agentleFS
lexvalolexvalo/riverscript-claude-plugin/skills/meeting-followup/SKILL.md

meeting-followup

Skill0 starsChanged 42 days agoMITView on GitHub

Turn a recorded meeting or call into decisions, owners, deadlines and the message that goes out afterwards. Use when the user asks for minutes, action items, a recap, a follow-up email, or what they committed to on a call.

8 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use meeting-prep and research.

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.
  • OpenAISkill

    meeting-prep

    Use when creating Public Equity Investing meeting prep briefs. Do not use for private diligence, IB, FP&A, legal, or scheduling-only tasks.

    Also in 3 projects that use this

  • NVIDIASkill

    research

    Before designing a feature, research how comparable libraries solve the problem, check best practices, known pitfalls, and upstream changes. Use when starting a new feature, investigating an unfamiliar area, or the user asks to research something.

    Also in 3 projects that use this

The file

We split this skill into the rules it gives an agent

4 rules. 0 are common, 3 are distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 6 edited versions we read keep these.

  • 3

    Distinctive

    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. Very specific:

    Check get_transcript_summary first.

    line 9
  2. Distinctive:

    Write the follow-up in the register of the meeting.

    line 14
  3. Distinctive:

    Never invent an owner or a deadline that nobody said.

    line 16
  4. Distinctive:

    If the user wants the message sent, hand them the draft.

    line 18

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

The work after a meeting is always the same: what was decided, who owes what, and the message that goes out.

  1. Find the meeting. If the user named it, use list_transcripts and match on the title and date. If they described it instead, search_transcripts on a phrase that would have been said in it.
  2. Check get_transcript_summary first. When RiverScript already generated a summary, it saves reading the whole thing. When it returns nothing, that is normal: fetch the text with get_transcript.
  3. Pull out, in this order, and only what the transcript actually supports:
    • decisions, each with the reasoning if it was given
    • actions, each with an owner and a date when one was named, and plainly marked as unassigned when not
    • open questions that were raised and left unanswered
  4. Write the follow-up in the register of the meeting. A team call gets a short message. A client call gets a formal recap. Lead with the decisions, keep the actions as a list, and put open questions last.

Never invent an owner or a deadline that nobody said. "No owner was named" is a useful line in a recap; a guessed name is a problem the user discovers in a week.

If the user wants the message sent, hand them the draft. Sending is theirs.

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.