cog-meeting-processing
This Claude Code skill processes meeting recordings and transcripts to extract structured outputs including decisions with context and rationale, action items assigned to owners with deadlines, team dynamics analysis measuring engagement and alignment, and executive summaries. Use it when you need to quickly convert raw meeting content into organized, actionable documentation that identifies who owns what tasks and captures strategic decisions for project tracking across teams.
git clone --depth 1 https://github.com/a5c-ai/babysitter /tmp/cog-meeting-processing && cp -r /tmp/cog-meeting-processing/library/methodologies/cog-second-brain/skills/meeting-processing ~/.claude/skills/cog-meeting-processingSKILL.md
- Extract decisions with context, rationale, and stakeholders
- Identify action items with owners, priorities, and deadlines
- Analyze team dynamics: engagement, alignment, collaboration quality
- Generate executive meeting summaries
- Segment transcripts into topics and discussion threads
- Route meeting artifacts to vault with project cross-references
## Tool Use Instructions
1. Use `file-read` to load the meeting transcript or recording
2. Parse transcript and identify speakers against participant list
3. Segment into topics and discussion threads
4. Extract decisions with context and rationale
5. Extract action items with owners and deadlines
6. Analyze team dynamics (engagement, alignment, disagreements)
7. Use `file-write` to create meeting notes in 03-professional
8. Use `file-search` to find related projects for cross-referencing
9. Use `git-commit` to commit meeting artifacts
## Examples
```json
{
"vaultPath": "./cog-vault",
"captureType": "meeting-transcript",
"transcriptPath": "./meeting-2026-03-02.txt",
"meetingTitle": "Sprint Planning Q1 W9",
"participants": ["Alex", "Jordan", "Sam"]
}
```Coordinate Crew (persistent) and Polecat (transient) agents using Gas Town's hook-based work distribution and GUPP principle.
System and API design guidance covering component boundaries, data flow, integration patterns, and scalability considerations.
This skill should be used when the user asks to "find skills in the wild", "assimilate popular workflows", "discover SKILL.md files in repos", "research external skills", "find workflow patterns", "survey the skill landscape", "what skills exist out there", or wants to investigate public repositories for extractable processes, babysitter plugins, and reusable procedural insights. Searches GitHub for SKILL.md files, classifies repos by archetype, and maintains structured research under docs/reference-repos/.
>-
This skill should be used when the user asks to "babysit issues", "work on assigned issues", "check a5c-agent issues", "process babysitter issues", or wants to find and work on open GitHub issues assigned to a5c-agent in the babysitter repo.