将群聊记录转化为规避微信折叠、无列表符号、Emoji 标题的精简中文总结。当用户已导出群聊记录(见 wechat skill)并想生成可直接发回微信群的摘要时使用。
Scanned 9/5/2026
Install to Claude Code
npx -y skills add chengmarc/wechat-to-ai --skill wechat-summary --agent claude-codeInstalls into .claude/skills of the current project.
Are you the author of Wechat Summary?
Add the live security badge to your README — it updates automatically with every re-scan.
[](https://www.skillsdirectory.com/skills/chengmarc-wechat-summary)More formats (shields.io, HTML) on the badges page.
---
name: wechat-summary
description: 将群聊记录转化为规避微信折叠、无列表符号、Emoji 标题的精简中文总结。当用户已导出群聊记录(见 wechat skill)并想生成可直接发回微信群的摘要时使用。
---
# 微信群聊总结指令模板
请按照以下约束为我提供的群聊记录编写总结:
### 核心约束
1. **字数限制**:总字数控制在 **600-700 字**之间即可,确保不被微信折叠。
2. **格式禁用**:**严禁使用** Markdown 的列表符号(如 `-` 或 `*`),微信不支持。
3. **标题格式**:统一使用 `Emoji序号 【议题名称】`,不含“一、二、三、四”等中文数字。
### 结构要求
1. **第一行(固定标题)**:`📝 群聊动态摘要 ({日期})`
2. **第二行(覆盖信息)**:`本次覆盖 {消息总条数} 条消息。首条消息:“{首条原文精准匹配}”;末条消息:“{末条原文精准匹配}”`()
3. **议题正文**:
- 描述讨论的核心内容,并将涉及到的关键群友昵称自然地融入叙述中。
- **传送门格式**:固定为 `[传送门搜索]:{关键词}`,关键词必须是该议题中最具代表性、能通过微信搜索精准定位的**原话片段**,禁止使用概括性描述或改写。
4. **末尾项**:最后一项固定为 `Emoji序号 【其他:{关键词A},{关键词B},{关键词C}】`,关键词最多3个。
注: 消息总条数请自行使用regex计算,计算方法:统计聊天记录中符合`【昵称】:内容⏎`格式的行数即为消息总条数。
---
### 议题优先级判断标准
当识别出的议题数量超出正文容量时,按以下标准排序,末位议题降级为"其他"项关键词:
1. **参与人数**:参与该议题发言的不同群友数量,越多越优先。
2. **消息密度**:该议题的连续消息条数,越高越优先。
3. **结论完整性**:有明确结论或共识的议题优先于开放性闲聊。
---
### 示例输出(供参考):
📝 群聊动态摘要 (YYYY-MM-DD)
本次覆盖 NNN 条消息。首条消息:”[首条消息原文]”;末条消息:”[末条消息原文]”
1️⃣ 【议题标题A】
群友甲和群友乙就某话题展开讨论,提出了观点一和观点二。群友丙补充了相关背景,群友丁表示认同并延伸出新的方向。最终大家在某结论上达成共识。
[传送门搜索]:[该议题最具代表性的原话关键词]
2️⃣ 【议题标题B】
群友戊分享了某资讯,引发群友己和群友庚的讨论。双方就核心分歧各抒己见,气氛热烈,最终未得出明确结论但话题持续发酵。
[传送门搜索]:[该议题最具代表性的原话关键词]
3️⃣ 【其他:关键词A,关键词B,关键词C】
群友辛提及话题甲;群友壬分享了话题乙;群友癸对话题丙发表了简短看法。
[传送门搜索]:[其他项中最具代表性的原话关键词]
Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.
No comments yet. Be the first to comment!
Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.
Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...
Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.
**Complete production-ready guide for Google Gemini embeddings API** This skill provides comprehensive coverage of the `gemini-embedding-001` model for generating text embeddings, including SDK usage, REST API patterns, batch processing, RAG integration with Cloudflare Vectorize, and advanced use cases like semantic search and document clustering. ---
Recovers prior coding-agent session context by running `catchup <agent> --since-compact`, which extracts a clean summary of a previous Codex, Claude Code, Antigravity, OpenCode, or Pi Agent session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", or asks to recover/summarize a previous session before continuing. Do NOT use for the current conversation, git history, or any non-agent log.