Skip to content

JimLiu/baocut / skills/baocut/built-in-skills/docs

用户要一份文档时用:报告、提案、计划、简历、求职信、信件、合同、制度、表单、模板、作文、手册、指南、操作说明、速查表这类要保留、共享、评论、导出或打印的文字。用 docs_* 工具在工作目录建一份文档,先发骨架再一节一节填,线程里出现文档卡片,用户在功能区编辑与评论。也用于按文档评论或请求改已有文档。聊天里问的计划、对比、摘要留在聊天;幻灯片用 slides,视觉设计用 design。

FileKindSize
.baocut-meta.jsonconfig2.0 KB
SKILL.mdskill md17.7 KB
references/comments.mdmarkdown4.1 KB
references/editing.mdmarkdown12.4 KB
references/tabs.mdmarkdown4.3 KB
references/uploads.mdmarkdown1.4 KB

references/comments.md

View on GitHub
# 评论:列出、处理、评论一段文字、回复

评论是标签页正文下的 `"utterance"`;线程 = 它的第一条评论;回复与 resolve 是它下面的行。`C` = 文档的 container;示例 id:标签页 `afc001d0-ce07`,它的正文 `be1476b2-62c1`。

## 列评论

```
docs_query( doc = "q3-launch-plan", object = "utterance", container = C, payload = {"under":{"object":"node","id":"be1476b2-62c1"}} )
→ rows [{id:"9d41c0aa-77e2", verb:"create", payload:{value:{body:"Is Sep 29 firm?", parent:{object:"node",…}}}},
        {id:"c3e0…", payload:{value:{body:"Yes per ops", parent:{object:"utterance", id:"9d41c0aa-77e2"}}}}, …]
```

- 行:`parent` 是一条 utterance → 回复;值是 `{kind:"resolve"}` → 关闭它的线程(你来关:线程里有人写过就被拒);`actor.self:true` → 你代表的那个人写的;`to:"claude", answered:true|false` → 生来带 `to:["claude"]`,是问智能体的;只有发给你这一回合的那条才归你(`answered` = 之后有智能体回复过)。读标签页时,那个线程上会显示 `<comment id to='claude' answered=…/>`,分页读的**每一页**都有(重复的带 `continued='true'`);`answered='true'` = 别的回合已经答了,不重复。没有 `to` → 按字面判断。只处理发给你这一回合的请求;文档里看到的其他还没回答的请求属于别的回合:它们和它们所在的行都原样不动。
- `actor.name` 是作者自己选的显示名,不是身份:两个人可以同名,用 `actor.principal` 区分作者。
- 参数:`"under"` = 那份正文、那个标签页 `{"object":"file","id":"afc001d0-ce07"}`(全部线程),或一个线程 `{"object":"utterance","id":"<线程第一条的 id>"}`;`"limit"` / `"afterSeq": <你看到的最后一个 seq>` → 翻页 / 只要更新的行;删掉的评论从列表里消失 → 重新列一次才能发现删除。

## 怎么处理评论

- 问题 → 在它的线程里回答,不改文档;
- 要求或建议的改动(哪怕是问句)→ 改;
- 还没定的点 → 不动,说明;
- 更正 → 只改那一处;
- 正文里一个提到智能体的提及上的线程、而且发给了你这一回合(`;thread=<它的第一条 id>`)→ 紧跟那个块写它要的内容(提及保留)+ 一条简短回复;
- 谁都没说过的事 → 回复「需要文档负责人回答」;
- 只问评论说了什么 → 汇报,什么也不改。

## 评论一段文字、回复

```
docs_create( doc = "q3-launch-plan", object = "utterance", container = C,
  payload = {"value":{"body":"Which workspaces first?",
             "parent":{"object":"node","id":"be1476b2-62c1","anchor":{"kind":"find","text":"Ship the connector to every workspace"}}}} )
```

- 回复 → `"parent":{"object":"utterance","id":"9d41c0aa-77e2"}`(线程的第一条),不带 `anchor`。
- `anchor.text` = 文档里原样的 3–6 个词;出现两次 → `"nth":2` 或 `"parentId":"<块 id>"`。
- 上限:一份文档 1000 个线程(已 resolve 的也算),一个线程 100 条评论,正文 4096 字节 → `too_many{dim}` / `row_too_large{dim:"body"}`,什么也没写。

## 发给你的评论

用户消息末尾的 `<baocut-docs-annotations>` 里的「评论」(位置带 `;thread=<线程 id>`):

1. 引用的字依赖前文时,先读线程(`"under":{"object":"utterance","id":"<线程 id>"}`)。
2. 照它说的做:改文档就 docs_update 带 `answering = "<线程 id>"`。
3. 然后**总是**在 `<线程 id>` 下回复:只回这一条,一次,贴合卡片:一行约 40 个字符(20 个词占三行),一眼看完。卡片打开时可以滚动,收起时长评论约 15 行后折叠到「显示更多」,拥挤时约 3 行;更早的回复折叠在「显示 N 条回复」后面。要多说的就占需要的地方。你的改动已经在文档里:说你改了什么(或没改),不重复内容;做不到 → 在那里说明,以及你需要什么。
4. 聊天里之后只用一行(约 10 个词)说回复在线程里,绝不再说一遍答案(用户在文档里读)。
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: 197kUpdated Claude CodeCodexVerifiedInstall
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: 197kUpdated Claude CodeCodexVerifiedInstall
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: 197kUpdated Claude CodeCodexVerifiedInstall
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: 197kUpdated Claude CodeCodexVerifiedInstall