Chen Geng Client Meeting Notes Assistant
Paste the following prompt into your AI chat to install this skill:
Please follow https://skillhub.cn/install/skillhub.md to install @user_88e00a20/chengeng-meeting-notes.
About this skill
Problem
Insurance conversations often end up as scattered chat logs, call transcripts, and ad hoc notes. A naive summary can blur customer statements, analyst inference, and next actions, leaving little material for follow-up.
How It Works
The skill treats a meeting note as a follow-up artifact rather than a transcript:
- Separate facts from inference: track what the customer explicitly said, what is inference, and what is pending.
- Stage and actions: identify the customer's stage and define who does what next.
- Quality gate: if scenario, target, or source material is missing, return a gap list and a low-confidence draft instead of inventing a final version.
Typical outputs include a communication summary, customer profile, explicit requirements, concerns, conclusions, next actions, reminders, and send-ready follow-up messages. If the user requests image cards, it first completes the text note, then generates visual-model.json, flowing HTML, and a PNG via Playwright. Completion requires checking the PNG, HTML, and render-report.json; an unverified image is not reported as delivered.
Boundaries
It fits first interviews, solution walkthroughs, phone/video calls, follow-up records, and joint visit reviews. It should not promise closing, claims, underwriting, medical, legal, or income outcomes, and it should not present unconfirmed items as conclusions. When input is thin, the priority is asking for purpose and materials, not fabricating customer background.
Use Cases
- Turn a first-requirements call transcript into stated needs, concerns, and next owner.
- Separate confirmed facts, inferences, and pending questions from solution session notes.
- Convert co-visit review notes into client stage, next actions, and follow-up reminders.
- For card requests, finish the written note, split long content, and verify PNG rendering.
Best For
- Insurance client advisors who need interview records turned into follow-up summaries and next actions.
- Sales support specialists who need to clarify objections, pending items, and owners from solution calls.
- Customer operations staff who need chat logs turned into send-ready follow-up messages and reminders.
- Insurance team leads who need co-visit reviews to check facts, inferences, and pending questions.
Related Skills
Generate and edit .pptx decks with python-pptx, applying structured layouts, design rules, native charts, and visual QA to reduce template-like output.
Tencent Cloud Table Recognition V3 is an OCR skill for detecting and recognizing tables in images or PDFs, supporting various table types like linear and borderless tables, with Excel export.
The complete set of online document operation tools provided by Tencent Docs MCP, supporting creation, querying, and editing of smart docs, Excel, PPT, mind maps, and more.
Turn a topic, notes, or tables into a complete PPT plan with logic, page layouts, visual and chart guidance, and natural defense scripts.