← 返回 Skills 市场
seetherianbow

Feishu Cards

作者 SeeTheRainBow · GitHub ↗ · v1.0.0
cross-platform ⚠ suspicious
479
总下载
0
收藏
6
当前安装
1
版本数
在 OpenClaw 中安装
/install feishu-cards
功能描述
Send customizable interactive Feishu cards with titles, content, buttons, and color templates via Feishu Open API for users or group chats.
使用说明 (SKILL.md)

Feishu Cards

Send interactive cards to Feishu (飞书) directly via Feishu Open API.

When to Use

  • User wants to send rich interactive messages in Feishu
  • Need buttons, forms, or dropdown menus in messages
  • Want beautifully formatted messages with colors

Installation

clawhub install feishu-cards

Usage

CLI

# Basic card
feishu-cards --to "ou_xxx" --title "标题" --content "内容"

# With buttons
feishu-cards --to "ou_xxx" --title "任务" --content "有新任务" --buttons "处理,稍后"

# Custom color
feishu-cards --to "ou_xxx" --title "警告" --content "注意" --template "red"

# To chat
feishu-cards --to "oc_xxx" --type "chat_id" --title "群通知" --content "大家好"

As Python Module

from feishu_card_sender import FeishuCardSender

sender = FeishuCardSender()
result = sender.send(
    recipient_id="ou_xxx",
    title="任务提醒",
    content="你有一个新任务",
    buttons=["立即处理", "稍后提醒"],
    template="blue"
)

Options

Flag Description Default
--to Recipient ID (user or chat) Required
--type ID type: open_id, user_id, chat_id open_id
--title Card title Required
--content Card content text Required
--buttons Comma-separated buttons None
--template Color: blue, green, red, yellow, grey blue
--note Optional note None

Card Elements

  • Header - Title with color template
  • Content - Main text (plain text format)
  • Buttons - Interactive buttons (primary/default types)
  • Note - Additional info with icon

Button Types

  • primary - Blue button (first button)
  • default - Gray button (other buttons)

Examples

Task Notification

python3 feishu_card_sender.py \
  --to "ou_9d00de9a95a2fb69c425f0a39930c67a" \
  --title "📋 任务通知" \
  --content "你有一个新任务待处理" \
  --buttons "立即处理,稍后提醒" \
  --template "blue"

Alert Card

python3 feishu_card_sender.py \
  --to "ou_xxx" \
  --title "⚠️ 警告" \
  --content "账户存在异常登录" \
  --template "red" \
  --buttons "查看详情"

Requirements

  • Python 3.7+
  • requests library

Install: pip install requests

Configuration

Credentials are read from environment variables (optional):

  • FEISHU_APP_ID
  • FEISHU_APP_SECRET

Defaults to OpenClaw's configured Feishu app.

Notes

  • Cards work in Direct Messages and group chats
  • Buttons open URLs (configure your callback server for full interactivity)
  • Maximum card size: 45KB

Made for ClawHub

安全使用建议
This skill appears to do what it says (send Feishu interactive cards) but it includes an embedded FEISHU_APP_ID and FEISHU_APP_SECRET in the source. Before installing, do the following: 1) Treat the embedded secret as a red flag — ask the publisher who owns that app/secret and whether it's intended for public use. 2) Prefer to set your own FEISHU_APP_ID and FEISHU_APP_SECRET in environment variables; do not rely on the embedded defaults. 3) If you cannot verify the embedded credentials' owner, remove or overwrite them in the code before use. 4) Audit button URLs and any callback server you configure to avoid linking to malicious endpoints. 5) Consider running the sender in a sandbox or test Feishu account first to observe behavior. If you need help verifying the origin of the credentials or modifying the code to remove defaults, get developer assistance.
功能分析
Type: OpenClaw Skill Name: feishu-cards Version: 1.0.0 The skill bundle appears benign. It provides functionality to construct and send interactive Feishu cards using the official Feishu Open API. The `SKILL.md` contains no prompt injection attempts. The Python scripts (`feishu_card_sender.py` and `feishu_cards.py`) primarily handle card JSON construction and legitimate API calls to `open.feishu.cn`. While `feishu_card_sender.py` includes hardcoded default `FEISHU_APP_ID` and `FEISHU_APP_SECRET`, these are explicitly stated as defaults for 'OpenClaw's configured Feishu app' and are not used for exfiltration or unauthorized access to other systems. There is no evidence of data exfiltration, malicious execution, persistence, or obfuscation with harmful intent.
能力评估
ℹ Purpose & Capability
Name, description, SKILL.md and the two Python modules all consistently implement Feishu card construction and sending. The required capabilities (HTTP requests to Feishu APIs) match the stated purpose. However the repository includes a hard-coded APP_ID and APP_SECRET used as defaults, which is surprising because the registry metadata lists no primary credential and the SKILL.md only describes optional env vars. That mismatch is noteworthy.
✓ Instruction Scope
SKILL.md and the code instruct the agent to build and POST Feishu interactive card JSON to Feishu endpoints. The runtime instructions do not tell the agent to read arbitrary user files or other unrelated environment variables, nor to transmit local data to unknown third-party endpoints. Button callbacks may open external URLs (the simple sender builds example.com links), and SKILL.md warns that a callback server is needed for full interactivity.
✓ Install Mechanism
There is no install spec that downloads external artifacts; this is effectively instruction + included source code. No external archives or installers are fetched during install, lowering installation risk.
⚠ Credentials
SKILL.md documents two optional environment variables (FEISHU_APP_ID and FEISHU_APP_SECRET). But feishu_card_sender.py contains hard-coded defaults (APP_ID and APP_SECRET values embedded in source). That creates a hidden credential default: if the user does not set env vars, the skill will use the embedded credentials to call Feishu on the user's behalf. The registry metadata did not declare a primary credential. Hard-coded secrets in published code are a security and provenance concern and may result in unexpected message sending under someone else's app.
✓ Persistence & Privilege
Skill is not always:true and does not request persistent system-wide configuration changes. It doesn't modify other skills or agent-wide settings and has no special OS privileges.
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-cards
  3. 安装完成后，直接呼叫该 Skill 的名称或使用 /feishu-cards 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-cards. - Send interactive, richly formatted cards to Feishu users or chats using the Feishu Open API. - Supports buttons, forms, dropdown menus, customizable colors, and notes in message cards. - Provides both CLI and Python module interfaces. - Flexible configuration via flags and environment variables. - Example usage and installation instructions included.
元数据
Slug feishu-cards
版本 1.0.0
许可证 —
累计安装 6
当前安装数 6
历史版本数 1
常见问题

Feishu Cards 是什么？

Send customizable interactive Feishu cards with titles, content, buttons, and color templates via Feishu Open API for users or group chats. 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 479 次。

如何安装 Feishu Cards？

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

Feishu Cards 是免费的吗？

是的，Feishu Cards 完全免费（开源免费），可自由下载、安装和使用。

Feishu Cards 支持哪些平台？

Feishu Cards 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 Cards？

由 SeeTheRainBow（@seetherianbow）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