agentleFS
zeiynzzeiynz/claude-skills/meeting-action-items/SKILL.md

meeting-action-items

Skill0 starsChanged 4 months agoMITView on GitHub

Turn raw meeting notes, transcripts, or voice-memo dumps into structured decisions, action items (with owner + due date), and open questions — ready to paste into Slack, email, or a tracker. Use whenever the user pastes meeting notes/transcripts, says "extract action items from this", "summarize this call", "who owns what from this meeting", or uploads a transcript file and wants next steps rather than a narrative recap. Trigger proactively any time raw unstructured meeting text appears in the conversation, even if the user's ask is vague ("here's the notes from today").

11 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use github.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • NVIDIASkill

    github

    Interact with GitHub using the gh CLI restricted to REST API only (no GraphQL). Use when the user wants to work with GitHub issues, pull requests, repos, releases, or Actions — especially in sandboxed environments where the GraphQL endpoint may be blocked. Trigger keywords - github, gh, pull request, PR, github issue, github actions, workflow, release, gh api.

    Also in 4 projects that use this

The file

We split this skill into the rules it gives an agent

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

  • 0

    Common

    Most of the 11 edited versions we read keep these.

  • 4

    Distinctive

    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:

    Call out anything that sounds like: a missed deadline being discussed, a disagreement that got glossed over rather than resolved, or a …

    line 31
  2. Distinctive:

    Ask (or infer from context) where this is going:

    line 34
  3. Distinctive:

    Don't invent due dates that weren't stated — "no date given" is more useful than a fabricated deadline

    line 40
  4. Distinctive:

    Don't attribute a decision to "the team" when only one or two people actually agreed and others were silent — silence isn't consent, note …

    line 41

“Common” is measured: kept by at least 6 in 10 of the 11 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 Action Items

Converts messy, real-world meeting input (half-sentences, crosstalk, someone saying "yeah let's do that" three different ways) into three clean buckets: decisions made, actions owed, and things still open. The goal is a summary someone could act on without having attended the meeting.

Why not just "summarize this meeting"

A narrative summary optimizes for understanding what happened. This skill optimizes for what happens next — a different, more useful artifact for most post-meeting workflows (standups, sales calls, project syncs, 1:1s).

Workflow

Step 1: Identify meeting type — it changes what to extract

  • Standup/status sync → focus on blockers and today/tomorrow commitments
  • Sales/customer call → focus on objections raised, next steps, and follow-up commitments made to the prospect
  • Project/planning meeting → focus on decisions + owners + dates
  • 1:1 → focus on commitments made by each party, don't over-formalize (a 1:1 doesn't need a project-tracker-style output)

Step 2: Extract into three buckets (never merge these)

Decisions made — things the group actually agreed on, stated definitively. Distinguish from discussed but not decided — if the transcript shows genuine ambiguity or disagreement, put it in Open Questions instead, don't force a decision that wasn't made.

Action items — format as: [Owner] — [specific action] — [due date if stated, else "no date given — flag"]. If a speaker isn't named in the transcript (common in auto-transcribed audio, e.g. "Speaker 2"), don't guess who they are — mark owner as "unclear — confirm" rather than inventing a name.

Open questions / unresolved — anything raised but not settled. This bucket is often the most valuable one and the most commonly dropped by narrative summaries.

Step 3: Flag risks explicitly

Call out anything that sounds like: a missed deadline being discussed, a disagreement that got glossed over rather than resolved, or a commitment made without clear ownership. These are the things that cause the next meeting to be "wait, who was doing this?"

Step 4: Format for the destination

Ask (or infer from context) where this is going:

  • Slack/email recap → short, scannable, bullets only, no headers needed for a short meeting
  • Tracker/ticket creation → one line per action item in a format ready to paste into Jira/Linear/Asana (title + owner + due date as separate fields)
  • Formal minutes → use the full template in references/minutes-template.md

Common pitfalls

  • Don't invent due dates that weren't stated — "no date given" is more useful than a fabricated deadline
  • Don't attribute a decision to "the team" when only one or two people actually agreed and others were silent — silence isn't consent, note it as tentative
  • Multi-speaker transcripts with unclear attribution: preserve the ambiguity rather than resolving it via guesswork

Reference

  • references/minutes-template.md — full formal-minutes format for board/leadership meetings

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.