agentleFS
moses607moses607/skillforge/skills/meeting-to-actions/SKILL.md

meeting-to-actions

Skill0 starsChanged 4 months agoMITView on GitHub

Convert meeting notes, a transcript, or a rough recap into a clean record of decisions, owned action items, and a follow-up message. Use whenever the user pastes meeting notes or a transcript, says "summarize this meeting", "what did we decide", "pull the action items", "who owns what", or asks for a recap email after a call. Trigger even from messy or partial notes.

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

4 rules. 0 are common, 3 are distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 6 edited versions we read keep these.

  • 3

    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. Distinctive:

    ALWAYS produce these three blocks:

    line 19
  2. Very specific:

    Never invent an owner or a due date.

    line 47
  3. Distinctive:

    If two people seem jointly responsible, name a single directly responsible owner and list the other as support — shared ownership means no …

    line 48
  4. Distinctive:

    Keep the recap skimmable: a busy attendee should get the gist in 15 seconds.

    line 49

“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

A meeting only pays off if decisions and owners survive it. Extract signal (decisions + actions), drop chit-chat, and make every commitment traceable to a person.

Extraction rules

  • Decision = a choice the group settled ("we'll go with Postgres"). Capture the decision AND its rationale if stated — future readers ask "why".
  • Action item = something a specific person will do by some time. Every action needs an owner. If the notes name no owner, write owner: UNASSIGNED — surfacing the gap is the point.
  • Open question = unresolved, needs a decision later. Don't fabricate resolutions.
  • Discard: greetings, tangents, re-litigated points that were then dropped, filler.

Output template

ALWAYS produce these three blocks:

## <Meeting> — <date>

### Decisions
1. <decision> — rationale: <if given, else "not stated">

### Action items
| # | Action | Owner | Due | Notes |
|---|--------|-------|-----|-------|
| 1 | <verb-first, concrete> | <name> | <date or "TBD"> | |

### Open questions
- <question> — <who needs to answer / by when>

Then, unless told not to, draft a follow-up message (Slack-length by default; email if the meeting was external):

### Follow-up draft
Subject: <meeting> — decisions & next steps
<2-3 line recap. Then the action list, each line "@owner: <action> (by <date>)". Close with the next checkpoint.>

Rules

  • Actions start with a verb: "Draft the RFC", not "RFC".
  • Never invent an owner or a due date. UNASSIGNED / TBD are correct answers.
  • If two people seem jointly responsible, name a single directly responsible owner and list the other as support — shared ownership means no ownership.
  • Keep the recap skimmable: a busy attendee should get the gist in 15 seconds.

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.