Copilot CLI Feishu WeChat Bridge
Paste the following prompt into your AI chat to install this skill:
Follow https://skillhub.cn/install/skillhub.md to install @user_6afd2e6f/github-coplit-im-bridge.
About this skill
What It Solves
When you are away from your machine, GitHub Copilot CLI is still mostly tied to a local terminal. This skill connects Copilot CLI to Feishu, DingTalk, or WeChat so that a phone message can start a CLI session and receive text, files, or images back in chat. It is useful for continuing a task from a mobile device without opening a laptop.
How It Works
- Two bridge tools:
cc-connecttargets Feishu/Lark, Slack, DingTalk, and Telegram;wechat-acptargets WeChat and is a community, hook-based bridge. - Official messaging channel: the Feishu path uses an enterprise app,
im:messagepermissions, WebSocket long connections, and event subscriptions to receive messages and return results. - Copilot authentication: it supports interactive login, environment variables, GitHub CLI tokens, secret managers, or wrapper scripts. Use the real
copilotbinary rather than the VS Code shim to avoid authentication failures. - Context continuity: because each IM message may start an isolated session, the skill can use a history-sync pattern to persist chat history in cc-connect session JSON and rebuild
.github/copilot-instructions.mdonmessage.sent, seeding the next session. - File delivery:
cc-connect sendcan return files or images to chat, and you can instruct Copilot to auto-send them from.github/copilot-instructions.md. - Long-running service: it can be persisted as a macOS LaunchAgent, Windows Scheduled Task, or Linux systemd unit.
Boundaries
It does not share conversation memory between VS Code Copilot and IM Copilot, but they can share the same project filesystem. For remote runs, --yolo is recommended to reduce confirmation blocking. Use a separate work_dir or filter_external_sessions to avoid session conflicts. The WeChat path relies on hooks, has weaker file and image support than Feishu, and may need extra attention to Chinese path encoding, permissions, and process persistence.
Use Cases
- Send a task from Feishu while away and let Copilot CLI modify code and return a patch file.
- Ask about an error log in WeChat and use wechat-acp to call Copilot for analysis and a reply.
- Ask Copilot in Feishu to generate a script or image and return the file via cc-connect send.
- Register the bridge as a LaunchAgent or systemd unit to keep remote Copilot sessions available.
Best For
- GitHub Copilot CLI users who want to continue code tasks from a phone.
- Platform engineers maintaining Feishu or DingTalk bots who need to integrate an external CLI.
- On-call systems engineers who need to inspect errors and ask for model-assisted triage remotely.
- Independent developers who prefer mobile-first workflows for personal Copilot CLI sessions.
Related Skills
Provides Claw with character-library selection, switching, saving, and global SOUL.md style sync for role-based conversation.
An AIONE Agentic AI Infrastructure SDK wrapper for building production AI agents with memory, skills, workflows, and hooks.
A Python/TypeScript SDK wrapper for the DeepSeek-Reasonix native AI coding agent, with prefix-cache support.
A browser automation tool for analysts, operators, and developers that locates elements, fills forms, extracts structured content, and supports no-code scheduling and export.