meeting-synthesizer
Skill0 starsChanged 2 months agoMITView on GitHub
Analyzes meeting transcripts, recording summaries, or rough notes and extracts decisions, action items, and follow-ups into a structured summary. Triggers when a transcript or meeting notes are shared, on 'summarize this meeting', 'pull out the action items', or when a large block of conversation text is pasted.
In this repository6 other files it gives its agents.
- content-repurposerSkill
- daily-check-inSkill
- linkedin-post-generatorSkill
- okr-managerSkill
- pre-call-prepSkill
- project-instructions-generatorSkill
The file
We split this skill into the rules it gives an agent
7 rules. About 0 are common, 7 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈7
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 12
Use this skill when:
- Distinctive: line 19
Read the entire transcript before producing any output
- Distinctive: line 24
If no clear decisions were made, say so explicitly.
- Distinctive: line 25
Keep the summary to 2-3 sentences maximum — the detail lives in the sections below it
- Distinctive: line 26
Use the exact output format below — do not improvise on structure.
- Distinctive: line 27
If the transcript mentions specific numbers, dates, or commitments, include them exactly as stated
- Distinctive: line 59
Follow-up call scheduled for Tuesday at 2pm
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Meeting Synthesizer
Analyzes meeting transcripts, recording summaries, or rough notes and extracts decisions, action items, and follow-ups into a structured, actionable summary.
Triggers
Use this skill when:
- User shares a meeting transcript, recording summary, or meeting notes
- User says "summarize this meeting," "what happened in this meeting," or "pull out the action items"
- User pastes a large block of text that looks like a conversation or transcript
Rules
- Read the entire transcript before producing any output
- Identify DECISIONS — things that were agreed on, not just discussed. If something was debated but no decision was reached, it goes in Open Questions, not Decisions
- Extract ACTION ITEMS with three fields: owner, task, and deadline. If the deadline wasn't mentioned, write "TBD" — don't invent one
- Note follow-ups that were promised but lack a clear owner or deadline
- Flag any unresolved disagreements or tensions — these often get lost after meetings and matter later
- If no clear decisions were made, say so explicitly. Don't manufacture consensus that didn't happen
- Keep the summary to 2-3 sentences maximum — the detail lives in the sections below it
- Use the exact output format below — do not improvise on structure. Consistency is the point
- If the transcript mentions specific numbers, dates, or commitments, include them exactly as stated
Output Format
Meeting Summary
[2-3 sentences: what this meeting was about and the key outcome]
Decisions Made
- [Each decision stated as a fact, not a discussion point]
Action Items
| Owner | Task | Deadline |
| [Name] | [Specific, actionable task] | [Date or "TBD"] |
Follow-ups Needed
- [Items that need attention but don't have clear owners or timelines yet]
Open Questions
- [Anything unresolved that should be addressed in a future conversation]
Key Quotes (if relevant)
- "[Notable quote that captures a position or commitment]" — [Speaker]
Example
Given rough notes from a client discovery call:
Meeting Summary
Discovery call with Marcus from Greenline Landscaping. Main pain point is estimate turnaround — taking 3-4 days, losing bids to faster competitors. Agreed to a follow-up call Tuesday to discuss a proposal for an AI-assisted estimating workflow.
Decisions Made
- Follow-up call scheduled for Tuesday at 2pm
- [Your Name] will prepare a lightweight proposal (not full SOW) for the call
- Greenline will share their current estimate template before Tuesday
Action Items
| Owner | Task | Deadline |
| [Your Name] | Draft proposal outline for AI-assisted estimating | Monday EOD |
| [Your Name] | Research competitor pricing for similar services | Monday |
| Marcus | Send current estimate template and 3 recent examples | Monday EOD |
Follow-ups Needed
- Marcus mentioned a "new sales hire starting in April" — unclear if this affects timeline or scope
- Pricing discussion deferred to Tuesday call
Open Questions
- What's Greenline's budget range? (Marcus deflected — revisit Tuesday)
- Does Marcus have authority to sign, or does this go to the owner?
Key Quotes
- "Every day that estimate sits on my desk is a day a competitor can steal the deal." — Marcus
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.