菜单
Turn a meeting audio recording into structured notes — attendees, agenda items discussed, key decisions, action items with owners, and open questions. Save the result as a Markdown file. Use when the user attaches an audio file of a meeting or explicitly asks for meeting notes from audio.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
| name | meeting-notes |
| description | Turn a meeting audio recording into structured notes — attendees, agenda items discussed, key decisions, action items with owners, and open questions. Save the result as a Markdown file. Use when the user attaches an audio file of a meeting or explicitly asks for meeting notes from audio. |
The user provides a meeting recording (audio file attachment or an existing audio file in their filesystem) and wants structured notes — not a verbatim transcript.
Examples:
Transcribe. Call transcribe_audio with the audio source (attachment bytes or file path). The tool auto-detects language.
Structure the notes. Write a concise markdown document with these sections. Omit sections that have no content — don't leave empty headings.
# {Title or "Meeting notes"} — {date}## Attendees — names mentioned; mark ones you're unsure about with (?)## Summary — 2-3 sentences: what was the meeting for, what got decided## Discussion — bullet list of the main topics covered, one line each## Decisions — numbered list of concrete decisions with context## Action items — - [ ] {action} — {owner} ({due date if mentioned})## Open questions — things raised but not resolved## Follow-ups — items deferred to a future meetingSave to the user's filesystem. Call fs_write with path: "meetings/{YYYY-MM-DD}-{slug}.md" and the content. Use today's date unless the meeting clearly happened on a different day (mentioned in the audio).
Show the result inline. Render the notes in chat so the user can scan them without opening the file. Add a note of where you saved it (users/<you>/meetings/...).
Offer follow-ups. Use offer_choices:
Evaluate multiple choices side-by-side based on relevant criteria, then present a comparison the user can act on. Use when the user asks to compare options, choose between alternatives, or weigh up X vs Y.
Day-of-week rotating proactive sweep — Mon=connections / Tue=routines / Wed=skills / Thu=memories / Fri=findings / Sat=cross-cutting / Sun=weekly summary. Forces outward scan instead of inward thrash. Routine-only; load this skill into a daily routine that fires AssistantAgent. Adapted from goanna's caretaker.
Use when an agent has had N consecutive quiet runs with nothing to do. Pivots to bounded inward consolidation (promote findings, refresh memory, audit asks) anchored in own data — NOT generic news summarisation. Adapted from goanna's reverie cycle. Routine-only; loaded by the routine that detects the quiet condition.
Use to track open questions you owe the user (asks) and time-bounded commitments you owe yourself (tasks). Write OPEN entries when you commit; promote to CLOSED when answered/done. Survives session compaction. Adapted from goanna's asks.md/tasks.md pattern.
Reviewer criteria for AI-generated code via with_review. Checks for security issues (injection, auth bypass, secret leakage), correctness, and project conventions. Use as criteria.skill when generating code that touches data, auth, or external systems.
Reviewer criteria for outbound email drafts via with_review. Checks tone-recipient match, professionalism, no AI tells, no placeholder leakage. Use as criteria.skill argument when reviewing email drafts before send.