No phase ownership
The same model validates problems, writes acceptance criteria, and signs off on launch. Corners get cut where nobody is watching.
Agent skill for product management
Generic AI gives you answers. PM Butler gives you a household staff: eight specialists who challenge assumptions, flag scope creep, and write the documentation you keep putting off.
Works with Cursor, Claude Code, Copilot, and any harness that accepts skills.
The problem
Forty-seven tabs. Twelve half-finished ideas. Zero decision log. Discovery, scope, architecture, QA, and launch need different instincts. Without a shared vocabulary, agents guess and decisions vanish into chat history.
The same model validates problems, writes acceptance criteria, and signs off on launch. Corners get cut where nobody is watching.
Two hundred messages later, nobody can answer why you built it that way. Post-mortems become archaeology.
Real teams argue about speed vs. quality. A single agreeable assistant lets scope creep and untested launches slide.
The ensemble
Each member owns an SDLC phase, speaks in a distinct voice, and flags concerns at three severity levels: Watch, Concern, Blocker.
Sample output
Structured output you can paste into your repo, not chat filler.
Ready to drop in
Run /pm-butler init once. The skill reads your stack, team size, and constraints before any persona speaks.
Project Edition maintains eleven markdown files as you work: decisions, scope, risks, changelog, and more. You do not stop to document; the staff does it while helping you ship.
Every persona watches for drift. Sculptor tracks scope creep as a percentage. Gatekeeper escalates when blockers pile up. Orange concerns are not optional.
Oracle validates the problem. Sculptor locks requirements. Architect designs the system. Alchemist protects the sprint. Gatekeeper signs off. Shipper launches. Librarian records what actually happened.
Shipper and Gatekeeper will disagree. That tension is a feature. The ensemble produces better outcomes than one voice saying yes to everything.
Choose your path
Install the skill from GitHub at no cost. Buy on Gumroad if you want the full markdown files, PDF guides, and extras without a harness.
The Ensemble
Free on GitHub
Phase coverage, team dynamics, coach and review modes, and structured output you can paste into Jira, Notion, or your repo.
Project Edition
Free on GitHub
Seven specialists maintain eleven living markdown files. Every interaction produces the answer, the doc update, and any concerns.
Complete Household
Gumroad bundle
Full SDLC coverage plus automatic documentation. Everything in both editions, persona cards, and quick-reference PDF.
The language
Each maps to one persona or workflow. Pick any to see what it does.
Create PROJECT.md with stack, team, constraints, and current SDLC phase.
Get started
Works today via GitHub and Claude Code. npm installer coming soon.
Add the marketplace, install the plugin, then run init.
/plugin marketplace add tedrubin80/pmbutler
Initialize project context inside your agent session.
/pm-butler init
Or clone the skill folder from GitHub into .cursor/skills/pm-butler/ today.
npx pm-butler skills install
After install, run /pm-butler route to see which persona owns your current phase. Source: github.com/tedrubin80/pmbutler. Raw markdown packs: Gumroad.
About
I build agent skills, prompt packs, and systems for people who think fast and document slow. PM Butler is a household of eight AI personas that cover discovery through launch: they challenge scope creep, flag risks, and write the docs you keep skipping.
Flexible enough for real projects. Structured enough to ship. Generic AI gives answers. PM Butler gives you a staff.
Also on Gumroad
PDF prompt guides for teams and developers. Sold alongside PM Butler on Gumroad.
Chaos-to-Clarity and Document Decoder guides for teams new to AI-assisted work.
Code Review Partner and Codebase Onboarding Assistant for engineering workflows.
AI Project Team and project strategy guides for PMs running cross-functional initiatives.