agentleFS
ridwankustantoridwankustanto/mandor/.claude/skills/pm-status/SKILL.md

pm-status

Skill2 starsChanged 40 days agoMITView on GitHub

Answer "where are we at" from project.db in a few lines, and say what the next action is. Use when the user says "/pm-status", "where are we", "what's the state", "what should I do next", or at the start of a session on an existing project.

2 other projects use a version of this.

Adopted by

Most recently taken up by

  • Other versions2 projects use a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 2

    1. hunterg325/claude-code-pm★ 2same name
    2. pinkroosterai/PinkRoosterMcp★ 2same name

    How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.

  • In this repository12 other files it gives its agents.

The file

We split this skill into the rules it gives an agent

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

  • 2

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Read state, never guess it.

    line 8
  2. Very specific:

    Ask with AskUserQuestion rather than inferring.

    line 39
  3. Very specific:

    Run this before anything else, then read only the docs relevant to what the user is asking about.

    line 44

≈ “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

/pm-status: where are we, and what is next

Read state, never guess it. Run these three, in order:

./pm status
./pm tree
./pm gate list
./pm check

Then answer in this shape, five lines or fewer:

  1. Phase, and whether its gate is clear or open
  2. Milestone burn, tasks done over total for the active milestone
  3. What is blocked, and by what
  4. What check found, if anything
  5. The single next action, named as a command

When check fails

Say which invariant broke and what fixes it. Do not offer to work around it.

  • Work item with no parent: it belongs to nothing, re-parent it or cut it
  • Epic in no milestone: it has no target, so nobody knows when it matters
  • Epic with no stories: nobody broke it down
  • Parent closed above an open child: the board is lying, reopen the parent
  • Story verified with no passing test naming it: the claim is not earned
  • Stale screen: a change invalidated its approval, it needs a design pass
  • Open gate on the current phase: name the gate, name who approves it

When the user asks something the tables cannot answer

Ask with AskUserQuestion rather than inferring. Status is the one place where a confident wrong answer costs the most, because everything downstream is planned on it.

Session start on an existing project

Run this before anything else, then read only the docs relevant to what the user is asking about. Do not bulk load docs/. The database tells you where things stand, the docs tell you why, and you only need the why for the part you are touching.

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.