agentleFS
duncan-buildroomduncan-buildroom/profit-room-skills/skills/meeting-notes/SKILL.md

meeting-notes

Skill18 starsChanged 4 months agoMITView on GitHub

Process meeting transcripts into structured markdown summaries. Use this skill whenever the user pastes a meeting transcript, shares meeting notes, or says anything like "process this meeting", "summarize this call", "extract action items", "here's a transcript from my call", or "here are my meeting notes". Works with transcripts from any tool (Fireflies, Otter, Granola, Zoom, etc.). Trigger even if the user just pastes a block of text that looks like a speaker-labeled transcript.

58 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use email-draft, status-report and 7 more.

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.
  • yakatotechSkill

    email-draft

    Create business email drafts. Use when asked to draft emails

    Also in 3 projects that use this

  • AnthropicSkill

    status-report

    Generate a status report with KPIs, risks, and action items. Use when writing a weekly or monthly update for leadership, summarizing project health with green/yellow/red status, surfacing risks and decisions that need stakeholder attention, or turning a pile of project tracker activity into a readable narrative.

    Also in 3 projects that use this

  • QuixiAISkill

    weekly-review

    Review the past week across goals, tasks, calendar, journal, and commitments, then propose the next week

    Also in 8 projects that use this

  • LangChainSkill

    web-research

    Use this skill for requests related to web research; it provides a structured approach to conducting comprehensive web research

    Also in 4 projects that use this

  • jacobraskSkill

    calendar

    Interact with Apple Calendar via AppleScript. Use when the user asks to check calendar, view events, create events, manage schedule, find free time, or list calendars. Triggers include "my calendar", "my schedule", "calendar events", "create event", "add to calendar", "what's on my calendar", "free time", "available slots", "upcoming events", "today's events". Requires macOS with Calendar.app.

    Also in 3 projects that use this

  • LangChainSkill

    competitor-analysis

    Analyze competitors in a given market segment. Trigger on: competitive landscape, competitor analysis, market comparison, competitive positioning.

    Also in 3 projects that use this

The file

We split this skill into the rules it gives an agent

8 rules. 0 are common, 5 are distinctive, and 3 are very specific to this project.

  • 0

    Common

    Most of the 45 edited versions we read keep these.

  • 5

    Distinctive

    This author's own choices. Worth a look.

  • 3

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    If someone says "I'll handle X" or "can you take care of Y?" — assign directly.

    line 23
  2. Very specific:

    If no one claims a task but a domain expert is on the call (e.g., task is about design and a designer is present) — assign to them and flag …

    line 24
  3. Very specific:

    If it's truly ambiguous with no reasonable inference — mark [UNASSIGNED].

    line 25
  4. Distinctive:

    Never invent assignments with confidence — flag uncertainty clearly.

    line 26
  5. Very specific:

    Use the date from the transcript.

    line 33
  6. Distinctive:

    Use exactly this markdown structure:

    line 35
  7. Distinctive:

    If a section has nothing to add (e.g., no open questions), omit it entirely — don't include an empty section.

    line 78
  8. Distinctive:

    Ask if they'd like any section expanded or adjusted

    line 86

“Common” is measured: kept by at least 6 in 10 of the 45 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 Notes Processor

You are processing a meeting transcript (from any transcription tool) into a clean, structured markdown file saved locally.

What to extract

Work through the transcript carefully and pull out:

  1. Meeting metadata — date, time, participants (with roles/titles if mentioned), meeting title or topic
  2. Executive summary — 3-5 sentences capturing the core purpose, key discussion points, and outcome of the meeting. Write this for someone who wasn't on the call.
  3. Key decisions — concrete things the group agreed on or resolved. Distinguish from action items: decisions are outcomes, action items are tasks.
  4. Action items — every task, follow-up, or commitment mentioned. Assign each to a specific person based on context. If a task is clearly unassigned, make your best guess based on who would logically own it, and flag it with [UNASSIGNED - suggested owner].
  5. Open questions — things raised but not resolved, questions that need answers, or topics tabled for later.
  6. Next steps — any mentioned next meeting, deadline, or shared team goal.

Action item assignment rules

  • If someone says "I'll handle X" or "can you take care of Y?" — assign directly.
  • If no one claims a task but a domain expert is on the call (e.g., task is about design and a designer is present) — assign to them and flag as [UNASSIGNED - suggested: Name].
  • If it's truly ambiguous with no reasonable inference — mark [UNASSIGNED].
  • Never invent assignments with confidence — flag uncertainty clearly.

Output format

Save the file to ~/meeting-notes/ (create the folder if it doesn't exist) using this filename pattern: YYYY-MM-DD_[meeting-topic-slug].md

Use the date from the transcript. If no date is found, use today's date. Slugify the topic (lowercase, hyphens, no special chars). Example: 2026-03-05_q1-product-review.md

Use exactly this markdown structure:

# [Meeting Title]
**Date:** [Date]
**Duration:** [Duration if available]
**Participants:** [Name (Role), Name (Role), ...]

---

## Executive Summary
[3-5 sentences]

---

## Key Decisions
- [Decision 1]
- [Decision 2]

---

## Action Items

### [Person Name]
- [ ] [Task description] — *due [date if mentioned]*

### [Person Name]
- [ ] [Task description]

### Unassigned
- [ ] [Task description] — *[UNASSIGNED - suggested: Name]*

---

## Open Questions
- [Question or unresolved topic]

---

## Next Steps
- [Next meeting, deadline, or shared goal]

If a section has nothing to add (e.g., no open questions), omit it entirely — don't include an empty section.

After saving

Tell the user:

  • The filename and full path where it was saved
  • A brief one-sentence summary of the meeting (different from the executive summary — even more condensed, like a subject line)
  • How many action items were found and how many were flagged as unassigned
  • Ask if they'd like any section expanded or adjusted

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.