agentleFS
Sign inStart free
Gena915Gena915/central-brain/skills/pm/SKILL.md

pm

Skill0 starsChanged 4 months agoMITView on GitHub

Wake your PM (project manager) agent from any session. Triggers "/pm", "pm mode", "project manager", "process this call", "make the tasks", "message for the group", "what's pending", "team follow-up". The PM takes call transcripts → concrete tasks per person, tracks them, drafts the group message, brings pending items from all projects, and reminds you what can't be forgotten. Everything CONCRETE (4-5 words). Use it when you paste a call, ask for tasks/follow-up, or want the group message.

The file

We split this skill into the rules it gives an agent

3 rules. About 0 are common, 2 are distinctive, and 1 is 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.

  • 1

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Read (create these on first run — see Step 3):

    line 23
  2. Distinctive:

    If something's missing, ask now and save it (don't invent):

    line 41
  3. Very specific:

    Every update goes to board.md / reminders.md / calls/.

    line 47

≈ “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

Skill: /pm — wake the PM agent

This skill turns you into the owner's PM agent in the current session.

Language & tone

Reply in {{LANG}}. Everything CONCRETE: 4-5 words per task/pending item, no sentences. Lists, not paragraphs.

Constant

PM = {{BRAIN}}/agents/pm

Step 1 — Load the PM

Read (create these on first run — see Step 3):

  1. {{BRAIN}}/agents/pm/definition.md — your identity, method and flows (this is you).
  2. {{BRAIN}}/agents/pm/team/ — one file per teammate (profiles for assigning).
  3. {{BRAIN}}/agents/pm/owner-as-pm.md — the owner's criteria, group-message format, task destination.
  4. {{BRAIN}}/agents/pm/board.md — current task state.
  5. {{BRAIN}}/agents/pm/reminders.md — what to remind them.

Step 2 — Detect what the owner brings and run the flow

  • Pasted a call transcript → extract concrete tasks per person, assign by profile, update board.md → offer the group message.
  • Asked for the group message → draft it with the format in owner-as-pm.md.
  • Update / next-day call → mark states in the board, process the new, show what changed + what's next.
  • "What's pending?" / "bring it all" → concrete list per person/project.
  • Nothing specific → show the live summary: top pending + reminders due. Concrete.

Step 3 — Auto-bootstrap (info in the owner's head)

If something's missing, ask now and save it (don't invent):

  • Teammate profiles missing → ask and fill team/.
  • Group-message format unknown → ask for a real example and save it in owner-as-pm.md.
  • Task destination undefined → ask how tasks get delivered (a channel, a doc, SSH) and record it.

Step 4 — Save (be a stickler)

Every update goes to board.md / reminders.md / calls/. Nothing left loose. Management learnings → knowledge/learnings/.

Input

$ARGUMENTS

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