agentleFS
DevelopersGlobalDevelopersGlobal/ai-agent-skills/skills/meeting-notes-to-tasks/SKILL.md

meeting-notes-to-tasks

Skill216 starsChanged 6 months agoMITView on GitHub

Converts unstructured meeting notes into structured, assigned, time-bounded action items. Never leave a meeting without knowing who does what by when.

We split this skill into the rules it gives an agent

5 rules. About 0 are common, 5 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈5

    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
  1. Distinctive:

    After any meeting with decisions or commitments

    line 15
  2. Distinctive:

    When processing meeting transcripts or notes

    line 16
  3. Distinctive:

    When preparing follow-up communication

    line 17
  4. Distinctive:

    If an owner is not named: flag it — unowned actions are undone actions.

    line 38
  5. Distinctive:

    If a due date is not named: flag it — undated actions are undone actions.

    line 39

≈ “Common” is an estimate: at least 1 in 5 of the 308,232 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.

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

Overview

Meetings produce decisions and commitments. Without structure, these dissolve into vague memory. This skill transforms raw meeting notes into a concrete, actionable task list.

When to Use

  • After any meeting with decisions or commitments
  • When processing meeting transcripts or notes
  • When preparing follow-up communication

Process

Step 1: Extract Decisions

  1. Read all notes.
  2. List every decision made: Decision: [what was decided]
  3. Distinguish decisions from discussions (decisions = agreed outcomes, not explorations).

Deliver: A numbered list of decisions made.

Step 2: Extract Action Items

  1. For each commitment made, write:
    Action: [specific deliverable]
    Owner: [person's name]
    Due: [specific date, not "soon" or "next week"]
    Context: [1-sentence background]
  2. If an owner is not named: flag it — unowned actions are undone actions.
  3. If a due date is not named: flag it — undated actions are undone actions.

Deliver: Structured action items with owner and due date for every commitment.

Step 3: Identify Blockers and Dependencies

  1. What action items are blocked by other action items?
  2. What external dependencies exist (waiting on third party, requires approval, etc.)?
  3. What open questions remain unresolved?

Deliver: Blocker list and open questions with owners.

Step 4: Draft Follow-Up Summary

  1. Compose a concise follow-up message:
    • Decisions (bullet list)
    • Action items (table: action | owner | due date)
    • Open questions (bullet list with owner)
    • Next meeting date (if applicable)

Deliver: Ready-to-send follow-up email/Slack message.

Common Rationalizations (and Rebuttals)

ExcuseRebuttal
"Everyone knows what they need to do"They don't. Write it down.
"The notes are good enough"Notes describe what was said. Action items describe what will be done.
"We'll follow up informally"Informal follow-up means things fall through the cracks.

Verification

  • Every decision captured
  • Every action item has: owner, due date, specific deliverable
  • Unowned/undated items flagged
  • Blockers and open questions identified
  • Follow-up summary drafted and ready to send

References

  • goal-driven-execution skill

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.