agentleFS
Sign inStart free
link7373link7373/agentic-pmo/.claude/skills/setup-pmo/SKILL.md

setup-pmo

Skill1 starsChanged 3 months agoMITView on GitHub

Initialize the Agentic PMO from the START-HERE.md charter. Reads the user's answers, validates them, confirms process conventions, optionally tests tool integrations, and seeds the knowledge/ memory files. Run this first, and re-run after editing START-HERE.md.

The file

We split this skill into the rules it gives an agent

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

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈3

    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:

    Clarify gaps: Ask only about gaps that block setup (e.g., target customer, methodology, top goal).

    line 15
  2. Distinctive:

    (Optional) Test integrations: If the user wants tool sync and a connector is available, verify access.

    line 39
  3. Distinctive:

    If not configured, confirm the PMO runs file-only (the default) and move on.

    line 40
  4. Very specific:

    Follow standards/document-standards.md for all seeded files.

    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

/setup-pmo — Stand up the PMO

The bootstrap workflow. Turns the filled-in START-HERE.md charter into a working, seeded PMO.

When to use

  • First time setting up the PMO, or after the user edits START-HERE.md.

Steps

  1. Read the charter. Parse all 9 sections of START-HERE.md. Note blanks and "no idea" answers.
  2. Clarify gaps. Ask only about gaps that block setup (e.g., target customer, methodology, top goal). For everything else, apply sensible defaults and record them as assumptions.
  3. Confirm process conventions. Reconcile the charter's process/cadence answers with standards/agile-standards.md defaults (sprint length, ceremonies, estimation scale). Confirm or adjust.
  4. Seed the knowledge base. Populate from the charter:
    • knowledge/product-context.md — product, stage, vision, users, market, goals/OKRs, north star.
    • knowledge/stakeholder-map.md — stakeholders, decision-makers, RACI skeleton.
    • knowledge/cadence.md — methodology, sprint length, ceremonies, calendar, teams.
    • knowledge/glossary.md — seed from the charter's terminology/acronyms (section 8).
    • knowledge/operating-rhythm.md — confirm/adjust the cadence to match the team's process answers.
    • knowledge/roadmap.md, knowledge/backlog.md, knowledge/raid-log.md, knowledge/intake.md — initialize empty with headers.
    • knowledge/governance.md — record gate/steerco cadence, escalation matrix, and risk appetite from the charter's section 9 (apply defaults and mark them as assumptions if blank).
    • knowledge/financials.md, knowledge/resources.md — seed budget/funding and team/roles answers from section 9; leave the registers empty if unknown.
    • knowledge/change-log.md, knowledge/lessons-learned.md, knowledge/metrics.md — initialize empty with headers.
    • knowledge/integrations.md — record any tools named and whether sync is desired (default: file-only).
    • knowledge/decision-log.md — log the setup decisions and assumptions made.
    • Verify the artifact output directories exist (each ships with a README): knowledge/prds/, knowledge/sprints/, knowledge/projects/, knowledge/launches/, knowledge/ceremonies/, knowledge/portfolio/, knowledge/discovery/, knowledge/status/, knowledge/capacity/, knowledge/deliverables/, knowledge/programs/, knowledge/financials/.
  5. (Optional) Test integrations. If the user wants tool sync and a connector is available, verify access. If not configured, confirm the PMO runs file-only (the default) and move on.
  6. Report readiness. Summarize what was seeded, which assumptions you made, and the next actions the user can take (e.g., /define-strategy, /run-discovery, /build-roadmap). Point to knowledge/operating-rhythm.md so they know the ongoing cadence, and to examples/ for the quality bar.

Methods & standards

  • Apply knowledge/methods/product-strategy.md to structure goals/OKRs in product-context.
  • Follow standards/document-standards.md for all seeded files.

Output

Seeded knowledge/* files and a readiness summary.

Created by Colin Beck<br> LinkedIn: https://www.linkedin.com/in/beckcolin/<br> GitHub: https://github.com/link7373

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