agentleFS
chacosoldierchacosoldier/compabob/.claude/skills/post-call/SKILL.md

post-call

Skill34 starsChanged 23 days agoMITView on GitHub

Capture a debrief right after a meeting or call: what was decided, what was committed, and what changed. Use for \"/post-call\", \"debrief the call with X\", or \"I just got off a call with Y\".

1 other project uses a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

4 rules. About 0 are common, 2 are distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 2

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Gather: Ask the user for the raw account of the call, or work from notes or a transcript they provide.

    line 12
  2. Very specific:

    Write or update the meeting note vault/Meetings/YYYY-MM-DD-<slug>.md.

    line 19
  3. Very specific:

    Update each attendee's vault/People/<Name>.md: append to ## Interactions, refresh their current focus.

    line 20
  4. Distinctive:

    Update the relevant project or pipeline note.

    line 21

≈ “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

Post-Call Debrief

Close the loop that /meeting-prep opens. Turn a finished conversation into durable vault state.

Steps

  1. Gather. Ask the user for the raw account of the call, or work from notes or a transcript they provide.
  2. Extract four things:
    • Decisions: what was actually decided.
    • Action items: who owes what, by when. Run these through the second-brain task intake gate so they do not duplicate existing tasks.
    • New information: anything that changes what the vault knows about a person, account, or project.
    • Follow-up: the next touchpoint, if any.
  3. Update the vault.
    • Write or update the meeting note vault/Meetings/YYYY-MM-DD-<slug>.md.
    • Update each attendee's vault/People/<Name>.md: append to ## Interactions, refresh their current focus.
    • Update the relevant project or pipeline note.
  4. Confirm the changes with the user before writing anything that overwrites existing content.

Output

A short summary first: the one decision or change that matters most. Then the meeting note content for review. Then the list of vault files that will be created or updated, for approval.

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.