← Back to list
✍️
baoyu-wechat-summary ✓ Security reviewed
Summarizes WeChat group chat highlights into a structured digest using the local wx-cli binary (h…
✍️ Writing By JimLiu Version v1.0.0 Updated 2026-09-03
6.3Overall rating

Installation

🤖 Install via AI

Copy the prompt below and send it to your AI assistant (e.g. Claude Code) — it will follow the instructions and install automatically.

Install the "baoyu-wechat-summary" skill by following the instructions at https://skill123.me/install/baoyu-wechat-summary.
⌨️ Command line install

Run in your terminal — downloads and installs to ~/.claude/skills/.

curl -fsSL https://skill123.me/install/baoyu-wechat-summary.sh | bash
📦 Download ZIP

Download the zip and extract it into your skills directory (e.g. ~/.claude/skills/), then restart your session.

⬇ Download v1.0.0 · 35 KB

About this skill

Overview

Summarizes WeChat group chat highlights into a structured digest using the local wx-cli binary (https://github.com/jackwener/wx-cli). Generates a normal digest by default; a roast (毒舌) version is opt-in. Maintains per-group history (history.json + history-digests.jsonl), per-user profiles, and per-group fact memory (memory.md) across runs, with privacy guardrails baked in. Use when the user asks to "总结群聊", "群聊精华", "群聊摘要", "summarize group chat", "group chat digest", mentions a WeChat group name with a time range, says "帮我看看 XX 群最近聊了什么", "XX 群有什么值得看的", or asks to "回溯画像" / "初始化画像" / "backfill profiles". Adds the roast version when the user says "毒舌版", "roast 版", "再来个毒舌的", or similar.

Source

  • Repo: https://github.com/JimLiu/baoyu-skills
  • Path: skills/baoyu-wechat-summary

Evaluation

AI-evaluated 2026-09-03: Remarkably detailed three-round digest workflow with mandatory attribution audits, incremental history, completion checklist, and prompt-injection defenses for group memory. Very niche: requires the wx-cli binary reading WeChat private data, and it mandates dangerouslyDisableSandbox for every command and builds persistent profiles of third-party group members, which privacy guardrail references only partly offset.

Score breakdown

Quality
9.0
Usability
4.0
Security
6.0
Popularity
9.0