Menú
When 飞书云文档 needs creating, reading, or updating → CRUD docs with Lark-flavored Markdown syntax.
Instalar con Codex o Claude Copia este prompt, pégalo en Codex, Claude u otro asistente, y deja que revise la página de la skill y la instale por ti.
When prompt, tool, or agent logic changes need regression testing → run eval benchmarks to detect regressions or improvements.
When a task can be parallelized (bulk code review, multi-module refactor, batch analysis) → split into subtasks running in isolated git worktrees via multiple workers.
When the user wants to research academic papers → search ArXiv, extract PDFs, summarize/review/Q&A, generate experiment code.
When you need to interact with web pages using the user's logged-in browser → control Chrome via @playwright/cli daemon, reusing cookies/session with persistent tabs.
When user needs AnyGenIO content generation → unified CLI for task execution with progressive disclosure.
When you need to persist files (reports, docs, evidence) beyond the session → create/query/delete durable artifacts.
Basado en la clasificación ocupacional SOC
| name | feishu-doc |
| description | When 飞书云文档 needs creating, reading, or updating → CRUD docs with Lark-flavored Markdown syntax. |
| triggers | {"intent_patterns":["云文档|document|docx|创建文档|读取文档|更新文档","知识库|wiki|知识空间","文档内容|写文档|编辑文档","帮我.*写到.*文档|write.*to.*doc|更新.*飞书.*文档","读.*飞书.*文档|read.*lark.*doc|看下.*这个.*文档","新建.*wiki|create.*wiki|发布.*知识库|publish.*wiki","文档.*链接|doc.*link|分享.*文档|share.*doc","追加.*内容|append.*content|在.*文档.*里.*加|add.*to.*doc"],"context_signals":{"keywords":["doc","document","docx","wiki","文档","知识库","document_id","写","读","创建","编辑","分享","追加"]},"confidence_threshold":0.5} |
| priority | 9 |
| requires_tools | ["bash"] |
| max_tokens | 300 |
| cooldown | 15 |
| 用户意图 | module | tool_action | 必填参数 |
|---|---|---|---|
| 创建文档 | doc | create | 可空（建议 title） |
| 读取文档 | doc | read | document_id |
| 读取文档内容 | doc | read_content | document_id |
| 写入 Markdown | doc | write_markdown | document_id, content（或 markdown） |
| 列出文档块 | doc | list_blocks | document_id |
| 更新文本块 | doc | update_block_text | document_id, block_id, content |
| 用户意图 | module | tool_action | 必填参数 |
|---|---|---|---|
| 列出知识空间 | wiki | list_spaces | - |
| 列出节点 | wiki | list_nodes | space_id |
| 创建节点 | wiki | create_node | space_id, title |
| 获取节点 | wiki | get_node | space_id, node_token |
python3 skills/feishu-cli/run.py '{
"action": "tool",
"module": "doc",
"tool_action": "create",
"title": "Q1 工作总结",
"folder_token": "fldcnXXXX"
}'
python3 skills/feishu-cli/run.py '{
"action": "tool",
"module": "doc",
"tool_action": "read_content",
"document_id": "doccnXXXX"
}'
python3 skills/feishu-cli/run.py '{
"action": "tool",
"module": "doc",
"tool_action": "write_markdown",
"document_id": "doccnXXXX",
"content": "## 概述\n\n本季度完成了以下关键目标：\n\n1. 项目 A 上线\n2. 性能优化 30%"
}'
# 列出知识空间
python3 skills/feishu-cli/run.py '{"action":"tool","module":"wiki","tool_action":"list_spaces"}'
# 列出节点
python3 skills/feishu-cli/run.py '{"action":"tool","module":"wiki","tool_action":"list_nodes","space_id":"7xxx"}'
https://xxx.feishu.cn/docx/doccnXXXX → document_id = "doccnXXXX"wiki get_node 获取 obj_token，再作为 document_id 使用飞书文档支持的 Markdown 是 Lark 风味，与标准 GFM 有一些差异：
# 到 ######```language 语法| col1 | col2 | 标准表格语法- [ ] 和 - [x]> 前缀callout、grid、mermaid、plantuml 等docx:document:readonly scopedocx:document scopewiki:wiki 相关 scopeurl 与 applink_urlmanage_permission_warning