Converts raw meeting transcripts into structured, actionable notes with decision logs, assigned action items, and key context preserved for future AI retrieval. This skill bridges the gap between what was discussed in a meeting and what AI agents need to know when acting on outcomes days or weeks later.
Use cases
- A project kickoff meeting where stakeholders express goals and constraints that need to guide subsequent AI-assisted work
- A sprint retrospective where the team identifies process improvements that should inform future planning AI prompts
- A design review where decisions and rationale need to be preserved for the engineering team implementing the spec
- A client call where requirements and expectations must be captured accurately for AI agents working on the project
- A technical architecture discussion where tradeoffs and decisions need to be searchable by future AI agents
Key features
- Extract the meeting metadata: date, attendees, meeting type, and stated purpose before processing content
- Identify and tag all decisions made during the meeting, recording both the outcome and the reasoning where expressed
- Parse action items with assigned owners, deadlines, and deliverables in structured format
- Preserve key context: constraints, dependencies, assumptions, and risks mentioned that could affect future work
- Format for AI retrieval: use consistent heading structures, bullet hierarchies, and searchable keywords
- Link related decisions to existing project documentation where applicable
- Generate a one-paragraph executive summary that captures the meeting outcome in plain language
When to Use This Skill
- After any meeting that will inform AI-assisted work in subsequent days or weeks
- When action items require tracking and follow-up across a team using AI tools
- When decisions made in meetings need to be searchable by AI agents working on the project
Expected Output
A structured markdown document with decision log, action items table, key context section, and AI-friendly formatting that can be stored in a project memory system.
Frequently Asked Questions
- How does this differ from standard meeting notes?
- Standard notes capture what was said. Structured notes capture decisions, action items, and context in formats optimized for AI retrieval. The output is designed to be stored in project memory and retrieved by AI agents working on related tasks.
- What if the meeting transcript is messy or incomplete?
- The skill identifies gaps and marks them explicitly (e.g., 'decision rationale unclear - follow up with [person]'). Partial information is better than no information, and the format makes it easy to fill in gaps later.
- Can this work with meeting recordings?
- Yes, when paired with a transcription tool, the skill processes the transcript directly. For video meetings, combine with a transcription step first, then apply the structured notes skill.
Related
Related
3 Indexed items
AI product requirement writing
Writes product requirements documents that AI agents can act on reliably, with explicit constraints, edge cases, and acceptance criteria that minimize the gap between what you mean and what the agent builds. This skill bridges the ambiguity of natural language product specs and the precision that AI agents require to produce consistent results.
Documentation from code
Extracts architecture decisions, API contracts, and usage patterns directly from code to produce accurate documentation that stays in sync with implementation. Documentation-from-code treats code as the source of truth and generates prose from it rather than maintaining documentation as a separate artifact that diverges over time.
Humanizer
Removes the common AI-generated writing patterns—significance inflation, filler -ing constructions, em-dash chains, and formulaic closers—that make machine-generated prose feel generic or overproduced. Runs a final 'still obviously AI?' audit pass before shipping any prose intended for human readers.