临时标题 |
| 一句话摘要 | 这份素材主要在讲什么 |
| 核心问题 | 它在回答什么问题 |
| 关键判断 | 这份素材真正有价值的观点是什么 |
| 深度判断 | 高 / 中 / 低 |
| 建议去向 | 主章节 / 课程单元 / 手册条目 / 知识库条目 / 案例 / 附录 / 移出 |
| 可能形态 | 成书 / 小册子 / 课程 / 系列文章 / 实务手册 / 知识库 |
| 风险提示 | 时效性 / 重复 / 口语化 / 观点过散 |
| 筛选结论 | 保留 / 降权 / 排除 |
| 理由 | 为什么这样判断 |
## 推荐输出
通读阶段默认只需要形成内部阅读依据,不必自动公开输出太多文件。
建议优先级如下:
1. **默认**:把通读结论直接压缩进 `书稿策划意见.md`
2. **可选**:当素材很多或需要留痕时,再生成 `processed/agent_reading_notes.md`
`processed/agent_reading_notes.md` 不需要过度工整,但应足够支撑后续主题聚类、内容形态判断、目录设计和删改判断。
## 注意事项
1. 如果某份素材明显与主线无关,也要先读完再移出,而不是只凭标题排除。
2. 如果逐字稿口语化很强,重点看其中是否已有可重组的论证顺序、案例素材和章节雏形。
3. 如果多个素材重复表达同一个判断,先各自读完,再决定保留哪个最强版本。
4. 如果素材较老,不要直接排除;先判断它是否仍承载母题、框架或关键转折。
5. 第二阶段如果要直接生成全书、课程、手册或知识库初稿,主 Agent 应优先保留足够的阅读依据供统稿时回看,但这些依据不一定都要公开给用户。
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| canvas-designanthropics/skillsCreate beautiful visual art in .png and .pdf documents using design philosophy. You should use this skill when the user asks to create a poster, piece of art, design, or other static piece. Create original visual designs, never copying existing artists' work to avoid copyright violations. | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |
| docxanthropics/skillsUse this skill whenever the user wants to create, read, edit, or manipulate Word documents (.docx files) or Word templates (.dotx files). Triggers include: any mention of 'Word doc', 'word document', '.docx', '.dotx', or requests to produce professional documents with formatting like tables of contents, headings, page numbers, or letterheads. Also use when extracting or reorganizing content from .docx or .dotx files, inserting or replacing images in documents, performing find-and-replace in Word files, working with tracked changes or comments, or converting content into a polished Word document. If the user asks for a 'report', 'memo', 'letter', 'template', or similar deliverable as a Word or .docx file, use this skill. Do NOT use for PDFs, spreadsheets, Google Docs, or general coding tasks unrelated to document generation. | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |
| pdfanthropics/skillsUse this skill whenever the user wants to do anything with PDF files. This includes reading or extracting text/tables from PDFs, combining or merging multiple PDFs into one, splitting PDFs apart, rotating pages, adding watermarks, creating new PDFs, filling PDF forms, encrypting/decrypting PDFs, extracting images, and OCR on scanned PDFs to make them searchable. If the user mentions a .pdf file or asks to produce one, use this skill. | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |
| pptxanthropics/skillsUse this skill any time a .pptx or .potx file is involved in any way — as input, output, or both. This includes: creating slide decks, pitch decks, or presentations; reading, parsing, or extracting text from any .pptx or .potx file (even if the extracted content will be used elsewhere, like in an email or summary); editing, modifying, or updating existing presentations; combining or splitting slide files; working with templates (.potx), layouts, speaker notes, or comments. Trigger whenever the user mentions "deck," "slides," "presentation," or references a .pptx or .potx filename, regardless of what they plan to do with the content afterward. If a .pptx or .potx file needs to be opened, created, or touched, use this skill. | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |