Skills for Real Engineers. Straight from my .agents directory.
baoyu-wechat-summary
Agent skill fromJimLiu/baoyu-skills
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.
How to install baoyu-wechat-summary
npx skills add JimLiu/baoyu-skills# or add only this skill to Claude Code: copy the folder
skills/baoyu-wechat-summary/
# into
~/.claude/skills/baoyu-wechat-summary/ (all projects)
.claude/skills/baoyu-wechat-summary/ (one project)
1# WeChat Group Summary23群聊精华提取专家。把零散的微信群聊记录提炼成结构化、可读性强的简报,并维护跨次运行的群聊历史与群友画像。底层依赖外部 [wx-cli](https://github.com/jackwener/wx-cli) 二进制(`wx` 命令),不打包脚本。45> **⚠️ Sandbox restriction**6>7> wx-cli reads from `~/.wx-cli/` (config, cache, daemon socket) and from WeChat's data directory (`~/Library/Containers/com.tencent.xinWeChat/` on macOS). Both paths are outside Claude Code's default sandbox. Every `wx` command in this skill needs to run with `dangerouslyDisableSandbox: true` from the start — don't waste a sandbox attempt first. The user can use `/sandbox` to view/edit restrictions.89## References(按需加载)1011本文件只保留工作流骨架;细节拆在 `references/` 下,**执行到对应步骤时再读,不要一开始全部读入**:1213| 参考文件 | 内容 | 何时读 |14|---------|------|-------|15| [references/setup.md](references/setup.md) | 环境检查(wx-cli 安装/权限/初始化)、wx-cli 命令速查、排障手册 | 新环境首次运行,或任何 `wx` 命令失败时 |16| [references/output-formats.md](references/output-formats.md) | 两版摘要的 Section 顺序、格式与内容规范、输出骨架、自检清单 | Round 2 动笔前 |17| [references/profiles.md](references/profiles.md) | 画像文件格式、更新规则、隐私红线、回溯流程 | Step 3.7 / 8.5 / Step 9 |18| [references/group-memory.md](references/group-memory.md) | 群级事实记忆的写入门槛、防注入、格式 | Step 8.6 |19| [references/preferences.md](references/preferences.md) | EXTEND.md 支持的键、首次配置流程 | 解析/写入 EXTEND.md,或未找到 EXTEND.md 时 |20| [references/bot-requests.md](references/bot-requests.md) | @bot 请求的提取、误触过滤、答复来源约束 | Step 3.9 有命中时 |2122## User Input Tools2324When this skill prompts the user, follow this tool-selection rule (priority order):25…
Excerpt shown under the repository's MIT license.
More skills in baoyu-skills
Similar skill repositories
An agentic skills framework & software development methodology that works.
A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls.
Public repository for Agent Skills
Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote.
Persistent Context Across Sessions for Every Agent – Captures everything your agent does during sessions, compresses it with AI, and injects relevant context back into future sessions. Works with Claude Code, OpenClaw, Codex, Gemini, Hermes, Copilot, OpenCode + More
