← 返回 Skills 市场
jason-aka-chen

Feishu Bot

作者 jason-aka-chen · GitHub ↗ · v1.0.0 · MIT-0
cross-platform ⚠ suspicious
121
总下载
0
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install feishu-bot-chen
功能描述
Feishu (Lark) Bot integration for messaging, group management, and approval workflows. Send messages, manage groups, handle approvals, and automate notificat...
使用说明 (SKILL.md)

Feishu Bot

Complete Feishu/Lark bot integration for AI agents.

Features

1. Messaging

  • Send text, rich text, and card messages
  • Send to users, groups, or via webhook
  • Reply to messages
  • Upload and send files/images

2. Group Management

  • Create groups
  • Add/remove members
  • Update group info
  • Bot group management

3. Approval Workflows

  • Create approval instances
  • Query approval status
  • Cancel approvals
  • Approval notifications

Prerequisites

  1. Create a Feishu App at https://open.feishu.cn/app
  2. Get App ID and App Secret
  3. Configure permissions:
    • im:message - Send messages
    • im:message:send_as_bot - Send as bot
    • contact:user.base:readonly - Read user info
    • im:chat - Manage groups
    • approval:approval - Approval workflows

Configuration

Set environment variables:

export FEISHU_APP_ID="cli_xxx"
export FEISHU_APP_SECRET="xxx"

Or configure in OpenClaw settings.

Usage

Send Text Message

from feishu_bot import FeishuBot

bot = FeishuBot()

# Send to user
bot.send_text("user_id", "Hello from bot!")

# Send to group
bot.send_text("chat_id", "Group message", is_chat=True)

Send Card Message

card = {
    "type": "template",
    "data": {
        "template_id": "xxx",
        "template_variable": {"title": "Notification"}
    }
}
bot.send_card("chat_id", card)

Create Group

group = bot.create_group(
    name="Project Team",
    user_ids=["ou_xxx", "ou_yyy"]
)
print(group["chat_id"])

Approval Workflow

# Create approval
approval = bot.create_approval(
    approval_code="xxx",
    user_id="ou_xxx",
    form={"field1": "value1"}
)

# Query status
status = bot.get_approval_instance(approval["instance_id"])

API Reference

Method Description
send_text(target, text, is_chat=False) Send text message
send_card(target, card, is_chat=False) Send card message
send_image(target, image_key, is_chat=False) Send image
send_file(target, file_key, is_chat=False) Send file
create_group(name, user_ids) Create group
add_group_members(chat_id, user_ids) Add members
remove_group_members(chat_id, user_ids) Remove members
create_approval(approval_code, user_id, form) Create approval
get_approval_instance(instance_id) Get approval status

Error Handling

Common errors:

  • 99991663: Token expired - refresh tenant token
  • 99991664: Permission denied - check app permissions
  • 99991661: User not found - verify user_id

Links

安全使用建议
This skill appears to be a straightforward Feishu (Lark) bot implementation, but there are a few things to check before installing: - The SKILL.md and the Python code require FEISHU_APP_ID and FEISHU_APP_SECRET (sensitive API credentials). The registry metadata did not declare those env vars — confirm the owner will prompt for/provide these securely before enabling the skill. - The code imports the 'requests' library but no dependency list or install steps are included. Ensure your environment will provide the required Python packages or that you trust the skill won't attempt to pull/install dependencies from untrusted sources. - Review the code yourself (or ask the publisher) to ensure the FEISHU_APP_ID/SECRET are used only for legitimate Feishu API calls and not forwarded elsewhere. The current code only calls open.feishu.cn endpoints and a user-supplied webhook URL, but always verify the source of the skill and the maintainer's reputation. - Be cautious if you plan to use upload_image or file-related methods: they will read local files (you must pass a path), so avoid passing sensitive local files. If you don't trust the publisher or cannot verify how credentials are handled, do not install or provide credentials. If you proceed, supply credentials with least privilege possible (Feishu app scoped to only the permissions you need) and monitor token usage.
功能分析
Type: OpenClaw Skill Name: feishu-bot-chen Version: 1.0.0 The skill bundle provides a legitimate integration for the Feishu (Lark) Open Platform API, enabling messaging, group management, and approval workflows. The implementation in feishu_bot.py follows standard API practices, uses official endpoints (open.feishu.cn), and contains no evidence of malicious behavior, data exfiltration, or prompt injection.
能力评估
ℹ Purpose & Capability
The SKILL.md and feishu_bot.py both implement expected Feishu bot capabilities (messaging, group mgmt, approvals) and call the Feishu Open Platform endpoints. This capability matches the name/description. However, the registry metadata declares no required environment variables or primary credential even though the instructions and code require FEISHU_APP_ID and FEISHU_APP_SECRET.
✓ Instruction Scope
The runtime instructions are scoped to Feishu API interactions: sending messages, uploading images, group and approval APIs. They instruct setting FEISHU_APP_ID/FEISHU_APP_SECRET and using the provided methods. The SKILL.md does not instruct reading unrelated system files or transmitting data to unexpected external endpoints.
ℹ Install Mechanism
There is no install spec (instruction-only plus a Python source file). This reduces install risk. However, the code imports the third-party 'requests' library but the skill does not declare dependencies; the runtime may fail or implicitly rely on a network-visible package being present in the environment.
⚠ Credentials
The SKILL.md and code expect FEISHU_APP_ID and FEISHU_APP_SECRET (sensitive credentials) which are appropriate for a Feishu integration. But the package metadata lists no required env vars or primary credential; that mismatch is concerning because the platform may not surface the credential requirement to you, and the skill will still attempt to read those env vars at runtime. No other unrelated credentials are requested.
✓ Persistence & Privilege
The skill does not request 'always: true', does not modify other skills or system config, and does not request elevated persistence. It runs as a normal, user-invocable skill.
如何使用
  1. 确保已安装 OpenClaw（本地或 Docker 部署）
  2. 在对话框中输入安装命令：/install feishu-bot-chen
  3. 安装完成后，直接呼叫该 Skill 的名称或使用 /feishu-bot-chen 触发
  4. 根据 Skill 的参数说明提供必要输入，即可获得结构化输出
版本历史
v1.0.0
Initial release of Feishu (Lark) Bot integration. - Send text, rich text, and card messages to users or groups - Group management: create groups, add/remove members, update info - Approval workflows: create approval requests, check status, cancel, receive notifications - Support for file and image upload/sending - Provides environment-based configuration and API reference for easy integration
元数据
Slug feishu-bot-chen
版本 1.0.0
许可证 MIT-0
累计安装 0
当前安装数 0
历史版本数 1
常见问题

Feishu Bot 是什么？

Feishu (Lark) Bot integration for messaging, group management, and approval workflows. Send messages, manage groups, handle approvals, and automate notificat... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 121 次。

如何安装 Feishu Bot？

在 OpenClaw 或 Claude Code 对话框中运行命令「/install feishu-bot-chen」即可一键安装，无需额外配置。

Feishu Bot 是免费的吗？

是的，Feishu Bot 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。

Feishu Bot 支持哪些平台？

Feishu Bot 跨平台运行，可在任意部署了 OpenClaw / Claude Code 的环境中使用（cross-platform）。

谁开发了 Feishu Bot？

由 jason-aka-chen（@jason-aka-chen）开发并维护，当前版本 v1.0.0。

推荐 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...
⬇ 463283 · 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.
⬇ 259410 · 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...
⬇ 200423 · 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.
⬇ 191115 · by steipete
ontology
Typed knowledge graph for structured agent memory and composable skills. Use when creating/querying entities (Person, Project, Task, Event, Document), linkin...
⬇ 190156 · by oswalpalash

💬 留言讨论