agentleFS
zhouey314-cloudzhouey314-cloud/ai-agent-skills/skills/meeting-to-actions/SKILL.md

meeting-to-actions

Skill0 starsChanged 51 days agoMITView on GitHub

Extract decisions and owner-tagged actions from a supplied transcript without inventing deadlines or sending assignments.

6 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, 2 are distinctive, and 3 are very specific to this project.

  • 0

    Common

    Most of the 6 edited versions we read keep these.

  • 2

    Distinctive

    This author's own choices. Worth a look.

  • 3

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Create a reviewable meeting follow-up from transcript evidence.

    line 10
  2. Distinctive:

    Use when the user supplies a transcript or notes and wants action items, not an automatic outbound message.

    line 14
  3. Very specific:

    Keep owner and due date unknown unless stated or clearly resolved in the transcript.

    line 28
  4. Very specific:

    If attribution is ambiguous, mark the owner unknown.

    line 34
  5. Very specific:

    Run python3 tests/validate.py from the repository root to check this skill's contract and example provenance.

    line 42

“Common” is measured: kept by at least 6 in 10 of the 6 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

Meeting to Actions

Purpose

Create a reviewable meeting follow-up from transcript evidence.

When to Use

Use when the user supplies a transcript or notes and wants action items, not an automatic outbound message.

Inputs

transcript, participants[], meeting_date, optional language.

Outputs

summary, decisions[], actions: [{task,owner,due,evidence_quote,confidence}], unknowns[].

Workflow

  1. Mark inaudible or contradictory transcript spans instead of smoothing them away.
  2. Extract only commitments or requests tied to a quoted span.
  3. Keep owner and due date unknown unless stated or clearly resolved in the transcript.
  4. Separate decisions from proposals and disagreements.
  5. Return a draft for human confirmation before any assignment is sent.

Failure Handling

If attribution is ambiguous, mark the owner unknown; if the transcript is incomplete, flag missing context. Never send or schedule automatically.

Example

synthetic_unverified: “Alex will review the sample draft” yields owner Alex and due date unknown.

Tests

Run python3 tests/validate.py from the repository root to check this skill's contract and example provenance. This is a structural test, not model-quality evidence.

Limitations

Transcription errors can propagate; the original recording or participant confirmation may be required.

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.