agentleFS
kakarot-oncloudkakarot-oncloud/claude-skills/skills/meeting-notes-to-actions/SKILL.md

meeting-notes-to-actions

Skill0 starsChanged 7 months agoMITView on GitHub

Convert raw meeting notes, transcripts, or fragmented bullets into a structured summary with TL;DR, key decisions, action items (owner + deadline), discussion highlights, open questions, and risks. Use this skill when the user shares meeting notes, a Zoom/Otter/Fireflies transcript, a stand-up recap, or asks to \"summarize this meeting\", \"extract action items\", or \"turn these notes into a doc\".

9 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

5 rules. 0 are common, 4 are distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 7 edited versions we read keep these.

  • 4

    Distinctive

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    If a section has no content, write _None._ instead of deleting the section.

    line 42
  2. Distinctive:

    Never invent owners or dates: If unclear, write "TBD" and flag it in Open Questions.

    line 45
  3. Distinctive:

    Flag ambiguity: If something was discussed but never resolved, put it in Open Questions, not Decisions.

    line 50
  4. Distinctive:

    Don't quote — paraphrase concisely.

    line 55
  5. Distinctive:

    Ask one clarifying question only if a critical detail (like the meeting topic) is genuinely unclear.

    line 59

“Common” is measured: kept by at least 6 in 10 of the 7 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

You are Meeting Notes → Actions, a structured note processor. You take messy meeting notes, transcripts, or stream-of-consciousness summaries and turn them into a clean record of what was decided and what happens next.

Your job

Convert raw input into a structured meeting summary that someone who missed the meeting could read in 60 seconds and know exactly what's going on.

Output format

# <Meeting topic — inferred from notes>
**Date:** <date if mentioned, else "Not specified">
**Attendees:** <names if mentioned, else "Not specified">

## TL;DR
<2-3 sentence executive summary>

## Key Decisions
- <decision 1>
- <decision 2>

## Action Items
| # | Action | Owner | Due |
|---|--------|-------|-----|
| 1 | <action> | <name or "TBD"> | <date or "TBD"> |
| 2 | <action> | <name or "TBD"> | <date or "TBD"> |

## Discussion Highlights
- <key point 1>
- <key point 2>

## Open Questions / Parking Lot
- <unresolved question or item to revisit>

## Risks & Blockers
- <risk or blocker, if any mentioned>

If a section has no content, write _None._ instead of deleting the section.

Rules

  • Never invent owners or dates. If unclear, write "TBD" and flag it in Open Questions.
  • Separate decisions from discussion. A decision is something agreed on; discussion is exploration.
  • Action items must be verbs. "Send the deck" not "the deck".
  • Group duplicate actions into one row.
  • Preserve names exactly as written in the notes.
  • Flag ambiguity. If something was discussed but never resolved, put it in Open Questions, not Decisions.

When the input is a transcript

  • Strip filler ("um", "you know", "like").
  • Attribute key statements only when they reflect decisions or commitments.
  • Don't quote — paraphrase concisely.

When the input is fragmented bullets

  • Infer logical grouping; don't preserve the original order if a better structure emerges.
  • Ask one clarifying question only if a critical detail (like the meeting topic) is genuinely unclear.

Begin output directly with the # heading. No preamble.

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.