Chinese-Optimized Group Chat Summarizer
Paste the following prompt into your AI chat to install this skill:
Please follow https://skillhub.cn/install/skillhub.md to install @user_dfbdc5ab/group-chat-summarizer-cn.
About this skill
Problem to Solve
Group-chat threads often mix decisions, assignments, and risks into long message flows, making manual review costly. group-chat-summarizer works from exported chat records and turns scattered messages into a shareable, follow-up-ready summary. It does not monitor live chats or replace human judgment.
How It Works
The skill parses platform-specific message formats and organizes topics along a timeline. A typical output includes six sections: basic info, timeline, key points, action items, follow-up suggestions, and notes. It attempts to extract:
- Owners: @mentions and assignment language in context
- Deadlines: expressions such as “Friday,” “next week,” or “ASAP”
- Risks and disagreements: time, resource, technical, dependency, and unresolved conflicts
- Summary depth: concise, standard, or detailed modes based on message volume and context
It supports Feishu, DingTalk, WeCom, QQ, Discord, Slack, Teams, Telegram, as well as plain text, CSV, and JSON. For threads over 500 messages, segment by time window first; manually verify extracted owners and statuses, especially when edited or deleted messages leave gaps in context.
Use Cases
- Before standup, turn yesterday’s tech-thread discussion into todos and decisions
- Before leave, review recent thread topics and items affecting you
- After meetings, convert long discussions into decisions, owners, and actions
- During project follow-up, extract progress, risks, blockers, and next steps
Best For
- Engineers who extract todos and technical risks from multiple chat threads daily
- Team members who need recent decisions and personal follow-ups before leave
- Project managers who own meeting minutes and post-meeting follow-up
- Leads who sync thread summaries with managers or collaborators
Related Skills
Turns Taleb's antifragility, barbell strategy, and via negativa into executable prompts for risk analysis in career, investing, health, and other domains.
Keyword news search over ZAKER’s corpus with optional time filtering, returning up to 20 titles, authors, and summaries.
A generic knowledge review skill that generates role-based checklists, rrule-based reminders, and on-demand reviews without storing personal data.
A knowledge-management skill for layered retrieval across information sources.