Meeting Transcript

What the source does

• FilesystemNone observedNo reads or writes in the source
• NetworkNone observedNo outbound calls in the source
• ShellNone observedNo commands run in the source
• DependenciesPinnedNothing floats
• SecretsNone foundNo keys in source

Five audit layers

Gates applied: no behavioural pass.

Audit 0.4.1 · source sha 6ea1a6ff2160 · 14 Oct 2026Report an issue or request a re-scan

• Publisherhuytieu GitHub userOwner of the repository this skill is read from
• Source folderhuytieu/COG-second-brain/.claude/skills/meeting-transcriptThe exact folder we audited
• LicenceMITAs the repository states it
• Commit pinned for this verdict6ea1a6ff2160A new audit runs when the source changes
• Repository statusNot archivedLast push 11 days ago
• Sandboxed runNot runSkills are read, not executed; layer L4 is skipped

Its description: Process meeting recordings and notes into structured decisions, action items, and team dynamics with intelligent noise filtering

---
name: meeting-transcript
description: Process meeting recordings and notes into structured decisions, action items, and team dynamics with intelligent noise filtering
roles: [product-manager, engineering-lead, founder, designer]
integrations: []
---

# COG Meeting Transcript Skill

## When to Invoke
- User shares a meeting transcript or recording notes
- User says "process meeting", "meeting notes", "meeting transcript"
- User has a block of text from a meeting they want structured
- User mentions wanting to extract action items from a meeting

## Agent Mode Awareness

**Check `agent_mode` in `00-inbox/MY-PROFILE.md` frontmatter:**
- If `agent_mode: team` — use the full parallel agent execution strategy below (3 agents)
- If `agent_mode: solo` — process sequentially: extract content first, then analyze dynamics, then enrich with context.

## Purpose
Extract strategic insights from meeting recordings and notes with intelligent content filtering to focus on substantive, actionable content while removing noise and irrelevant information.

## Command: `/meeting-transcript`

## Parallel Agent Team Execution Strategy

**Use parallel agents to process different aspects of the transcript simultaneously.**

### Phase 1: Setup (Orchestrator)
1. Receive transcript content from user
2. Detect content type (meeting vs braindump) and classify domain
3. Split transcript into logical sections for parallel processing

### Phase 2: Parallel Processing (Spawn 2-3 Agents Simultaneously)
**Launch ALL agents in a single message using Task tool with `run_in_background: true`:**

#### Agent 1: "content-extractor" (subagent_type: general-purpose)
```
Extract structured content from the meeting transcript.

1. Filter out side chats, technical difficulties, and irrelevant banter
2. Identify and extract: decisions made (with rationale), action items (with owners/deadlines), strategic themes
3. Capture key quotes and insights from participants
4. Note unresolved issues and follow-up needs

Return: Decisions list, action items list, strategic themes, key quotes, unresolved issues.
```

#### Agent 2: "dynamics-analyst" (subagent_type: general-purpose)
```
Analyze team dynamics and meeting effectiveness.

1. Assess communication patterns and participation levels
2. Identify leadership moments and collaboration quality
3. Evaluate decision-making process effectiveness
4. Assess meeting efficiency (time well spent vs wasted)
5. Note any tensions, disagreements, or alignment issues

Return: Team dynamics assessment, participation analysis, meeting effectiveness score.
```

#### Agent 3: "context-enricher" (subagent_type: general-purpose)
```
Enrich meeting content with project/product context.

1. If project-related: read recent braindumps and notes for context
2. Check if discussed topics relate to known issues/PRs on GitHub
3. Connect decisions to existing strategic priorities
4. Identify competitive intelligence if competitors mentioned

Return: Contextual connections, related documents, strategic alignment notes.
```

### Phase 3: Assembly (Orchestrator)
1. Collect results from all processing agents
2. Assemble structured meeting summary following Content Structure template
3. Add proper metadata (participants, duration, type, action item count)
4. Save to appropriate domain meeting folder
5. Flag urgent action items for immediate attention

## Content Filtering Guidelines

### EXCLUDE (Filter Out)
- **Side Conversations**: "Hey, did you see the game last night?"
- **Technical Difficulties**: "Can you hear me now?" "Your mic is muted"
- **Incomplete Thoughts**: "So I was thinking we should... never mind"
- **Casual Banter**: Weather, personal anecdotes unrelated to work
- **Interruptions**: "Sorry, I have to take this call"
- **Unclear Statements**: Mumbled or inaudible content

### INCLUDE (Keep and Analyze)
- **Strategic Discussions**: Market analysis, competitive positioning
- **Decision Points**: "We've decided to move forward with Option A"
- **Action Items**: "Alex will complete the analysis by Friday"
- **Problem Solving**: Discussion of challenges and proposed solutions
- **Planning**: Timeline discussions, resource allocation
- **Insights**: "The key insight is that customers want..."
- **Concerns**: "My concern is that this approach might..."

## Metadata Template
```yaml
---
type: meeting-transcript
domain: [personal|professional|project-specific]
project: [project-name] # Only for project-specific meetings
date: YYYY-MM-DD
created: YYYY-MM-DD HH:MM
meeting_type: [1-on-1|team-meeting|strategic-planning|project-review|other]
participants: [participant1, participant2, participant3]
duration: [minutes]
content_filtered: true
accuracy_verified: [true|false|pending]
action_items_count: [number]
decisions_count: [number]
tags:
  - meeting
  - transcript
  - domain-tag
  - project-tag
status: [processed|needs-follow-up|action-required]
---
```

## Content Structure

### 1. Meeting Overview
- **Date/Time**: When the meeting occurred
- **Participants**: Who was present and their roles
- **Purpose**: Primary objective of the meeting
- **Duration**: Actual meeting length
- **Type**: Category of meeting

### 2. Key Decisions (Verified Content Only)
- **Decision**: What was decided
- **Rationale**: Why this decision was made
- **Owner**: Who is responsible for implementation
- **Timeline**: When decision takes effect
- **Impact**: Expected outcomes and implications

### 3. Action Items (Substantive Only)
- **Task**: Specific action to be taken
- **Owner**: Person responsible
- **Deadline**: When it's due
- **Dependencies**: What needs to happen first
- **Success Criteria**: How completion will be measured

### 4. Strategic Themes (From Substantial Discussion)
- **Theme**: Major topic or pattern discussed
- **Context**: Why this theme is important
- **Implications**: What this means for the team/project
- **Next Steps**: How to address or leverage this theme

### 5. Unresolved Issues
- **Issue**: Problem or question 

Excerpt, first 6,000 characters of SKILL.md, verbatim from the audited commit. It is text from someone else’s repository, quoted so you can judge it before your agent reads it.

git clone https://github.com/huytieu/COG-second-brain
git -C COG-second-brain checkout 6ea1a6ff2160

Works in

1. 2026-10-14
   ✓SAFE B 89 / 100

   first audit · source 6ea1a6ff2160

Questions about Meeting Transcript

• github.com/huytieu/COG-second-brain/tree/main/.claude/skills/mee — the audited source at commit 6ea1a6ff2160 and every finding aboveObserved · 14 Oct 2026

Spotted something wrong? Report a correction · Methodology