飞书文档文件夹摘要生成器

Extract summaries from all documents in a Feishu folder. Use when the user needs to recursively scan a Feishu wiki space or drive folder, read all documents...

Security Scan

The skill's code and runtime instructions are coherent with its stated purpose (recursively summarizing documents in a Feishu folder), but it does not declare how Feishu authentication/permissions are provided — confirm platform connectors and access scope before use.

Purpose & Capability

Name/description match the included instructions and helper script: both focus on recursively reading Feishu wiki/drive folders and producing a Markdown summary report. The helper Python file contains only report-generation utilities and does not request unrelated capabilities.

Instruction Scope

SKILL.md explicitly instructs the agent to parse Feishu URLs and call feishu_wiki and feishu_doc actions to traverse and read documents. That is within scope for a folder-summary skill. However, the SKILL.md and script do not state how authentication is handled (no env vars or tokens declared) — the skill appears to assume the agent/platform provides Feishu access. Also note the instructions will cause the agent to read the full contents of all documents in the target folder (sensitive data access) — this is expected but important to be aware of.

Install Mechanism

No install spec and no external downloads. The skill is effectively instruction-driven with a small helper script that contains only local formatting and summarization helpers. Nothing in the install surface writes or executes remote code.

Credentials

The skill declares no required environment variables or credentials. In practice, Feishu API calls require authorization; the SKILL.md expects feishu_wiki/feishu_doc actions (likely provided by the platform) to handle auth. This omission is not necessarily malicious but is a gap: verify how your agent/platform supplies Feishu credentials and what scope (read-only vs. read/write) it grants.

Persistence & Privilege

always is false and the skill does not request persistent presence or attempt to modify other skills or global agent settings. It does not include autonomous 'always-on' privileges.

Assessment

This skill appears to do what it claims: recursively read documents in a Feishu wiki/drive folder and produce a Markdown report. Before installing, confirm: (1) how Feishu authentication is provided by your agent/platform (the skill does not declare required env vars or tokens), and ensure the granted credentials are least-privilege (prefer read-only). (2) The skill will read the full content of every document in the target folder — do not use it on folders that contain sensitive or private data unless you trust the agent and environment. (3) The included Python script only contains local formatting utilities and does not contact external endpoints or exfiltrate data; nonetheless, verify where generated reports are stored or transmitted by your agent. If you need higher assurance, request or inspect how the agent supplies Feishu tokens and audit access logs on your Feishu account.

Feishu Folder Summary

This skill extracts summaries from all documents in a Feishu folder (wiki or drive), recursively scanning sub-folders and generating a comprehensive Markdown report.

Overview

The skill performs the following operations:

1. Parses the Feishu folder URL to extract space_id and node_token
2. Recursively traverses the folder structure using feishu_wiki API
3. Reads each document's content using feishu_doc API
4. Generates structured summaries for each document
5. Compiles a comprehensive Markdown report with:
   • Complete directory tree
   • Document summaries organized by folder
   • Statistics and status overview
   • Links to original documents

Supported URL Formats

• Wiki folders: https://{domain}.feishu.cn/wiki/{node_token}
• Drive folders: https://{domain}.feishu.cn/drive/folder/{folder_token}

Workflow

Step 1: Extract Folder Information

Parse the provided Feishu URL to identify:

• Document type (wiki or drive)
• Space ID (for wiki)
• Node token or folder token

Step 2: Recursive Traversal

Use feishu_wiki API to traverse the folder structure:

feishu_wiki action="get" token="{node_token}"         # Get folder info
feishu_wiki action="nodes" space_id="{space_id}"      # List child nodes

For folders with has_child: true, recursively process child nodes.

Step 3: Document Reading

For each document node, read its content:

feishu_doc action="read" doc_token="{obj_token}"

Step 4: Generate Summary

Extract from each document:

• Title: Document title
• Type: Document or Folder
• Status: Complete, In Progress, or Empty
• Core Content: Key points, main topics, important information
• Child Documents: If folder, list contained documents

Step 5: Compile Report

Generate a Markdown report with:

1. Header (source URL, generation time, document count)
2. Directory tree visualization
3. Hierarchical summaries (by folder level)
4. Statistics table
5. Related links

Output Format

The generated report includes:

# {Folder Name} Document Summary Report

**Source:** {URL}  
**Generated:** {Timestamp}  
**Total Documents:** {Count}

---

## Directory Structure

{Tree visualization}

---

## Level 1 Summaries

### 1. {Document Name}
- **Type:** {docx/folder}
- **Status:** {Complete/In Progress/Empty}
- **Summary:** {Core content description}

### 2. {Folder Name}/
- **Type:** folder
- **Documents:** {Count}
- **Summary:** {Folder description}

#### 2.1 {Child Document}
- **Type:** docx
- **Summary:** {Content summary}

---

## Statistics

| Category | Count | Status |
|----------|-------|--------|
| Total | X | - |
| Complete | X | ✅ |
| In Progress | X | 🚧 |
| Empty | X | ⚠️ |

---

*Report generated by feishu-folder-summary skill*

Example Usage

User Request:

"Extract summaries from https://caz6yhvgk5z.feishu.cn/wiki/BzslwD3Nei1Dggkvin5cV2hDnob"

Skill Execution:

1. Parse URL → Wiki folder, node_token=BzslwD3Nei1Dggkvin5cV2hDnob
2. Get folder info → space_id=7593876306731732193, title="AI云平台"
3. Recursively traverse → Found 14 level-1 nodes, 30+ child documents
4. Read each document → Extract content and generate summaries
5. Compile report → Generate comprehensive Markdown summary

Output:

• Complete directory tree
• Hierarchical summaries for all 44 documents
• Status tracking (✅ Complete, 🚧 In Progress, ⚠️ Empty)
• Statistics overview

Key Considerations

• Recursive Depth: Process all levels of nested folders
• Document Types: Handle docx (documents) and folder (containers)
• Error Handling: Continue processing if individual document read fails
• Content Length: Generate concise but informative summaries
• Status Detection: Identify empty or placeholder documents
• Token Efficiency: Summarize long documents appropriately

API Reference

See references/feishu_api.md for detailed API documentation.