agentleFS
masterpeteworldmasterpeteworld/claude-skills/.claude/skills/meeting-assistant/SKILL.md

meeting-assistant

Skill0 starsChanged 25 days agoMITView on GitHub

Turn meeting transcripts or raw notes into chronological minutes with confirmed decisions, pending items, disagreements, and an owner/deadline action table.

The file

We split this skill into the rules it gives an agent

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

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈4

    Distinctive · estimate

    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:

    Normalize input: - prefer timestamps and speaker labels.

    line 17
  2. Distinctive:

    Never mix confirmed decisions with pending items.

    line 28
  3. Very specific:

    Every action item has an Owner (use Unassigned if unknown) and a Deadline (use TBD if unknown).

    line 29
  4. Distinctive:

    Use only content from the provided material.

    line 30
  5. Distinctive:

    If inputs are missing or unreadable, say exactly what is missing and stop.

    line 33

≈ “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

Source: https://github.com/aipoch/medical-research-skills (scientific-skills/Other/meeting-assistant), MIT, AIPOCH. Trimmed for general use.

Meeting Assistant

When to Use

  1. Meeting minutes from raw notes or transcripts, with a clear timeline of what was discussed.
  2. Action item tracking after recurring meetings (weekly syncs, standups, steering committees, client/partner calls) where owners and deadlines must be captured.
  3. Cross-team project sync: consolidate decisions, disagreements, and follow-ups into one output.
  4. Decision logging where confirmed decisions must be separated from items still pending confirmation.
  5. Post-meeting follow-up prep: concise next steps and unresolved questions.

Workflow

  1. Normalize input - prefer timestamps and speaker labels; if missing, infer order from paragraphs and explicit time cues.
  2. Timeline - sort entries by timestamp (or inferred order); write a concise chronological summary that keeps key context.
  3. Extract
    • Decisions: statements of approval, confirmation, or commitment.
    • Pending: proposals, open questions, "to be confirmed" items.
    • Disagreements: explicit objections, conflicting views, unresolved trade-offs.
    • Action items: task + owner + deadline (+ optional status).
  4. Structure output in this fixed order: Basic Info -> Timeline Summary -> Decisions (Confirmed) -> Items Pending Confirmation -> Disagreements / Open Issues -> Action Items table.

Output Rules

  • Timeline follows meeting order.
  • Never mix confirmed decisions with pending items.
  • Every action item has an Owner (use Unassigned if unknown) and a Deadline (use TBD if unknown).
  • Use only content from the provided material. No invented facts, owners, or dates.
  • Preserve numbers, dates, and commitments exactly.
  • Mask emails and phone numbers in the output unless the user asks to keep them.
  • If inputs are missing or unreadable, say exactly what is missing and stop.

Output Template

# Meeting Minutes

## Basic Information
- Meeting Subject:
- Date:
- Participants:
- Recorder:

## Timeline Summary (Chronological)
1. [time] ...

## Decisions (Confirmed)
1. ...

## Items Pending Confirmation
1. ...

## Disagreements / Open Issues
- ...

## Action Items
| Task | Owner | Deadline | Status |
|------|-------|----------|--------|

End with a one-line note of any assumptions made (e.g., inferred order, missing deadlines marked TBD).

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.