$ show qiye45/wechatDownload
wechatDownload is a desktop GUI utility for bulk-downloading articles from WeChat official accounts (ĺžŽäżĄĺ Źäźĺˇ). The exported artifacts in example/ prove a production pipeline that converts articles into HTML, MHTML, Markdown, PDF, DOCX, and CSV, while also pulling embedded images, videos (nested MP4s), audio, cover images, and reader comments, and recording social metrics (like_num, read_num, share_num, comment_count) per article into CSV files. The tool supports single-article, full-account batch, and collection-based downloads, plus keyword filtering â all driven from a local GUI (README documents version 4.7+ and Windows/macOS use).
The LLM identified 2 files worth highlighting for reuse:
A self-contained skill definition that teaches an AI agent to operate the WeChat downloader through MCP tools. It documents the JSON-RPC 2.0 calling convention, the credential-acquisition workflow (get_public_account_id before batch_download_articles), supported output formats, and the local-to-remote MCP endpoint fallback strategy. This is a reusable pattern for wrapping any desktop/CLI tool as an agent-controllable MCP skill, and can be lifted into a different project with only endpoint names changed.
Machine-readable evaluation cases that pair expected agent tool invocations with sample inputs/outputs, enabling regression testing of the skill against an LLM. It demonstrates a lightweight, schema-based eval harness pattern for agent skills â useful to any team building MCP or function-calling integrations, and independent of the WeChat domain.