← Back to Skills Marketplace
jfvincentyang

feishu-meeting-minutes

by jfvincentyang · GitHub ↗ · v1.2.0 · MIT-0
cross-platform ⚠ suspicious
148
Downloads
0
Stars
0
Active Installs
2
Versions
Install in OpenClaw
/install feishu-meeting-minutes
Description
飞书会议纪要自动生成工具。从飞书妙记链接、minute token 或现成 transcript 文件生成结构化中文会议纪要，并可选导出 PDF、上传回飞书云空间。适用于用户提供飞书妙记链接要求整理会议纪要、要求将逐字稿转正式文档、或希望把会议录音对应 transcript 快速整理成可分发纪要的场景。
README (SKILL.md)

飞书会议纪要生成器

优先使用内置 Node 脚本，不要手写临时 shell 管道。

工作流

  1. 从飞书妙记 URL 或原始 minute_token 中提取 token。
  2. 使用 lark-cli 拉取会议基础信息。
  3. 在独立 session 目录中下载 transcript。
  4. 自动生成结构化 Markdown 会议纪要。
  5. 可选使用 pandoc + xelatex 输出 PDF。
  6. 可选将 PDF 上传回飞书云空间。

运行方式

从飞书妙记直接生成纪要：

node scripts/generate_minutes.mjs --minute-url "https://example.feishu.cn/minutes/obcnqx9afzs2xxmjy6g772nq" --output-dir "./output"

使用原始 token：

node scripts/generate_minutes.mjs --minute-token "obcnqx9afzs2xxmjy6g772nq" --output-dir "./output"

基于已有 transcript 文件生成：

node scripts/generate_minutes.mjs --transcript-file "./transcript.txt" --title "项目周会" --minute-token "obcnqx9afzs2xxmjy6g772nq" --output-dir "./output"

导出 PDF 并上传：

node scripts/generate_minutes.mjs --minute-token "obcnqx9afzs2xxmjy6g772nq" --output-dir "./output" --pdf --upload

依赖

  • 需要 node
  • 拉取妙记与上传文件时需要 lark-cli
  • 使用 --pdf 时需要 pandoc 与 xelatex
  • 建议安装中文字体 Noto Sans CJK SC

所需权限

拉取妙记与 transcript 前，需要这些 scope：

  • minutes:minutes:readonly
  • minutes:minutes.artifacts:read
  • minutes:minutes.transcript:export
  • vc:note:read

上传 PDF 前，还需要：

  • drive:file:upload

授权示例：

lark-cli auth login --scope "minutes:minutes:readonly minutes:minutes.artifacts:read minutes:minutes.transcript:export vc:note:read drive:file:upload"

产物

  • meeting_minutes_YYYYMMDD_\x3Cslug>_\x3Ctoken>.md
  • meeting_minutes_YYYYMMDD_\x3Cslug>_\x3Ctoken>.pdf（仅 --pdf）

注意事项

  • 脚本只会在它自己创建的 session 目录内搜索 transcript，避免误用历史文件。
  • 会议纪要为结构化自动整理结果，分发前应结合原始 transcript 复核。
  • 如需调整输出格式，按需读取 references/template.md。
Usage Guidance
This skill appears to do what it claims: it runs a local Node script which calls lark-cli to fetch Feishu minute data and optionally uses pandoc/xelatex and lark-cli to produce and upload PDFs. Before installing or running: 1) review the bundled script (scripts/generate_minutes.mjs) yourself — it is included and readable; 2) only grant lark-cli the listed scopes if you trust that CLI and want it to fetch minutes and upload files; 3) if you are concerned about data exfiltration, avoid using --upload and prefer supplying a local transcript file instead of authorizing remote fetch; 4) run in a controlled directory and inspect generated artifacts before sharing; 5) if you need higher assurance, run the script in an isolated environment or container.
Capability Analysis
Type: OpenClaw Skill Name: feishu-meeting-minutes Version: 1.2.0 The skill bundle is a legitimate tool for generating structured meeting minutes from Feishu (Lark) transcripts. The core logic in `scripts/generate_minutes.mjs` uses `spawnSync` with `shell: false` to interact with the `lark-cli` and `pandoc` binaries, effectively mitigating shell injection risks. It includes robust input validation for tokens and sanitizes filenames. The instructions in `SKILL.md` are consistent with the code's functionality and even advise the agent against using manual shell pipes, favoring the secure Node.js implementation.
Capability Assessment
✓ Purpose & Capability
Name/description (Feishu meeting minutes) match the code and instructions: the script extracts a minute token or accepts a transcript, calls lark-cli to fetch artifacts/transcripts, summarizes text, renders Markdown, and optionally calls pandoc/xelatex and lark-cli to upload. No unrelated credentials or services are requested.
ℹ Instruction Scope
SKILL.md instructs the agent to run the included Node script which itself invokes external CLI tools (lark-cli, pandoc, xelatex). The script reads/writes files under an output/session directory and only references the transcript and metadata needed for summarization. Note: the script uses child process calls to run external CLIs (expected for this workflow). The instructions ask the user to authenticate lark-cli with several Feishu scopes — this is appropriate but grants lark-cli access to fetch minutes/transcripts and to upload files if --upload is used.
✓ Install Mechanism
No install spec — instruction-only with a bundled Node script. No downloads from arbitrary URLs or archive extraction. The runtime relies on existing CLIs (node, lark-cli, pandoc, xelatex) which is proportionate to the described capabilities.
✓ Credentials
The skill requests no environment variables or secret fields. Authentication is delegated to lark-cli (the SKILL.md shows the required Feishu scopes). This is proportional: network access and credentials are handled by the official CLI the user authorizes, not by hidden env variables inside the skill.
✓ Persistence & Privilege
Skill is not always-enabled and does not attempt to modify other skills or system-wide settings. It creates and uses a per-session output directory as documented. Autonomous invocation (disable-model-invocation:false) is the platform default and not a standalone concern here.
How to Use
  1. Make sure OpenClaw is installed (local or Docker)
  2. Run the install command in chat: /install feishu-meeting-minutes
  3. After installation, invoke the skill by name or use /feishu-meeting-minutes
  4. Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.2.0
Safer 1.2.0 release: replaced bash flow with a Node CLI, added stricter token parsing, session-scoped transcript lookup, explicit dependency/scope declarations, Markdown generation, optional PDF export, and optional Feishu Drive upload.
v1.0.0
Initial release: 自动化生成飞书会议纪要的全流程工具 - 支持从飞书妙记链接自动提取会议内容，生成专业格式的纪要，并输出为 PDF 文件 - 支持用户以多种触发方式（提供妙记链接、关键词指令、会议录音等）生成会议纪要 - 实现会议纪要整理、逐字稿提取、内容结构化和 PDF 导出等完整流程 - 支持一键上传会议纪要 PDF 至飞书云空间 - 明确所需 API 权限与使用指引，保障顺畅集成
Metadata
Slug feishu-meeting-minutes
Version 1.2.0
License MIT-0
All-time Installs 0
Active Installs 0
Total Versions 2
Frequently Asked Questions

What is feishu-meeting-minutes?

飞书会议纪要自动生成工具。从飞书妙记链接、minute token 或现成 transcript 文件生成结构化中文会议纪要，并可选导出 PDF、上传回飞书云空间。适用于用户提供飞书妙记链接要求整理会议纪要、要求将逐字稿转正式文档、或希望把会议录音对应 transcript 快速整理成可分发纪要的场景。 It is an AI Agent Skill for Claude Code / OpenClaw, with 148 downloads so far.

How do I install feishu-meeting-minutes?

Run "/install feishu-meeting-minutes" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.

Is feishu-meeting-minutes free?

Yes, feishu-meeting-minutes is completely free, licensed under MIT-0. You can download, install and use it at no cost.

Which platforms does feishu-meeting-minutes support?

feishu-meeting-minutes is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).

Who created feishu-meeting-minutes?

It is built and maintained by jfvincentyang (@jfvincentyang); the current version is v1.2.0.

More Skills
self-improving agent
Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Clau...
⬇ 463942 · by pskoett
Skill Vetter
Security-first skill vetting for AI agents. Use before installing any skill from ClawdHub, GitHub, or other sources. Checks for red flags, permission scope, and suspicious patterns.
⬇ 259883 · by spclaudehome
Polymarket
Query Polymarket prediction markets. Check odds, find trending markets, search events, track price movements.
⬇ 232503 · by joelchance
Self-Improving + Proactive Agent
Self-reflection + Self-criticism + Self-learning + Self-organizing memory. Agent evaluates its own work, catches mistakes, and improves permanently. Use when...
⬇ 200739 · by ivangdavila
Github
Interact with GitHub using the `gh` CLI. Use `gh issue`, `gh pr`, `gh run`, and `gh api` for issues, PRs, CI runs, and advanced queries.
⬇ 191401 · by steipete
ontology
Typed knowledge graph for structured agent memory and composable skills. Use when creating/querying entities (Person, Project, Task, Event, Document), linkin...
⬇ 190375 · by oswalpalash

💬 Comments