feishu-doc-writer

Feishu document writing skill. Handles known API pitfalls (block ordering, unsupported formats). Activate when writing content into Feishu docs or creating structured documents.

227 stars

Best use case

feishu-doc-writer is best used when you need a repeatable AI agent workflow instead of a one-off prompt.

Feishu document writing skill. Handles known API pitfalls (block ordering, unsupported formats). Activate when writing content into Feishu docs or creating structured documents.

Teams using feishu-doc-writer should expect a more consistent output, faster repeated execution, less prompt rewriting.

When to use this skill

  • You want a reusable workflow that can be run more than once with consistent structure.

When not to use this skill

  • You only need a quick one-off answer and do not need a reusable workflow.
  • You cannot install or maintain the underlying files, dependencies, or repository context.

Installation

Claude Code / Cursor / Codex

$curl -o ~/.claude/skills/feishu-doc-writer/SKILL.md --create-dirs "https://raw.githubusercontent.com/hyperlist/feishu-multi-agent/main/skills/feishu-doc-writer/SKILL.md"

Manual Installation

  1. Download SKILL.md from GitHub
  2. Place it in .claude/skills/feishu-doc-writer/SKILL.md inside your project
  3. Restart your AI agent — it will auto-discover the skill

How feishu-doc-writer Compares

Feature / Agentfeishu-doc-writerStandard Approach
Platform SupportNot specifiedLimited / Varies
Context Awareness High Baseline
Installation ComplexityUnknownN/A

Frequently Asked Questions

What does this skill do?

Feishu document writing skill. Handles known API pitfalls (block ordering, unsupported formats). Activate when writing content into Feishu docs or creating structured documents.

Where can I find the source code?

You can find the source code on GitHub using the link provided at the top of the page.

Related Guides

SKILL.md Source

# Feishu Document Writer

## ⭐ 推荐:MD 导入 API(长文档首选)

飞书原生 MD 解析,**支持表格**,无 block 乱序。

**流程:** 本地写 .md → 上传素材 → 创建导入任务 → 轮询结果 → 加权限

```python
# Step 1: 上传
POST /drive/v1/medias/upload_all  → file_token

# Step 2: 导入
POST /drive/v1/import_tasks
  body: { file_extension: "md", file_token, type: "docx",
          file_name: "标题", point: {mount_type: 1, mount_key: ""} }
  → ticket

# Step 3: 轮询
GET /drive/v1/import_tasks/{ticket}  → doc_token, url

# Step 4: 加权限
POST /drive/v1/permissions/{doc_token}/members?type=docx
  body: { member_type: "openid", member_id: "ou_xxx", perm: "full_access" }
```

完整 Python 脚本:[references/md-import.py](references/md-import.py)

```bash
# 用法
python3 references/md-import.py report.md "报告标题"
# 或设置环境变量
FEISHU_APP_ID=cli_xxx FEISHU_APP_SECRET=xxx python3 references/md-import.py report.md "标题"
```

## 备选:feishu_doc 工具(短文档/追加)

### 约束
- **无 Markdown 表格**(返回 400)— 用列表替代
- **逐章节 append** — 每次 1 个 heading + 内容,保证顺序
- **创建后必须加权限** — Bot 创建的文档默认只有 Bot 能看

### 工作流
```
1. feishu_doc create → doc_token
2. feishu_perm add → 授权用户
3. feishu_doc append × N → 逐章节写入
```

### 表格替代方案
```markdown
**模型 A — ✅ 通过**
- Token 消耗: 46,817
- 评价: 稳定可靠
```

## 方案选择

| 场景 | 方案 |
|------|------|
| 长文档 / 含表格 / 严格顺序 | ⭐ MD 导入 |
| 短文档 / 追加 / 修改已有文档 | feishu_doc |
| 替换整篇 | feishu_doc write(单次调用无乱序) |

## 报告类文档结构

1. **背景** — 为什么做、测什么
2. **结果总览** — 结论前置(✅/❌),每个对象核心数据
3. **问题详析** — 现象 + 原始证据(代码块)+ 因果链
4. **最终结论** — 一句话 + 建议

**原则:** 章节自包含、结论前置、必须附原始证据、因果链完整。

## Error Handling

| Error | Cause | Fix |
|-------|-------|-----|
| 400 on append | Markdown 表格 | 用 MD 导入或列表替代 |
| Block 乱序 | 多次 append | 用 MD 导入 |
| 403 | 权限不足 | 检查 `docx:document` scope |
| 99992402 on import | 缺 point 字段 | 加 `point: {mount_type:1, mount_key:""}` |

详细消息格式规范见 `references/feishu-message-format.md`。

Related Skills

feishu-chat

227
from hyperlist/feishu-multi-agent

飞书群聊管理:创建群、添加/移除成员、修改群信息。需要 exec 权限执行 curl 命令。

feishu-multi-agent

227
from hyperlist/feishu-multi-agent

飞书多 Agent 系统搭建指南。当用户要求创建新的功能 Agent、配置飞书群聊绑定、 搭建多 Agent 协作系统时激活此 skill。 触发词:创建 agent、新建 agent、添加 agent、create agent、多 agent、飞书绑定。

Maintenance Skill

227
from hyperlist/feishu-multi-agent

飞书多 Agent 项目维护指南 - 仅供维护 feishu-multi-agent 项目时使用。

delegate-agent

227
from hyperlist/feishu-multi-agent

Delegate tasks to agents asynchronously. Triggers on "让XX做", "delegate to", "assign to", "派发", "布置任务".

Config Update Skill

227
from hyperlist/feishu-multi-agent

OpenClaw 配置安全更新指南。

agent-comm

227
from hyperlist/feishu-multi-agent

跨 Agent 通信。当用户说"问XX"、"让XX做"、"发给XX"、"check agent status"时使用。

project-switcher

227
from hyperlist/feishu-multi-agent

多项目管理和目录切换。用户发送 /repo 时列出项目,选择后切换工作目录。 适用于 coder agent 同时维护多个代码仓库的场景。

git-workflow

227
from hyperlist/feishu-multi-agent

Git 工作流规范。管理分支、commit、PR 的标准流程。 用户发送 /git 或涉及版本控制操作时触发。

code-review

227
from hyperlist/feishu-multi-agent

代码审查技能。用户发送 /review 或要求 review 时触发。 自动检查代码质量、安全问题、架构建议。

writer

31392
from sickn33/antigravity-awesome-skills

Document creation, format conversion (ODT/DOCX/PDF), mail merge, and automation with LibreOffice Writer.

Document ProcessingClaude

Cold Email Writer

3891
from openclaw/skills

Writes personalized cold emails that actually get replies

Content & Documentation

Policy Writer

3891
from openclaw/skills

Generate professional internal policies for any business function — HR, IT, finance, compliance, data privacy, acceptable use, and more.

Business Management