Meeting notes distiller
Skill sisodiabhumca/agent-skills/skills/meeting-notes-distiller
Production-Ready Agent Skills : product analytics, growth experiments, CRM, research synthesis, postmortems, data contracts, SaaS spend, compliance, architecture maps, and LLM eval and many more.
npx -y skills add sisodiabhumca/agent-skills --skill meeting-notes-distillerAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
One thing to look at
- 0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
What its author says it does
Copied from the file, not written here
Use when given a meeting transcript or raw notes to produce a structured summary — decisions made, action items (with owner + due date), risks/blockers, open questions, and a follow-up email draft. Vendor-neutral; works with output from any transcription provider.
SKILL.md
1.5 KB, 308 tokens by cl100k_base, as published. Nobody here has run it
Meeting Notes Distiller
When to invoke
- "Summarize this meeting transcript."
- "Extract action items from these notes."
- "Draft a follow-up email from this meeting."
Inputs needed
- Transcript or notes — plain text, Markdown, VTT, or SRT.
- Attendees (optional) — to disambiguate owner attribution.
- Meeting purpose (optional) — improves the summary framing.
Workflow
- Clean — strip timestamps, speaker tags, filler tokens.
- Extract:
- Decisions (what was agreed)
- Action items (action, owner, due date)
- Risks / blockers
- Open questions
- Validate — every action item must have an owner; flag unowned ones.
- Draft a follow-up email summarizing the above.
Output format
## Summary
## Decisions
## Action items
| # | Action | Owner | Due | Source line |
## Risks / blockers
## Open questions
## Follow-up email (draft)
Guardrails
- Never invent owners, dates, or decisions not in the source.
- Mark items missing an owner as
(unowned)and surface them. - Quote the source line/index for every action item.
Reference code
distill.py does pattern-based extraction (timestamps, speaker tags, action verbs, due-date phrasing).