从飞书云文档或知识库读取内容，转换为 Markdown 格式后进行分析和展示。支持 docx（新版文档）和 sheet（电子表格）两种知识库文档类型。
Works with
AI-first code editor with Composer
Before installing skills in Cursor, ensure your development environment meets these requirements:
node --versionfeishu-cli-readExecute the skills CLI command in your project's root directory to begin installation:
Fetches feishu-cli-read from riba2534/feishu-cli and configures it for Cursor.
The CLI shows a list of agents. Use arrow keys and space to select Cursor:
Confirm successful installation by checking the skill directory location:
Restart Cursor to activate feishu-cli-read. Access via /feishu-cli-read in your agent's command palette.
We perform automated surface-level scans (Gen AI Scanner, Socket, Snyk) during installation. These checks detect common vulnerabilities but do not guarantee complete security. Always review skill source code and verify the publisher's reputation before production use.
Skills execute code in your environment. Always review source, verify the publisher, and test in isolation before production.
Submit your Claude Code skill and start earning
Create detailed user stories, acceptance criteria, and feature specs
Example
Generate user stories for 'password reset feature' with acceptance criteria, edge cases, and test scenarios
Reduce spec writing time by 50%, ensure comprehensive coverage
Research competitors, compare features, identify gaps
Example
Analyze 5 competitor products, create feature comparison matrix, suggest differentiation opportunities
Complete competitive research in 2 hours instead of 2 days
Evaluate features using frameworks (RICE, ICE, Kano) and create prioritized backlogs
Example
Score 20 feature ideas using RICE framework, generate prioritized roadmap with rationale
0
total installs
0
this week
797
GitHub stars
0
upvotes
Run in your terminal
0
installs
0
this week
797
stars
从飞书云文档或知识库读取内容，转换为 Markdown 格式后进行分析和展示。支持 docx（新版文档）和 sheet（电子表格）两种知识库文档类型。
feishu-cli auth login）docx:document 或 docx:document:readonly（普通文档）、wiki:wiki:readonly（知识库）feishu-cli auth login --scopes "docx:document:readonly offline_access" 授权，doc export 会自动读取保存的 User TokenMarkdown 作为中间态：本地文档与飞书云文档之间通过 Markdown 格式进行转换，中间文件存储在 /tmp 目录中。
/feishu-read <document_id>
/feishu-read <node_token>
/feishu-read <url>
解析参数
/docx/ → 普通文档，使用 doc export/wiki/ → 知识库文档，使用 wiki export导出为 Markdown（含图片下载）
普通文档:
feishu-cli doc export <document_id> --output /tmp/feishu_doc.md --download-images --assets-dir /tmp/feishu_assets
doc export 会自动解析 User Access Token（如已登录），解析优先级：
--user-access-token 命令行参数FEISHU_USER_ACCESS_TOKEN 环境变量~/.feishu-cli/token.json（通过 auth login 保存）config.yaml 中的 user_access_token找到 User Token 时使用用户身份访问，未找到时回退为 App Access Token（租户身份）。
若遇到 code=1770032 forBidden（App 无权限且未登录）或 code=99991679 Unauthorized（User Token 缺少 scope），需先完成 User Token 授权：
feishu-cli auth login --scopes "docx:document:readonly offline_access"
知识库文档:
feishu-cli wiki export <node_token> --output /tmp/feishu_wiki.md --download-images --assets-dir /tmp/feishu_assets
重要：务必使用 --download-images 参数下载文档中的图片到本地，否则只能看到 feishu://media/<token> 引用，无法理解图片内容。
可选参数：
--user-access-token：手动指定 User Access Token（不填则自动从 ~/.feishu-cli/token.json 读取）--front-matter：在 Markdown 顶部添加 YAML front matter（含标题和文档 ID）--highlight：保留文本颜色和背景色（输出为 HTML <span> 标签）--expand-mentions：展开 @用户为友好格式（默认开启，需要 contact:user.base:readonly 权限）读取文本内容
读取并理解图片内容
--assets-dir 指定的目录是否有下载的图片# 列出下载的图片
ls /tmp/feishu_assets/
# 使用 Read 工具查看图片
# Read /tmp/feishu_assets/image_1.png
# Read /tmp/feishu_assets/image_2.png
报告结果
向用户报告：
| URL 格式 | 类型 | 命令 |
|---|---|---|
https://xxx.feishu.cn/docx/<id> |
普通文档 | doc export |
https://xxx.feishu.cn/wiki/<token> |
知识库（docx/sheet） | wiki export |
https://xxx.larkoffice.com/docx/<id> |
普通文档 | doc export |
https://xxx.larkoffice.com/wiki/<token> |
知识库（docx/sheet） | wiki export |
# 读取普通文档
/feishu-read <document_id>
/feishu-read https://xxx.feishu.cn/docx/<document_id>
# 读取知识库文档
/feishu-read <node_token>
/feishu-read https://xxx.feishu.cn/wiki/<node_token>
导出的 Markdown 支持以下飞书特有块类型的转换：
| 飞书块类型 | Markdown 表现 |
|---|---|
| Callout 高亮块 | > [!NOTE]、> [!WARNING] 等 6 种 GitHub-style alert |
| 块级/行内公式 | $formula$（LaTeX 格式） |
| 画板 (Board) | [画板/Whiteboard](feishu://board/...) 链接 |
| ISV 块 (Mermaid) | 画板链接 |
| QuoteContainer | > 引用语法（支持嵌套） |
| AddOns/SyncedBlock | 透明展开子块内容 |
| Iframe | <iframe> HTML 标签 |
使用 --highlight 参数时，带颜色的文本输出为 <span style="color:..."> 标签。
知识库文档可能是目录节点（包含子节点），需要特殊处理。
当导出知识库文档时，如果 Markdown 内容显示为：
[Wiki 目录 - 使用 'wiki nodes <space_id> --parent <node_token>' 获取子节点列表]
说明这是一个Wiki 目录节点（block_type=42），子文档列表存储在知识库元数据中。
# 1. 先获取节点信息，记录 space_id
feishu-cli wiki get <node_token>
# 2. 列出该节点下的子节点
feishu-cli wiki nodes <space_id> --parent <node_token>
# 步骤 1：尝试导出文档
feishu-cli wiki export <node_token> -o /tmp/doc.md
# 步骤 2：检查内容
# 如果显示 "[Wiki 目录...]"，说明是目录节点
# 步骤 3：获取节点信息
feishu-cli wiki get <node_token>
# 记录 space_id 和 has_child 字段
# 步骤 4：获取子节点
feishu-cli wiki nodes <space_id> --parent <node_token>
# 步骤 5：逐个导出子节点
feishu-cli wiki export <child_node_token_1> -o /tmp/child1.md
feishu-cli wiki export <child_node_token_2> -o /tmp/child2.md
| 错误 | 原因 | 解决 |
|---|---|---|
code=1770032, msg=forBidden |
App Token 无权限访问该文档 | 通过 auth login --scopes "docx:document:readonly offline_access" 授权 User Token，doc export 会自动读取 |
code=99991679, msg=Unauthorized |
User Token 缺少 docx:document:readonly scope |
重新执行 feishu-cli auth login --scopes "docx:document:readonly offline_access" |
code=131002, param err |
参数错误 | 检查 token 格式 |
code=131001, node not found |
节点不存在 | 检查 token 是否正确 |
code=131003, no permission |
无权限访问 | 确认应用有 wiki:wiki:readonly 权限 |
code=131004, space not found |
知识空间不存在 | 检查 space_id 是否正确 |
空内容或 Unknown block type |
特殊块类型 | 见「高级：Wiki 目录节点处理」章节 |
情况 1：文档内容为空
情况 2：图片下载失败
--assets-dir 目录是否可写情况 3：部分块类型无法识别
<!-- Unknown block type: XX -->情况 4：大型文档
feishu-cli doc blocks <doc_id> --all 自动分页如果遇到网络错误或 API 限流：
# 添加 --debug 查看详细错误信息
feishu-cli wiki export <token> --debug
# 等待几秒后重试
sleep 5 && feishu-cli wiki export <token>
Q: 提示权限不足 / no permission / forBidden
docx:document:readonly（普通文档）或 wiki:wiki:readonly（知识库）权限feishu-cli auth login --scopes "docx:document:readonly offline_access"
doc export 会自动读取，无需额外参数Q: 文档不存在 / node not found
document_id 和 node_token）/docx/ 后为 document_id，/wiki/ 后为 node_token）Q: Token 过期 / 认证失败
feishu-cli auth status 检查当前认证状态feishu-cli auth login 重新认证FEISHU_APP_ID 和 FEISHU_APP_SECRET 环境变量是否正确Make data-driven prioritization decisions faster
Draft PRDs, status updates, and stakeholder presentations
Example
Create executive summary of Q3 roadmap, monthly progress report, feature launch announcement
Save 3-5 hours/week on communication overhead
Prerequisites
Time Estimate
30-60 minutes to see productivity improvements
Steps
Common Pitfalls
✓ Do
✗ Don't
💡 Pro Tips
✓ Use when
Use for user story writing, competitive research, roadmap prioritization, stakeholder communication, and PRD drafting. Best for reducing repetitive documentation and research work.
✗ Avoid when
Avoid for strategic product vision (requires deep customer empathy), pricing decisions (needs market and financial expertise), or when face-to-face customer discovery is more valuable than speed.
mattpocock/skills
parcadei/continuous-claude-v3
cursor/plugins
ailabs-393/ai-labs-claude-skills
pproenca/dot-skills
mattpocock/skills
feishu-cli-read is among the better-maintained entries we tried; worth keeping pinned for repeat workflows.
Solid pick for teams standardizing on skills: feishu-cli-read is focused, and the summary matches what you get after install.
Keeps context tight: feishu-cli-read is the kind of skill you can hand to a new teammate without a long onboarding doc.
We added feishu-cli-read from the explainx registry; install was straightforward and the SKILL.md answered most questions upfront.
Useful defaults in feishu-cli-read — fewer surprises than typical one-off scripts, and it plays nicely with `npx skills` flows.
feishu-cli-read fits our agent workflows well — practical, well scoped, and easy to wire into existing repos.
feishu-cli-read has been reliable in day-to-day use. Documentation quality is above average for community skills.
feishu-cli-read has been reliable in day-to-day use. Documentation quality is above average for community skills.
feishu-cli-read is among the better-maintained entries we tried; worth keeping pinned for repeat workflows.
Useful defaults in feishu-cli-read — fewer surprises than typical one-off scripts, and it plays nicely with `npx skills` flows.
showing 1-10 of 31