메뉴
MUST BE USED when generating meeting summaries after analysis and routing. Creates per-brain and overall summaries, updates CLAUDE.md files. Works with analyzing-meetings and routing-brains skills.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
SOC 직업 분류 기준
| name | summarizing-meetings |
| description | MUST BE USED when generating meeting summaries after analysis and routing. Creates per-brain and overall summaries, updates CLAUDE.md files. Works with analyzing-meetings and routing-brains skills. |
Generate actionable meeting summaries after routing:
For product-specific context, see CLAUDE.local.md.
Role: Programme Manager / Chief of Staff
Mindset:
## [Brain Name] - Meeting Updates
**Meeting**: [Meeting Name] | **Date**: [Date]
### Items Routed to This Brain
#### Decisions
- **[Decision Topic]** (YYYY-MM-DD)
- *Decision*: [What was decided]
- *Rationale*: [Why, if discussed]
- *Impact*: [What this affects]
#### Action Items
| Action | Owner | Due Date | Context |
|--------|-------|----------|---------|
| [Action] | [Name] | [Date] | [Related discussion] |
#### Discussion Points
- [Key point 1]
- [Key point 2]
#### Blockers/Questions
- **[Blocker/Question]**
- *Context*: [Why this matters]
- *Status*: [Pending/Needs Resolution]
### Cross-Brain Dependencies
- [Any items that also affect other brains]
# Meeting Summary | [Meeting Name] | [Date]
## Overview
**Attendees**: [List participants]
**Duration**: [Approximate length]
**Purpose**: [Meeting objective]
## Brain Distribution
| Brain | Items Routed | Key Outcome |
|------------|--------------|-------------|
| [Brain 1] | [N] items | [One-line summary] |
| [Brain 2] | [N] items | [One-line summary] |
| Unmatched | [N] items | Pending assignment |
## Cross-Brain Themes
- [Theme across multiple brains]
- [Dependencies identified]
## Consolidated Action Items
| # | Action | Owner | Due | Brain |
|---|--------|-------|-----|------------|
| 1 | [Action] | [Name] | [Date] | [Brain] |
## Unresolved Items
- [Items requiring follow-up]
## Next Steps
- [Overall next steps]
For short meetings or highlights only:
**Meeting Recap** | [Meeting Name] | [Date]
**Routed to Brains:**
- [Brain 1]: [N] items ([one-line summary])
- [Brain 2]: [N] items ([one-line summary])
**Key Decisions:**
- [Decision 1] → [Brain]
**Action Items:**
- [ ] [Action] - [Owner] - [Due] → [Brain]
**Unmatched Items**: [N] items pending assignment
Append new decisions:
- **[Decision Topic]** (YYYY-MM-DD)
- *Decision*: [What was decided]
- *Rationale*: [Why this choice]
- *Trade-offs*: [What we're giving up]
- *Related docs*: Meeting notes [Date]
Update if meeting changed status:
**Last Updated**: YYYY-MM-DD HH:MM
- **Progress**: [Updated based on discussion]
- **Recent Changes**: [What changed]
- **Next Milestone**: [Updated if discussed]
Before updating any CLAUDE.md, ask:
Should I update [Brain Name]/CLAUDE.md with:
- [N] decisions
- [N] action items
- [N] status updates
- [N] questions resolved
Proceed? (y/n)
Classify items using Leverage-Neutral-Overhead:
| Classification | Criteria | Handling |
|---|---|---|
| Leverage | Decisions affecting multiple brains, blockers, timeline changes | Highlight prominently |
| Neutral | Status updates, routine discussions | Standard placement |
| Overhead | Administrative, scheduling, logistics | Capture briefly or omit |
Before finalizing, ensure summary answers:
| Question | Your Summary Must Answer |
|---|---|
| "What did we decide?" | Clear decisions with owners |
| "Who's doing what by when?" | Action items with deadlines |
| "What's blocking us?" | Blockers with resolution plans |
| "What changed?" | Status updates with impact |
| "What do I need to do?" | Clear next steps for reader |
If any question can't be answered → there's a gap.
Routed items:
- frontend-modernization: 2 decisions, 1 action
- api-platform: 1 blocker, 2 discussions
- Unmatched: 0 items
# Meeting Summary | Weekly Sync | 2026-01-21
## Overview
**Attendees**: Engineering Lead, PM, Designer
**Duration**: 30 minutes
**Purpose**: Weekly status and blockers
## Brain Distribution
| Brain | Items | Key Outcome |
|------------|-------|-------------|
| frontend-modernization | 3 | React migration approved |
| api-platform | 3 | API blocker identified |
## Consolidated Action Items
| # | Action | Owner | Due | Brain |
|---|--------|-------|-----|------------|
| 1 | Create React migration plan | Engineering | Jan 28 | frontend-modernization |
| 2 | Escalate API blocker | PM | Jan 22 | api-platform |
## Next Steps
- React migration kickoff scheduled for next week
- API blocker needs resolution before launch
MUST BE USED when analyzing meeting transcripts or notes. Classifies input type, attributes speakers, and verifies names against colleagues.json. Works with routing-brains and summarizing-meetings skills for complete workflow.
A framework for evaluating whether a product's success is mathematically possible based on its cost structure, acquisition assumptions, and unit economics. Use this when vetting a new job opportunity, evaluating a startup's viability, or determining if a failing product can be "iterated" to success.
A structured method for gathering high-signal, contextual feedback from a trusted network to validate ideas or navigate complex career decisions. Use this when facing a "fork in the road" career choice, prioritizing product features, or narrowing down topics for public speaking or content.
Create and maintain individual colleague communication profiles in Markdown. Use when the user wants to document a person's communication style, tone preferences, decision style, sensitivities, channels, response cadence, or examples of good vs bad communication, and store it as a per-person profile under input/org/profiles/.
Gather context through high-leverage eigenquestions when information is missing or ambiguous. ACTIVATE THIS SKILL when: (1) context is missing or unclear, (2) user asks something requiring unstated assumptions, (3) working within a brain without recent context, (4) starting new work or strategic decisions, (5) multiple valid approaches exist without clear direction, (6) user says "clarify", "help me think through", or "what should I consider". This skill asks ONE discriminating question at a time to unlock maximum downstream clarity.
Drafts concise, professional PM emails using the CRAFT method. Use when user needs to compose, draft, write, or rewrite professional email communication including follow-ups, status updates, escalations, and stakeholder messages.