发现优质的 AI Agent 技能

- Normalize inbound updates to a single envelope: - `update_id`, `chat_id`, `user_id`, `message_id`, `text`, `callback_data`, `type` - This makes routing logic consistent across message types.

POST `/sendMessage` ```json { "chat_id": 123456789, "text": "Hello",

- Slash commands (chat input) - User context commands - Message context commands

Lattice is a file-based operating system for AI agent teams. It replaces volatile chat windows with persistent files, enabling agents to work stably through long, iterative development cycles via an 8-phase execution pipeline.

Send messages to WeChat contacts by automating the macOS WeChat desktop app.

Store, search, and chat with your personal knowledge base using SuperMemory's API.

AI agent CLI for interacting with OnChat on Base L2

Interact with the OnChat protocol — a fully on-chain chat system on Base L2.

Practical constraints and API details for publishing to WeChat Official Accounts. Sourced from production debugging sessions.

Use this checklist before pushing `research-to-wechat` as a public-facing skill update.

Use this skill as a research-first control plane. Do not duplicate downstream skill wording.

All notable changes to `research-to-wechat` will be documented in this file.