Token导航 LogoToken导航

Agent Skill · 研究检索

add-feishu(添加飞书)

add-feishu 用于查找、检索和筛选相关信息,适合在 OpenClaw 中需要根据关键词、任务场景或来源线索快速定位候选结果时使用。可结合来源仓库、安装命令和原始 README 继续核验具体用法。安装前建议确认权限范围、维护状态,以及是否会触发联网、命令执行或文件读写。

add-feishu 是研究检索类 Agent Skill,可用宿主为 OpenClaw,通过ClawHub获取,权限为需要联网;许可证为 MIT-0,第三方扫描已通过,按安装量在研究检索类的 73,675 个 Skill 里排第 9,543。

总安装 14,041周安装 597GitHub Stars 公开资料未说明下载 4,919核验 2026-05-01

安装说明

本站只整理中文说明,不托管安装包,也不代用户安装。
GitHub
许可证
MIT-0
版本
1.0.0

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手,先确认命令和权限,再让它执行。

请帮我安装这个 Agent Skill:add-feishu(添加飞书)
来源仓库:https://github.com/will-17173/add-feishu
安装命令:
openclaw skills install add-feishu
安装前请先检查当前环境是否支持对应 CLI,并向我确认将要执行的命令、安装目录、联网范围和文件读写权限;确认后再执行。

命令行安装

复制命令到本机终端执行。该命令会通过 OpenClaw 从第三方来源获取 Skill;本站只展示命令,不托管安装包,也不自动执行。

ClawHubOpenClaw
openclaw skills install add-feishu

这个 Skill 是做什么的

研究检索类 Skill 主要解决「找资料、核对事实、把来源整理清楚」的问题,通常会让助手先检索再总结。

通过 WebSocket 长连接接入飞书频道消息流。无需公网 URL 或 ngrok 隧道转发。可与 Slack、Telegram 等平台共存使用。需配置飞书机器人 Webhook 密钥。适用宿主包括 OpenClaw,接入前应确认版本、权限和运行环境要求。消息处理应遵循企业信息安全规范。

add-feishu 属于研究检索类 Skill,可作为该场景下的辅助能力补充。

上手步骤

4 步
  1. 1

    确认自己的宿主工具

    公开资料标注支持 OpenClaw;先确认自己用的是其中之一,再按对应工具的 Skills 目录放置。

  2. 2

    拿到安装命令

    可以直接复制的命令是 openclaw skills install add-feishu;命令里的占位符换成自己的路径或密钥再执行。

  3. 3

    安装后重启宿主

    命令执行完要完全退出宿主工具再打开,让新装的 Skill 被重新扫描到,否则列表里可能看不到。

  4. 4

    按最小权限试用

    它需要需要联网,先在测试目录或测试账号里跑,确认没问题再放到正式项目。

常见问题

6 条

add-feishu 怎么安装?

在终端执行 openclaw skills install add-feishu。装完完全退出宿主工具再打开,让它重新扫描本地 Skill。

add-feishu 支持哪些 AI 工具?

公开资料标注支持 OpenClaw。其他工具只要能读取本地 Skill 目录,一般也能手动放进去,但要自己确认触发方式是否一致。

add-feishu 需要什么权限?

权限级别是需要联网。该 Skill 可能需要联网访问来源站点、仓库或外部 API;具体网络访问范围需要结合源码和 README 复核。

add-feishu 是免费的吗?

来源标注的许可证是 MIT-0。本站不代收任何费用,也不托管安装包;能否商用、要不要署名,以许可证原文为准。

add-feishu 用的人多吗?

公开数据是累计安装 14,041 次,近一周安装 597 次,下载 4,919 次。这些数字来自第三方目录统计,只能当作热度参考,不代表质量或安全性。

add-feishu 安全吗?

第三方扫描结果为通过,但这只覆盖已知的静态检查项,不能替代自己读一遍源码和安装命令。

值得选的地方和要先想清楚的地方

值得选的地方

  • 专注 OpenClaw 一种宿主,触发方式和使用习惯不用来回切换。
  • 许可证明确为 MIT-0,商用和分发边界好判断。
  • 第三方扫描已通过,常见的高风险行为没有命中。

先想清楚的地方

  • 第三方目录整理,版本更新和行为细节以来源仓库为准。

适不适合你

更适合

  • 已经在用 OpenClaw,想直接扩展它能力的人。
  • 需要处理研究检索类任务、又不想每次都手写提示词的人。
  • 需要许可证清楚、并且有第三方扫描结果的团队项目。

不太适合

  • 需要厂商级技术支持和 SLA 的生产系统。

研究检索类 Skill 对比

6 个同类
Skill总安装GitHub 星权限许可证扫描
find-skills

寻找技能 · Codex、Claude

31,199,81316,486操作浏览器MIT有提醒
self-improving-agent

自我改进 Agent · OpenClaw

16,464,0023,396接触敏感数据MIT-0通过
soultrace

灵魂追踪 · Codex、Claude

7,588,94412需要联网未明确有提醒
self-improving

自我完善 · OpenClaw

6,829,2841,046需要联网MIT-0通过
microsoft-foundry

微软代工厂 · Codex、Claude

6,614,144764调用外部服务未明确有提醒
add-feishu

添加飞书 · 本页

14,041—需要联网MIT-0通过

按安装量取同分类前几名;数字来自第三方目录统计,只作热度参考,不代表质量结论。

SKILL.md 原文

name
add-feishu
description
Add Feishu (Lark) as a channel. Uses WebSocket long connection — no public URL or ngrok needed. Works alongside WhatsApp, Telegram, Slack, or as a standalone channel.

Add Feishu Channel

This skill adds Feishu (飞书/Lark) support to NanoClaw using the skills engine for deterministic code changes, then walks through interactive setup.

Phase 1: Pre-flight

Check if already applied

Read .nanoclaw/state.yaml. If feishu is in applied_skills, skip to Phase 3 (Setup). The code changes are already in place.

Ask the user

Use AskUserQuestion to collect configuration:

AskUserQuestion: Do you have a Feishu (Lark) app already created, or do you need to create one?

If they have one, ask for the App ID and App Secret. If not, walk them through creation in Phase 3.

Phase 2: Apply Code Changes

Run the skills engine to apply this skill's code package. The package files are in this directory alongside this SKILL.md.

Initialize skills system (if needed)

If .nanoclaw/ directory doesn't exist yet:

npx tsx scripts/apply-skill.ts --init

Apply the skill

npx tsx scripts/apply-skill.ts .claude/skills/add-feishu

This deterministically:

  • Adds src/channels/feishu.ts (FeishuChannel class with self-registration via registerChannel)
  • Adds src/channels/feishu.test.ts (unit tests)
  • Appends import './feishu.js' to the channel barrel file src/channels/index.ts
  • Installs the @larksuiteoapi/node-sdk npm dependency
  • Updates .env.example with FEISHU_APP_ID and FEISHU_APP_SECRET
  • Records the application in .nanoclaw/state.yaml

If the apply reports merge conflicts, read the intent file:

  • modify/src/channels/index.ts.intent.md — what changed and invariants

Validate code changes

npm test
npm run build

All tests must pass (including the new feishu tests) and build must be clean before proceeding.

Phase 3: Setup

Create Feishu App (if needed)

If the user doesn't have an app, tell them:

I need you to create a Feishu app: 1. Go to Feishu Open Platform (or Lark Open Platform for international) 2. Click Create App → Custom App 3. Fill in app name and description (e.g., "NanoClaw Assistant") 4. Go to Credentials & Basic Info — copy the App ID and App Secret 5. Go to Event Subscriptions → Add Events → search and add: - im.message.receive_v1 (Receive messages — v2.0) 6. Go to Permissions & Scopes → add the following permissions: - im:message (Send & receive messages) - im:message:send_as_bot (Send messages as bot) - im:chat (Read chat info) - im:chat.members:read (Read chat members) 7. Go to Bot tab → enable the bot feature 8. Click Publish / Apply for Release Note: For enterprise use, your IT admin may need to approve the app.

Wait for the user to provide the App ID (format: cli_xxxxxxxxxxxxxxxxxx) and App Secret.

Configure environment

Add to .env:

FEISHU_APP_ID=cli_xxxxxxxxxxxxxxxxxx
FEISHU_APP_SECRET=your_app_secret_here

Channels auto-enable when their credentials are present — no extra configuration needed.

Sync to container environment:

mkdir -p data/env && cp .env data/env/env

The container reads environment from data/env/env, not .env directly.

Build and restart

npm run build
launchctl kickstart -k gui/$(id -u)/com.nanoclaw  # macOS
# Linux: systemctl --user restart nanoclaw

Phase 4: Registration

Get Chat ID

Tell the user:

To register a Feishu chat with NanoClaw, I need the chat's ID: For a direct (p2p) chat: 1. Add the bot to your Feishu contacts 2. Open a direct message to the bot 3. Send any message — NanoClaw will log the JID as fs:p2p:<your_open_id> 4. Check logs/nanoclaw.log for: Message from unregistered Feishu chat For a group chat: 1. Add the bot to the group: Group Settings → Members → Add Bot 2. Send any message in the group (or @mention the bot) 3. NanoClaw will log the JID as fs:oc_<chat_id> 4. Check logs/nanoclaw.log for: Message from unregistered Feishu chat

Tell user to check the log:

tail -f logs/nanoclaw.log | grep "unregistered Feishu"

Wait for the user to provide the JID (format: fs:oc_xxxxx or fs:p2p:ou_xxxxx).

Register the chat

For a main chat (responds to all messages):

registerGroup("fs:<chat-id>", {
  name: "<chat-name>",
  folder: "feishu_main",
  trigger: `@${ASSISTANT_NAME}`,
  added_at: new Date().toISOString(),
  requiresTrigger: false,
  isMain: true,
});

For additional chats (trigger-based, responds only when @mentioned or triggered):

registerGroup("fs:<chat-id>", {
  name: "<chat-name>",
  folder: "feishu_<group-name>",
  trigger: `@${ASSISTANT_NAME}`,
  added_at: new Date().toISOString(),
  requiresTrigger: true,
});

Phase 5: Verify

Test the connection

Tell the user:

Send a message to your registered Feishu chat: - For main chat: Any message works - For non-main: @mention the bot or include a question/request keyword The bot should respond within a few seconds.

Check logs if needed

tail -f logs/nanoclaw.log

Troubleshooting

Bot not receiving messages

Check:

  1. im.message.receive_v1 event is added in the app's Event Subscriptions
  2. App is published / enabled (enterprise apps need admin approval)
  3. For groups: the bot is added as a member of the group
  4. FEISHU_APP_ID and FEISHU_APP_SECRET are set in .env AND synced to data/env/env
  5. Service is running: launchctl list | grep nanoclaw (macOS) or systemctl --user status nanoclaw (Linux)

Bot not responding in groups

By default, NanoClaw only responds in groups when:

  • The bot is @mentioned
  • The message contains a request keyword (帮, 请, 分析, etc.)
  • The message ends with ? or ?

To make the bot respond to all messages in a group, register it with requiresTrigger: false.

"Message from unregistered Feishu chat" in logs

This is normal — it means the bot is receiving messages, but the chat isn't registered yet. Follow Phase 4 to register.

Finding the JID

If the log message is hard to find:

sqlite3 store/messages.db "SELECT DISTINCT chat_jid FROM chats WHERE channel = 'feishu'"

App Secret security

The App Secret is sensitive. Store it only in .env and data/env/env. Do NOT commit these files to version control.

JID Format Reference

Chat typeJID formatExample
Group chatfs:oc_<id>fs:oc_4e359893776d45f7cd05d40e3ee10f55
Direct (p2p)fs:p2p:<open_id>fs:p2p:ou_7a66d6bd1baa3e6e3d7b3df9a8c90000

After Setup

If running npm run dev while the service is active:

# macOS:
launchctl unload ~/Library/LaunchAgents/com.nanoclaw.plist
npm run dev
# When done testing:
launchctl load ~/Library/LaunchAgents/com.nanoclaw.plist
# Linux:
# systemctl --user stop nanoclaw
# npm run dev
# systemctl --user start nanoclaw

Removal

To remove Feishu integration:

  1. Delete src/channels/feishu.ts and src/channels/feishu.test.ts
  2. Remove import './feishu.js' from src/channels/index.ts
  3. Remove FEISHU_APP_ID and FEISHU_APP_SECRET from .env
  4. Remove Feishu registrations from SQLite: sqlite3 store/messages.db "DELETE FROM registered_groups WHERE jid LIKE 'fs:%'"
  5. Uninstall: npm uninstall @larksuiteoapi/node-sdk
  6. Rebuild: npm run build && launchctl kickstart -k gui/$(id -u)/com.nanoclaw (macOS) or npm run build && systemctl --user restart nanoclaw (Linux)

平台分布

OpenClaw

80.47%
按下载量换算3,958

安全审计

VirusTotal

通过

ClawScan

通过

Static analysis

未展示

权限和风险

需要联网

该 Skill 可能需要联网访问来源站点、仓库或外部 API;具体网络访问范围需要结合源码和 README 复核。

安装前确认

本站仅展示第三方公开信息,不托管安装包,不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。目前只有一个公开来源,建议同时核对源仓库。

继续浏览同类 Skills