christo

Wecom

AI Agentv1.0.3
By christoUpdated 2026-05-114 versions · latest released 2026-04-07wecom@clawhub_qidu/wecom
Workflow OrchestrationTool Use#微信

According to AlphaMoat, as of 2026-10, Wecom has 12,882 downloads and 10 stars — ranked by downloads #2,160 among 10,914 AI skills in this ranking, and #292 of 1,632 in AI Agent.

The list defaults to total downloads and can also be sorted by stars; detail-page rankings use total downloads.

Downloads
12.9K
Stars
10
Overall download rank
#2,160
Top 20% overall · Top 18% in AI Agent
PlatformDownloadsStarsComments
ClawHub ↗6.3K94
SkillHub ↗12.9K10—

Platforms count differently and update at different times.

What this skill does

It sends text and markdown messages to a WeCom group using WECOM_WEBHOOK_URL for the group bot address, and works with Claude Code, Claude Desktop and other MCP clients. Version 1 does not support tables, code blocks or H1 to H3 headers; the webhook URL grants posting rights to that group, so keep it out of repositories and logs.

Profile published 2026-10-27

What you can do with it

  • Push task progress into a project group
  • Post build or monitoring results as markdown

When to use it

  • Agent results should reach a WeCom group
  • A group bot URL already exists and messages should go straight out

Example prompts

Generated from the skill’s documentation as examples; not results of actual runs.

Post today's deployment result to the project group
Push this markdown summary to our WeCom group

Monthly Trend

Downloads12.9K
4.5K9.0K13.5K2026-03 · Downloads 5.1K2026-05 · Downloads 6.7K2026-06 · Downloads 7.5K2026-07 · Downloads 8.0K2026-08 · Downloads 8.5K2026-09 · Downloads 9.4K2026-10 · Downloads 12.9K26-0326-0926-10
Stars10
910102026-03 · Stars 92026-05 · Stars 102026-06 · Stars 102026-07 · Stars 102026-08 · Stars 102026-09 · Stars 102026-10 · Stars 1026-0326-0926-10

The counting method changed in 2026-09: skills with the same name are now counted separately by author, and the full catalog is covered. Dashed lines show months before the change; they are not compared with later months, and no growth is computed across the change.

MonthDownloadsMoMStars
2026-1012.9K—10
2026-099.4K—10
2026-088.5K+5.6%10
2026-078.0K+7.0%10
2026-067.5K+11.0%10
2026-056.7K—10
2026-035.1K—9

SKILL.md (original)

The author’s original file, shown as plain text without edits or review by AlphaMoat. Links are not clickable; check commands before running them. Fetched 2026-10-23.

4.1 KB · ClawHub v1.0.3
---`
name: wecom
description: "Send messages to WeCom (企业微信) via webhooks using MCP protocol. Works with Claude Code, Claude Desktop, and other MCP clients."
---

# WeCom Skill

Send text and markdown messages to `WeCom` (`企业微信`) via incoming webhooks (ENV: `WECOM_WEBHOOK_URL`).

`WeCom` is the enterprise version (using in office) of the famous all-in-on IM `WeChat` envied by Elon Musk.
Show all (164 lines)

## Setup

```bash
# Navigate to skill directory
cd skills/wecom

# Install dependencies
npm install

# Build TypeScript
npm run build

# Set webhook URL
export WECOM_WEBHOOK_URL="https://qyapi.weixin.qq.com/cgi-bin/webhook/send?key=YOUR_KEY"
```

## Usage with Claude Code

Add to your `~/.config/claude_code/mcp.json`:

```json
{
  "mcpServers": {
    "wecom": {
      "command": "node",
      "args": ["/path/to/clawdbot/skills/wecom/dist/index.js"],
      "env": {
        "WECOM_WEBHOOK_URL": "https://qyapi.weixin.qq.com/cgi-bin/webhook/send?key=YOUR_KEY"
      }
    }
  }
}
```

Then restart Claude Code. You'll have three new tools:

# Tools

## `send_wecom_message`

Send a text message to WeCom.

```bash
# Simple message
await send_wecom_message({ content: "Hello from OpenClaw!" });

# With mentions
await send_wecom_message({
  content: "Meeting starting now",
  mentioned_list: ["zhangsan", "lisi"]
});
```

## `send_wecom_markdown_v2`

Send a markdown_v2 message to WeCom. **Recommended** — supports tables, code blocks, nested blockquotes, H1-H3 headers, and all standard markdown.

```bash
await send_wecom_markdown_v2({
  content: `# Annual Report

## Revenue by Quarter
| Quarter | Revenue | Growth |
| :---- | -----: | ----: |
| Q1 | ¥1.2M | +15% |
| Q2 | ¥1.8M | +50% |
| Q3 | ¥2.1M | +17% |

## Notes
> Key insight: mobile revenue grew 80%
>
>> Detail: driven by short video ads
>
>> Another point: new user acquisition cost down 30%

## Code Example
\`\`\`python
def hello():
    print("Hello WeCom!")
\`\`\`

---

More info [here](https://work.weixin.qq.com/api/doc)`
});
```

# WeCom Markdown v2 Features

markdown_v2 supports everything the original markdown supports, **plus**:

| Feature | Syntax | Example |
|---------|--------|----------|
| Tables | `\| col \| col \|` with `\| :--- \| -----: \|` | Supported with alignment |
| Nested blockquotes | `>>>` or `>>` | Up to 3 levels |
| H1/H2/H3 | `#` `##` `###` | Three heading levels |
| Code blocks | `\`code\`` and `\`\`\`lang` | Inline and multi-line |
| Horizontal rule | `---` | Dividers |
| Links | `[text](url)` | Standard markdown |
| Images | `![alt](url)` | Direct URL |

# WeCom Markdown (v1) Tags

The original `send_wecom_markdown` supports these limited tags:

| Feature | Syntax |
|---------|--------|
| Bold | `**text**` or `<strong>text</strong>` |
| Italic | `*text*` or `<i>text</i>` |
| Strikethrough | `~~text~~` or `<s>text</s>` |
| Mention | `<@userid>` |
| Link | `<a href="url">text</a>` |
| Image | `<img src="url" />` |
| Font size | `<font size="5">text</font>` |
| Color | `<font color="#FF0000">text</font>` |

⚠️ **v1 does NOT support tables, code blocks, or H1-H3 headers.** Use `send_wecom_markdown_v2` when you need those.

# Environment Variables

| Variable | Required | Default | Description |
|----------|----------|---------|-------------|
| `WECOM_WEBHOOK_URL` | Yes | - | WeCom webhook URL |
| `WECOM_TIMEOUT_MS` | No | 10000 | Request timeout (ms) |

# How To

Get `WECOM_WEBHOOK_URL` following steps here, and envolve it as a bot into a group chat:

(Tip: You should get the `WECOM_WEBHOOK_URL` entirely as a URL, NOT just a KEY )

### STEP 1

![STEP 1](https://cdn.jsdelivr.net/gh/qidu/qidu.github.io@main/public/images/wecom/step1_wecom.png)

### STEP 2

![STEP 2](https://cdn.jsdelivr.net/gh/qidu/qidu.github.io@main/public/images/wecom/step2_wecom.png)

### STEP 3

![STEP 3](https://cdn.jsdelivr.net/gh/qidu/qidu.github.io@main/public/images/wecom/step3_wecom.png)

### STEP 4

![STEP 4](https://cdn.jsdelivr.net/gh/qidu/qidu.github.io@main/public/images/wecom/step4_wecom.png)

# Reference

[Message Receiving and Sending in a Group Chat](https://developer.work.weixin.qq.com/document/path/99110)

[Download WeCom Apps](https://work.weixin.qq.com/#indexDownload)

Popular in AI Agent

self-improving agentAI Agent

Records learnings, errors and corrections as Markdown files for later reuse and promotion into workspace memory.

↓ 1.6M★ 4.5Kpskoett
技能发现·Find SkillsAI Agent

Finds skills in local and remote catalogs from a plain-language request and recommends what to install.

↓ 1.6M★ 1.8K桂皮
Agent BrowserAI Agent

A browser-automation command line skill for AI agents.

↓ 1.2M★ 1.0KNicolas Kleiber
Self-Improving + Proactive AgentAI Agent

Turns corrections and self-review into tiered memory and promotes or archives it by use.

↓ 696.4K★ 1.6KIván
Proactive AgentAI Agent

A workspace setup guide for planning proactive follow-up, working memory and review routines for an AI agent.

↓ 579.3K★ 916halthelobster
Skill CreatorAI Agent

A guide to creating and updating effective Claude skills.

↓ 477.3K★ 485chindden
Skill VetterAI Agent

Reviews a third-party skill's source, permissions, and danger patterns against a checklist before it is installed.

↓ 445.2K★ 1.3Kspclaudehome
唐朝诗仙李白 · Ai Agent SkillAI Agent

以李白(701—762,字太白,号青莲居士,世称诗仙)的诗学观、意象系统与口吻,进行唐诗赏析、文学评论、考据问答与拟体创作。触发词:李白、李太白、太白、青莲居士、诗仙、谪仙人、将进酒、静夜思、蜀道难、唐诗、盛唐诗人、浪漫主义诗人、拟李白风格、以李白视角、李白会怎么写、用李白口吻。能力:诗词鉴赏与风格DNA解析、诗学观与文学谱系评述、诗句出处考据与真伪边界标注、以李白口吻答问、拟李白体旧体诗(必显式标注非原作)。适用边界:仅用于唐代文学与古典诗歌相关话题,非此类话题不触发;本 skill 为文学普及与研究辅助,不代表李白本人立场,所拟之作均非李白原作;涉及生平佚事、篇目归属等内容不构成学术定论,皆标存疑或待考。

↓ 435.8K★ 4user_ff4d9420

Data as of 2026-10. Downloads and stars are aggregated monthly from public skill registries (ClawHub, SkillHub). See data methodology.