agentleFS
Sign inStart free
Industrial-AI-Research-LabIndustrial-AI-Research-Lab/nir-agent-overlay/skills/meeting-record/SKILL.md

meeting-record

Skill0 starsChanged 45 days agoMITView on GitHub

Turn a meeting transcript into a meeting record in docs/meetings/ (clean the transcript, sanitize it, extract decisions with time codes and actions, check the result). Use when the student says "сделай запись встречи", "оформи протокол", "make the meeting record".

The file

We split this skill into the rules it gives an agent

1 rule. About 0 are common, 1 is distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    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:

    Commit only the record. A transcript is committed only after step 2 and only if the student asks for it.

    line 26

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 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-record

Work only from the transcript the student gives you; add no knowledge of your own. Every decision carries a time code and the speaker.

  1. Clean. Fix recognition errors in the project terms the student lists. Do not change the meaning, shorten or add lines; mark unclear passages as [unclear, MM:SS].
  2. Sanitize. Replace the names of everyone except the student and the supervisor with roles in square brackets, one label per person throughout. Remove passwords, keys, tokens, internal addresses, partner data, grades and personal topics. Give the student the table "original name → label" separately; it is never committed.
  3. Extract. Quote verbatim the lines where a decision was taken or an action was set, with time code and speaker. Then fill docs/meetings/YYYY-MM-DD.md from 0000-template.md: decisions with time codes; actions with owner, due date and issue number; open questions. Owner or date not named: write "not stated". Unsure whether it was a decision: mark [check].
  4. Board. List the agreed actions as JSON with title, owner, deadline, timecode, only those both sides agreed to; offer to open each one with the experiment-issue skill or gh issue create --project.
  5. Check. Compare the record with the transcript: omitted or invented decisions, a wrong speaker, wrong numbers or dates. Give a time code per error and fix only those. When in doubt, run the check twice and compare the answers.
  6. Commit only the record. A transcript is committed only after step 2 and only if the student asks for it.

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