agentleFS
CharleneTStrainCharleneTStrain/product-ops-skills/skills/meeting-to-action-converter/SKILL.md

meeting-to-action-converter

Skill0 starsChanged 21 days agoMITView on GitHub

Turn meeting notes, transcripts, or recordings summaries into a short recap of action items with one owner and a due date each, plus decisions and open questions. Use when someone pastes meeting notes or a transcript and wants next steps, action items, a recap email, a follow-up message, or asks "what did we agree to?

The file

We split this skill into the rules it gives an agent

6 rules. About 0 are common, 6 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈6

    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:

    Read the whole source and pull out three kinds of things:

    line 18
  2. Distinctive:

    Only count something as an action item if the source shows someone taking it on.

    line 24
  3. Distinctive:

    Every action item needs:

    line 28
  4. Distinctive:

    If two people both said they'd handle something, list it once with both names and flag "Owner unclear."

    line 39
  5. Distinctive:

    Keep it short enough to paste into chat or email as is.

    line 60
  6. Distinctive:

    If the person wants a follow-up message, write it as the recap with one opening line, ready to send.

    line 62

≈ “Common” is an estimate: at least 1 in 5 of the 372,429 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

Meeting to action converter

Most meetings end with everyone agreeing and nobody owning anything. This skill finds the commitments hidden in the conversation and makes each one specific enough to check off.

Before you start

If .agents/product-ops-context.md exists (or .claude/product-ops-context.md), read it first. Use the team, owners, tools, meetings, and metric definitions it already has, and only ask for what's missing or specific to this task. If it doesn't exist, go ahead with what you're given, and suggest running product-ops-context once so the next skill doesn't have to ask.

Step 1: Find the commitments

Read the whole source and pull out three kinds of things:

  • Action items: someone said they would do something, or was asked and agreed
  • Decisions: a call was made (hand these to the decision-log skill if a full entry is needed)
  • Open questions: raised but not answered, or parked for later

Only count something as an action item if the source shows someone taking it on. "We should look into X" with no taker is an open question, not an action.

Step 2: Make each action specific

Every action item needs:

FieldRule
ActionStarts with a verb; says what "done" looks like
OwnerOne person, by name. Never a team, never "we," never two names
DueDate from the source. If none was set, write "No date set"
Depends onAnother action or person, if the source says

Rewrite vague actions into checkable ones only using what the source says: "follow up on pricing" becomes "Send Dana the updated pricing sheet" if the notes say that's what was meant. If the source doesn't say, keep it vague and flag it.

If two people both said they'd handle something, list it once with both names and flag "Owner unclear."

Step 3: Write the recap

# [Meeting name] — [Date]
**Attendees:** [names]

## Action items
- [ ] **[Owner]:** [Action] — Due [date]

## Decisions
- [Decision, one line each]

## Open questions
- [Question] — Who can answer: [name, if known]

## Flags
- [Actions with no owner, no date, or an unclear owner]

Keep it short enough to paste into chat or email as is. No meeting narrative, no "great discussion," no summary of who said what unless asked.

If the person wants a follow-up message, write it as the recap with one opening line, ready to send.

Related skills

  • decision-log — log the decisions in full
  • ritual-calendar — check the meeting has a clear purpose
  • cross-team-dependency-map — track actions that block other teams

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.