agentleFS
Sign inStart free
Sach1ngSach1ng/PM-operating-OS/.agents/skills/pm-os-onboarding/SKILL.md

pm-os-onboarding

Skill3 starsChanged 22 days agoMITView on GitHub

Interactive setup for PM-Operating-System in Codex. Use when the user says onboard, PM-OS setup, set up PM-OS, or asks to configure this repo for Codex or dual-runtime.

The file

We split this skill into the rules it gives an agent

5 rules. About 0 are common, 3 are distinctive, and 2 are 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.

  • 2

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Ask in small batches: company + role.

    line 21
  2. Distinctive:

    After company + role, offer a short public-web research pass.

    line 22
  3. Very specific:

    Write config/pm-os-config.yaml with runtime.primary and runtime.codex_install_scope.

    line 23
  4. Distinctive:

    Run from repo root:

    line 25
  5. Distinctive:

    Keep the conversation short.

    line 31

≈ “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-OS Onboarding

Collect PM context, write config/pm-os-config.yaml, create a product dossier, run setup.

When to use

  • onboard
  • PM-OS setup
  • set up PM-OS
  • configure this repo

Workflow

  1. Confirm you will write config, copy knowledge/products/_template/ to a named product folder, and run ./scripts/setup.sh.
  2. Runtime: default codex. Offer both if they still use Cursor. Codex scope: repo or user.
  3. Ask in small batches: company + role; product name + type; manager/VIPs; goals + deprioritize; Slack/Drive/GitHub/Figma/Jira/browser; MCP now or skip.
  4. After company + role, offer a short public-web research pass. Skip unless they want it.
  5. Write config/pm-os-config.yaml with runtime.primary and runtime.codex_install_scope. Keep template booleans unless they opted out. Set skills.eval_brief: true.
  6. Copy knowledge/products/_template/ → knowledge/products/<slug>/ if that folder does not exist.
  7. Run from repo root:
    • Codex: ./scripts/setup.sh --runtime codex --codex-scope <repo|user>
    • Dual: ./scripts/setup.sh --runtime both --codex-scope <repo|user>
    • Cursor only if they asked: ./scripts/setup.sh --runtime cursor
  8. Next steps: fill brief.md, then evals.md if the product is AI; example at knowledge/products/harbor-copilot/; Codex context in PM-OS-AGENTS.md; MCP in .codex/config.toml. continual-learning is Cursor-first.

Keep the conversation short. Do not invent company facts. Do not depend on Cursor-only tools.

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