Name: dingtalk-connection
Author: xiaomingx

Imported from xiaomingx/moltbot-connector-feishu-dingtalk (skills/dingtalk-connection/SKILL.md) via skills.sh. Install upstream with npx skills add xiaomingx/moltbot-connector-feishu-dingtalk --skill dingtalk-connection. Copyright stays with the author.

DingTalk Bridge

Bridge DingTalk bot messages to Clawdbot Gateway over a local WebSocket connection.

Architecture

DingTalk user -> DingTalk cloud -> webhook (bridge.py) -> Clawdbot Gateway -> AI agent

Setup

1. Create DingTalk bot

Create a bot that can send outgoing webhooks and set the callback URL to your public endpoint.

2. Run bridge

cd <skill-dir>/dingtalk-connection
uv sync
DINGTALK_SIGNING_SECRET=your_secret uv run python bridge.py

3. Auto-start (macOS)

uv run python setup_service.py
launchctl load ~/Library/LaunchAgents/com.clawdbot.dingtalk-bridge.plist

Environment variables

Variable	Required	Default
`DINGTALK_PORT`	—	`3210`
`DINGTALK_PATH`	—	`/dingtalk`
`DINGTALK_SIGNING_SECRET`	—	—
`DINGTALK_BOT_ID`	—	—
`DINGTALK_BOT_NAME`	—	—
`CLAWDBOT_CONFIG_PATH`	—	`~/.clawdbot/clawdbot.json`
`CLAWDBOT_AGENT_ID`	—	`main`
`DINGTALK_THINKING_THRESHOLD_MS`	—	`2500`

Install dingtalk-connection and it becomes one more candidate the router can pick - when it fits.

A listing is a routing target with a manifest: what it does, which domains it covers, what it costs and who publishes it. Once installed it sits beside your own models and tools, is scored like any other candidate for each request, and shows up in the trace when it wins. Ratings come from workspaces that installed it, one per account.

{ "ocm": "1", "id": "xiaomingx-moltbot-connector-feishu-dingtalk-dingtalk-connection", "kind": "skill", "name": "dingtalk-connection", "description": "Bridge DingTalk outgoing webhook messages to Clawdbot Gateway and send replies back to DingTalk sessions. Use when setting up DingTalk as a messaging channel, troubleshooting webhook delivery, or running the local bridge service.", "publisher": "xiaomingx", "version": "1.0.0", "capabilities": { "domains": [ "customer_support" ], "tags": [ "skill-md", "skills-sh" ], "languages": [ "en" ] }, "quality_prior": 0.6, "examples": [ "Bridge DingTalk outgoing webhook messages to Clawdbot Gateway and send replies back to DingTalk sessions. Use when setting up DingTalk as a messaging channel, troubleshooting webhook delivery, or running the local bridge service." ], "primary": false, "metadata": { "source": { "provider": "skills.sh", "repository": "https://github.com/xiaomingx/moltbot-connector-feishu-dingtalk", "path": "skills/dingtalk-connection/SKILL.md", "ref": "HEAD", "url": "https://www.skills.sh/xiaomingx/moltbot-connector-feishu-dingtalk/dingtalk-connection", "key": "xiaomingx/moltbot-connector-feishu-dingtalk/skills/dingtalk-connection/SKILL.md" } }, "instructions": "# DingTalk Bridge\n\nBridge DingTalk bot messages to Clawdbot Gateway over a local WebSocket connection.\n\n## Architecture\n\n```\nDingTalk user -> DingTalk cloud -> webhook (bridge.py) -> Clawdbot Gateway -> AI agent\n```\n\n## Setup\n\n### 1. Create DingTalk bot\n\nCreate a bot that can send outgoing webhooks and set the callback URL to your public endpoint.\n\n### 2. Run bridge\n\n```bash\ncd <skill-dir>/dingtalk-connection\nuv sync\nDINGTALK_SIGNING_SECRET=your_secret uv run python bridge.py\n```\n\n### 3. Auto-start (macOS)\n\n```bash\nuv run python setup_service.py\nlaunchctl load ~/Library/LaunchAgents/com.clawdb", "cost": { "context_tokens": 255 } }

dingtalk-connection

About

DingTalk Bridge

Architecture

Setup

1. Create DingTalk bot

2. Run bridge

3. Auto-start (macOS)

Environment variables

Install dingtalk-connection and it becomes one more candidate the router can pick - when it fits.

Use it

Manifest

Reviews