agentleFS
Sign inStart free
QuixiAIQuixiAI/agi-memory/skills/installed/meeting-follow-up/SKILL.md

meeting-follow-up

Skill617 starsChanged 10 months agoMITView on GitHub

Turn completed meetings into an accurate recap, owned actions, and user-approved follow-up drafts

We split this skill into the rules it gives an agent

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

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈5

    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:

    Identify the meeting: Use the user's wording and calendar details to confirm the event, date, and attendees.

    line 18
  2. Distinctive:

    Choose the source: Prefer notes or a transcript supplied by the user.

    line 19
  3. Very specific:

    Check context: Use recall and relevant email threads to identify earlier promises or conflicts.

    line 21
  4. Distinctive:

    Do not mark a suggestion as a decision, a discussion point as a commitment, or an attendee as an owner without evidence.

    line 29
  5. Distinctive:

    Do not ingest a transcript merely because a likely recording exists.

    line 30
  6. Distinctive:

    When no notes or transcript are available, ask the user for notes or offer a recap template.

    line 31

≈ “Common” is an estimate: at least 1 in 5 of the 308,232 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 Follow-up

Convert evidence from a completed meeting into a concise record and a controlled set of next actions. Use meeting-prep for work before a meeting.

Workflow

  1. Identify the meeting. Use the user's wording and calendar details to confirm the event, date, and attendees. If the match is ambiguous, show likely events instead of choosing silently.
  2. Choose the source. Prefer notes or a transcript supplied by the user. If Fathom is available, list likely recordings and let the user identify the right one before ingesting it. Calendar metadata alone is not evidence of what was discussed.
  3. Extract outcomes. Separate decisions, commitments, action items, owners, due dates, open questions, and topics explicitly deferred. Quote sparingly and preserve uncertainty.
  4. Check context. Use recall and relevant email threads to identify earlier promises or conflicts. Label these as prior context rather than meeting outcomes.
  5. Draft the package. Produce a scannable recap, an owner-by-owner action list, and any requested follow-up email draft. Flag every missing owner or date rather than inventing one.
  6. Confirm mutations. Show proposed memory, backlog, Todoist, or Asana entries before creating them unless the user's request already specified their exact content and destination. Show every outbound message and recipient before sending.
  7. Report completion. Return what was recorded, created, or sent, including anything that failed and the exact retry or manual step.

Control and Failure Boundaries

  • "Follow up" authorizes analysis and drafting, not sending mail, assigning another person, or creating external tasks without confirmation.
  • Do not mark a suggestion as a decision, a discussion point as a commitment, or an attendee as an owner without evidence.
  • Do not ingest a transcript merely because a likely recording exists; ingestion changes local memory and requires a deliberate choice.
  • When no notes or transcript are available, ask the user for notes or offer a recap template. Never manufacture minutes from the calendar title.

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.

Check your setup, free