← 返回 Skills 市场
dearchenzj

feishu-emoji

作者 DearChenzj · GitHub ↗ · v1.0.0 · MIT-0
cross-platform ✓ 安全检测通过
221
总下载
0
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install feishu-emoji
功能描述
在飞书聊天中发送内联表情包图片,需将图片下载到指定媒体目录并通过 message 工具调用发送。
使用说明 (SKILL.md)

feishu-emoji - 飞书表情包发送技能

版本:1.0
创建时间:2026-03-16
依赖:无(仅需 curl 和 message 工具)
数据源:fabiaoqing.com(免费表情包网站)


🎯 技能目标

让 OpenClaw AI 能够在飞书聊天中发送内联表情包图片,增强对话表达力。


📋 核心原理

关键发现

  • 成功路径/home/admin/.openclaw/media/inbound/ → 飞书显示为内联图片
  • 失败路径/tmp/ → 飞书显示为附件链接(📎)

技术要点

  1. 图片必须保存到 OpenClaw 媒体目录才能被飞书识别为内联图片
  2. CDN 防盗链:fabiaoqing.com 的图片需要 Referer 头才能访问
  3. 使用 message 工具media 参数指向媒体目录中的文件

🛠️ 使用方式

方法一:直接发送(推荐)

当用户请求发送表情包时,执行以下步骤:

# 1. 下载表情包到媒体目录(带 Referer 头)
curl -sL -H "Referer: https://fabiaoqing.com/" "图片 URL" -o /home/admin/.openclaw/media/inbound/emoji_\x3C关键词>.jpg

# 2. 使用 message 工具发送
message(action="send", message="你的回复文字", media="/home/admin/.openclaw/media/inbound/emoji_\x3C关键词>.jpg")

方法二:调用 API(需要先启动服务)

如果已部署表情包 API 服务(emoji_server.py):

# 1. 获取表情包信息
curl -s "http://localhost:8000/emoji?keyword=大学生"

# 2. 下载 proxy_url 到媒体目录
curl -sL "http://localhost:8000/image?url=\x3Cencoded_url>" -o /home/admin/.openclaw/media/inbound/emoji_xxx.jpg

# 3. 发送
message(action="send", message="表情包来了!", media="/home/admin/.openclaw/media/inbound/emoji_xxx.jpg")

📦 表情包来源

推荐网站

  • fabiaoqing.com - 免费表情包,无需登录
  • 搜索 URL 格式:https://fabiaoqing.com/search/bqb/keyword/\x3C关键词>/type/bq/page/1.html

热门关键词

  • 日常:好的、收到、谢谢、OK、没问题
  • 情绪:开心、难过、生气、惊讶、无语
  • 场景:打工人、大学生、摸鱼、加班、开会
  • 动物:猫猫、狗狗、熊猫、兔子

图片 URL 特征

  • 通常来自第三方 CDN(如 img.soutula.com
  • 需要 Referer: https://fabiaoqing.com/ 才能访问
  • 格式多为 .jpg,大小 10-50KB

🔧 完整示例

示例 1:发送"收到"表情包

# 下载
curl -sL -H "Referer: https://fabiaoqing.com/" \
  "https://img.soutula.com/bmiddle/006APoFYly1glojj7wfc5j306o06odg1.jpg" \
  -o /home/admin/.openclaw/media/inbound/emoji_shoudao.jpg

# 发送
message(action="send", \
  message="收到!马上处理~", \
  media="/home/admin/.openclaw/media/inbound/emoji_shoudao.jpg")

示例 2:发送"猫猫"表情包

# 先获取表情包信息(可选)
curl -s "https://fabiaoqing.com/search/bqb/keyword/猫猫/type/bq/page/1.html" | \
  grep -o 'data-original="[^"]*"' | head -1

# 下载并发送
curl -sL -H "Referer: https://fabiaoqing.com/" \
  "https://img.soutula.com/bmiddle/xxx.jpg" \
  -o /home/admin/.openclaw/media/inbound/emoji_maomao.jpg

message(action="send", \
  message="猫猫表情包来了!🐱", \
  media="/home/admin/.openclaw/media/inbound/emoji_maomao.jpg")

⚠️ 注意事项

版权

  • 表情包均来自互联网,版权归原作者所有
  • 请勿商用
  • 个人聊天使用通常没问题

技术限制

  • 图片链接可能失效(第三方 CDN)
  • 建议控制调用频率(避免被网站封禁)
  • 飞书图片发送仅限媒体目录内的文件

文件管理

  • 建议命名规范:emoji_\x3C关键词>.jpg
  • 定期清理旧文件(避免占用过多空间)
  • 单个文件通常 10-50KB

🧪 测试清单

安装后测试以下关键词:

  • 好的
  • 收到
  • 谢谢
  • 猫猫
  • 打工人

确保图片能正常显示为内联图片(不是附件链接)。


📁 文件结构

skills/feishu-emoji/
├── SKILL.md          # 本说明文件
└── (可选)
    ├── emoji_sender.py    # Python 发送脚本
    └── emoji_keywords.json # 常用关键词映射表

🚀 进阶功能(可选)

1. 关键词映射表

创建 emoji_keywords.json 存储常用表情包 URL:

{
  "收到": "https://img.soutula.com/bmiddle/xxx.jpg",
  "好的": "https://img.soutula.com/bmiddle/yyy.jpg",
  "猫猫": "https://img.soutula.com/bmiddle/zzz.jpg"
}

2. 随机表情包

支持发送随机表情包:

# 从关键词列表随机选一个
keywords=("好的" "收到" "谢谢" "OK")
random_keyword=${keywords[$RANDOM % ${#keywords[@]}]}

3. 表情包 API 服务

部署完整 API 服务参考:

  • /home/admin/.openclaw/workspace/emoji_server.py
  • /home/admin/.openclaw/workspace/README_EMOJI_API.md

💡 使用场景

  • ✅ 日常聊天增强表达
  • ✅ 工作群活跃气氛
  • ✅ 回复确认(收到/好的)
  • ✅ 情绪表达(开心/无语/震惊)
  • ❌ 正式公文/严肃场合
  • ❌ 商业用途

Happy Emoji Sending! 🎉

安全使用建议
This skill appears to do exactly what it says: search for emoji images on fabiaoqing.com (or use built-in CDN mappings), download them into the OpenClaw media directory, and call the platform 'message' tool to send inline images. Before installing, ensure: (1) the runtime has Python and the required packages (requests, beautifulsoup4) or adjust the SKILL.md to install them; (2) you are comfortable with the skill writing files to /home/admin/.openclaw/media/inbound (or set OPENCLAW_MEDIA_DIR to a different directory); (3) allowing outbound HTTP(S) requests is acceptable — the skill will fetch external image URLs and could, in edge cases, reach internal endpoints if the scraped page contains such links (consider URL validation/whitelisting); (4) you’re aware of copyright and usage restrictions for downloaded images. If you need tighter security, run the skill in a sandboxed environment, add URL validation and size limits to the downloader, and ensure the 'message' tool is the official OpenClaw integration rather than an unexpected binary.
功能分析
Type: OpenClaw Skill Name: feishu-emoji Version: 1.0.0 The skill is designed to search for and send emojis in Feishu (Lark) by downloading images from fabiaoqing.com. It uses standard tools like `curl` and a Python script (`emoji_sender.py`) to retrieve images and save them to a specific local directory (`/home/admin/.openclaw/media/inbound/`) required for inline display. The logic is transparent, aligns with the stated purpose, and contains no evidence of data exfiltration, persistence, or malicious prompt injection.
能力评估
Purpose & Capability
Name/description (send inline emoji to Feishu) matches what the files and SKILL.md do: discover image URLs, download them to the OpenClaw media directory, and invoke the 'message' tool to send media. The use of fabiaoqing.com and typical image CDNs is coherent with the stated source.
Instruction Scope
Runtime instructions and the python script focus on searching fabiaoqing.com, downloading image URLs with a Referer header, saving into /home/admin/.openclaw/media/inbound, then calling the message tool. This stays within the stated scope. Minor risk: the skill downloads arbitrary image URLs discovered on web pages — this can cause the agent environment to make outbound requests to third-party or internal hosts (SSRF/internal network access) if the scraped data contains unexpected URLs; this is an expected tradeoff for a downloader but worth noting.
Install Mechanism
No install specification (instruction-only) — the skill includes a small Python script and example curl commands but does not download or execute external installers. This is low-risk from an install perspective.
Credentials
The skill requests no secrets or privileged env vars. It writes into a media directory (/home/admin/.openclaw/media/inbound) which is consistent with its purpose. One minor inconsistency: SKILL.md claims 'dependencies: none (only need curl and message tool)', but the included script requires Python packages (requests, beautifulsoup4) listed in package.json — the environment must have those packages available for the script to work.
Persistence & Privilege
The skill does not request always:true and does not modify other skills or system-wide configs. It only writes files to its media directory as expected for its function.
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-emoji
  3. 安装完成后,直接呼叫该 Skill 的名称或使用 /feishu-emoji 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
feishu-emoji 1.0.0 - Initial release: enables sending inline emoji images in Feishu chats using OpenClaw AI. - Downloads emoji images from fabiaoqing.com with proper Referer handling. - Ensures images are saved to the OpenClaw media directory for proper inline display. - Provides command-line examples and optional API support for automated emoji sending. - Includes tips for copyright, file management, and extensibility with keyword mapping and random selection.
元数据
Slug feishu-emoji
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-emoji 是什么?

在飞书聊天中发送内联表情包图片,需将图片下载到指定媒体目录并通过 message 工具调用发送。 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 221 次。

如何安装 feishu-emoji?

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

feishu-emoji 是免费的吗?

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

feishu-emoji 支持哪些平台?

feishu-emoji 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-emoji?

由 DearChenzj(@dearchenzj)开发并维护,当前版本 v1.0.0。

💬 留言讨论