Feishu Doc Summarizer

Automatically read and summarize Feishu/Lark docx or wiki links in chat using the user's fixed summary schema from MEMORY.md.

Security Scan

The skill's description (summarize Feishu/Lark docs) matches its instructions, but the runtime instructions call Feishu-specific tools without declaring required credentials or explaining where those connectors run, which is an unexplained gap.

Purpose & Capability

The skill's stated purpose (read and summarize Feishu/Lark docx or wiki links) matches the actions described in SKILL.md (resolve wiki→docx, call feishu_wiki and feishu_doc, summarize). However, the SKILL.md relies on feishu_wiki and feishu_doc operations but the skill declares no required credentials or environment variables — a mild incoherence unless the platform provides built-in Feishu connectors. The absence of a homepage/source and no metadata about which integration this uses adds uncertainty.

Instruction Scope

Instructions stay within the stated purpose: detect links, resolve wiki to doc, read document, pull user's summary schema from MEMORY.md, and produce a structured summary. The SKILL.md asks the agent to read MEMORY.md (the user's summary schema) which is reasonable for this task. The instructions do not ask to read unrelated system files, nor to send data to unexpected external endpoints; they only reference feishu_doc/feishu_wiki (expected for a Feishu integration).

Install Mechanism

Instruction-only skill with no install spec or code files — lowest install risk. Nothing is downloaded or written to disk by the skill itself.

Credentials

SKILL.md expects to call feishu_wiki(action=get, token=...) and feishu_doc(action=read, doc_token=...), which will typically require Feishu API credentials or an authenticated connector. The skill's metadata declares no required env vars, no primary credential, and no config paths. That mismatch is the main concern: it is unclear which credentials (if any) will be used, where they are stored, or whether the connector will prompt for or reuse global Feishu credentials. This ambiguity affects data access and potential exfiltration risk.

Persistence & Privilege

The skill is not always-enabled and does not request system-wide persistence. It is user-invocable and allows autonomous invocation (default), which is normal for skills. It does not claim to modify other skills or system settings.

What to consider before installing

Before installing, confirm how the platform provides Feishu access: does your agent have a built-in feishu_doc/feishu_wiki connector and which Feishu account/credentials will it use? Ask whether document contents or generated summaries are stored or sent to any external service beyond your chat. Because the skill reads MEMORY.md for a summary schema, ensure that file doesn't contain sensitive credentials. Test the skill first with a non-sensitive document and verify the permission prompts and where logs or cached data are kept. If the platform expects you to supply Feishu API keys, prefer supplying a least-privilege key and review its scope. If you can't confirm these details, treat the skill cautiously.

Overview

Given a Feishu/Lark document link (docx or wiki), read the document content and reply in-chat with a structured summary following the user’s fixed schema stored in MEMORY.md.

Workflow

0) Input detection

• Trigger when the user message contains a Feishu/Lark docx link like:
  • https://...larkoffice.com/docx/DOC_TOKEN
• Also trigger when the user message contains a Feishu/Lark wiki link like:
  • https://...larkoffice.com/wiki/WIKI_TOKEN

The user may provide no additional instructions; default to summarizing.

1) Resolve link → doc token (if needed)

• If it is a docx link: extract doc_token directly.
• If it is a wiki link:
  • Use feishu_wiki(action=get, token=wiki_token) to resolve the underlying object.
  • If the object type is docx, extract its doc token.
  • If not docx, tell the user what type it is and what you can support.

2) Read document content

• Use feishu_doc(action=read, doc_token=doc_token) to retrieve the full document content.
• If permissions fail or content is empty, ask the user to confirm they granted read access.

3) Summarize with the fixed schema (from memory)

• Before drafting, retrieve the summary schema from memory (search MEMORY.md for “Feishu 云文档摘要偏好” / “固定模板”).
• Produce the summary strictly following the section order and rules in memory.
• Citations: In the “引用原文片段” section, only quote text that appears in the document; do not fabricate.

Long documents

If the document is very long:

1. Chunk by headings/paragraph groups, summarize each chunk briefly.
2. Merge chunk summaries into the final schema.
3. Keep “引用原文片段” short and representative.

4) Reply back to the user

• Send the final formatted summary back to the current conversation.
• Include the original link in “文档元信息/链接”.

Output format (must follow memory)

Follow the user’s schema in MEMORY.md exactly; keep missing items as “无/未知” rather than removing sections.