CAT
/Skills
SkillsMCPMarketplacesDigestToolsAdvertise

This week in Claude

Every Monday: Claude Code, Agent SDK, MCP, and the Anthropic platform moves worth your time.

Skills by Category
Frontend DevelopmentBackend & APIsTesting & QASecurityDevOps & CI/CDGit & Pull RequestsDocumentationCode Review & QualityAI & Agent BuildingSkill Development
MCP Servers by Category
Sales & MarketingWeb & Browser AutomationDatabasesAI & LLM ToolsCloud & InfrastructureCommunication & MessagingDeveloper ToolsDesign & CreativeDocuments & KnowledgeSearch & Web Crawling
Marketplaces by Category
AI Agents & OrchestrationLLM IntegrationDevelopment ToolsFrontend & UIBackend & APIsDatabasesTesting & Code QualityDevOps & CloudSecurity & ComplianceGit & Version Control

Cross AI Tools

Discover Claude Code plugins, extensions, and tools. Automatically updated directory of Anthropic Claude AI marketplaces with development tools, productivity plugins, and integrations.

Resources

  • Browse Skills
  • Browse MCP Servers
  • Browse Marketplaces
  • Plugins Reference

Community

  • About
  • Tools
  • Feedback
  • Privacy Policy
  • Advertise

Built for the Claude Code community with Claude Code by @mertduzgun

Independent project, not affiliated with Anthropic

Wechat Binding

starchild-ai-agent/official-skills
794 installs13 stars
Summary

Handles the full WeChat account binding flow so Claude can push messages to users via send_to_wechat. You generate a QR code, the user scans it in WeChat, you poll for confirmation, then call connect or reconnect depending on whether it's their first time. The skill documentation is careful about channel awareness (web shows the QR inline, Telegram needs send_to_telegram with the image path) and emphasizes not auto-polling the status endpoint to avoid spamming the API. It distinguishes between connect for new bindings and reconnect for re-establishing dropped sessions, with status checks to figure out which one you need. Straightforward if you're building multi-channel delivery and need WeChat as an output.

Install to Claude Code

npx -y skills add starchild-ai-agent/official-skills --skill wechat-binding --agent claude-code

Installs into .claude/skills of the current project.

CodeRabbit
CodeRabbit
AI writes the code. CodeRabbit catches the slop.
Try For Free →
Keep your Mac awake
Keep your Mac awake
Keep your Mac awake while Claude Code and 40+ AI agents run. Sleeps when they're idle.
One time payment $9 →
Context.devContext.dev
Context.dev
Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →
Make your agent a DeFi expert
Make your agent a DeFi expert
Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →
Make money from your Skills
Make money from your Skills
On Capafy, your Skill runs online 24/7 as an agent product, and you get paid every time someone uses it.
Start earning →
AppSignal
AppSignal
Monitor with ease. Code with confidence.
Start Free Trial →
CodeRabbit
CodeRabbit
AI writes the code. CodeRabbit catches the slop.
Try For Free →
Keep your Mac awake
Keep your Mac awake
Keep your Mac awake while Claude Code and 40+ AI agents run. Sleeps when they're idle.
One time payment $9 →
Context.devContext.dev
Context.dev
Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →
Make your agent a DeFi expert
Make your agent a DeFi expert
Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →
Make money from your Skills
Make money from your Skills
On Capafy, your Skill runs online 24/7 as an agent product, and you get paid every time someone uses it.
Start earning →
AppSignal
AppSignal
Monitor with ease. Code with confidence.
Start Free Trial →
Files
  • logo.png
SKILL.mdView on GitHub

📱 WeChat Binding

Connect / reconnect / disconnect the user's WeChat account so the agent can push messages via send_to_wechat.

The wechat tool stays built-in. This SKILL.md is the reference doc.

See also

  • config/context/references/messaging-channels.md — how to actually send messages once bound
  • skills/tg-bot-binding/SKILL.md — analogous Telegram flow

Typical binding flow

qrcode → user scans → qrcode_status(qrcode=...) → connect(bot_token=...)
  1. Generate QR: wechat(action="qrcode") — saves an image to workspace, returns qrcode (id) + file_path.
  2. Show the QR to the user. On web channel: include the file_path so the frontend renders the image. On TG/WeChat channel: send the image via send_to_telegram with the file_path.
  3. Wait for the user to scan + confirm in WeChat. Don't auto-poll — let them say "scanned" / "done" first.
  4. Poll for completion: wechat(action="qrcode_status", qrcode=<id from step 1>). Returns bot_token once scan + confirm completes.
  5. Connect: wechat(action="connect", bot_token=<from step 4>). Optional: ilink_bot_id, ilink_user_id if the user has multiple WeChat accounts.
  6. Confirm to user: "WeChat connected. You can now push messages with send_to_wechat."

Actions

actionrequiredpurpose
status—Current WeChat connection state. Use before reconnect, to verify binding.
qrcode—Generate QR code image (saved to workspace). Returns qrcode id + file_path.
qrcode_statusqrcodePoll whether user has scanned + confirmed. Returns bot_token on success.
connectbot_tokenComplete a NEW WeChat connection (after first-ever QR scan). Optional: ilink_bot_id, ilink_user_id.
disconnect—Terminate current WeChat session (unlink).
reconnectbot_tokenRe-establish a previously-bound WeChat (token from a fresh QR scan).

connect vs. reconnect

  • connect — first-time binding. The user has NEVER bound this WeChat before.
  • reconnect — the user was previously connected, the connection dropped (e.g. ilink session expired), and they just scanned a fresh QR.

When in doubt, call status first:

  • connected: false + no prior history → connect
  • connected: false + prior history exists → reconnect

Channel-aware QR display

User channelHow to show the QR
WebInclude file_path in your reply — frontend renders it inline
Telegramsend_to_telegram(file_path=<qr_path>, message_type="photo")
WeChat(You can't — they're trying to bind WeChat in the first place. Tell them to open the web app.)

Critical rules

  • Don't auto-poll qrcode_status after qrcode. Wait for user confirmation that they scanned + confirmed in WeChat. Auto-polling spams the upstream API.
  • Each qrcode call generates a fresh image. Don't re-use an old qrcode id with a new image — the upstream session is tied to the id.
  • Never paste bot_token in chat. It's a credential. Once you have it from qrcode_status, immediately pass it to connect / reconnect and don't echo it back to the user.
  • disconnect is destructive — confirm with the user before calling it.
Featured
CodeRabbit
CodeRabbit
AI writes the code. CodeRabbit catches the slop.
Try For Free →
Keep your Mac awake
Keep your Mac awake
Keep your Mac awake while Claude Code and 40+ AI agents run. Sleeps when they're idle.
One time payment $9 →
Context.devContext.dev
Context.dev
Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →
Make your agent a DeFi expert
Make your agent a DeFi expert
Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →
Make money from your Skills
Make money from your Skills
On Capafy, your Skill runs online 24/7 as an agent product, and you get paid every time someone uses it.
Start earning →
AppSignal
AppSignal
Monitor with ease. Code with confidence.
Start Free Trial →
Categories
AI & Agent Building
First SeenJun 3, 2026
View on GitHub

Recommended

More AI & Agent Building →
agent-memory-mcp

sickn33/antigravity-awesome-skills

agent memory mcp
954
39.4k
agent-memory-mcp

davila7/claude-code-templates

agent memory mcp
521
27.7k
llm-application-dev-langchain-agent

sickn33/antigravity-awesome-skills

llm application dev langchain agent
306
39.4k
llm-application-dev

moizibnyousaf/ai-agent-skills

Building applications with Large Language Models - prompt engineering, RAG patterns, and LLM integration. Use for AI-powered features, chatbots, or LLM-based automation.
1.1k
ai-prompt-engineering-safety-review

github/awesome-copilot

Comprehensive safety analysis and improvement framework for AI prompts with detailed assessment methodologies.
9.4k
34.3k
emblem-ai-prompt-examples

emblemcompany/agent-skills

emblem ai prompt examples
8.7k
10