PM Jarvis
AI-powered copilot for Product Managers built for Claude Code. Clone the repo, fill out your context, and let it learn your company, team, and writing style.
Philosophy
Context over prompting
PM Jarvis organizes your company knowledge, writing styles, stakeholder profiles, and past decisions so every output sounds like it came from someone who actually works there.
Workflows, not chat
Instead of typing open-ended questions, you run purpose-built commands that cover the full product management lifecycle. From strategy and research to PRDs, metrics, meetings, launches, knowledge management, code, and retrospectives. 73 commands, all connected.
Ship the draft, then iterate
A one-page PRD that ships Monday beats a ten-page spec that ships never. Every document is a living artifact you refine over time, not a one-shot deliverable.
What you get
Pre-built context library
Templates for company info, writing styles, stakeholder profiles, and strategic frameworks (7 Powers, JTBD, PLG Iceberg, Growth Loops, and more)
73 slash commands
One command per recurring PM task — PRDs, meeting notes, pricing analysis, code reviews, and a compounding second-brain wiki
7 sub-agents
Multi-perspective reviews from engineer, designer, executive, legal, UX researcher, skeptic, and customer voice
Knowledge assets
63 curated interview questions, validated survey templates, canvas templates, and 139 AI prompt references
Persistent memory
File-based memory system with hooks that inject context every session — your copilot remembers what happened last time
How it works
PM Jarvis runs with Claude Code, an agentic AI code assistant that can read and write files on your computer. Unlike a chatbot, it has access to your entire project folder so it can reference your company info, past PRDs, stakeholder profiles, and writing style in every single conversation.
The system is built on three layers:
Project knowledge
Company info, writing styles, stakeholder profiles, strategy frameworks, and past decisions — all stored as simple text files in your context library.
Skills
73 registered slash commands for recurring tasks. Each one knows which context files to pull from, how to format the output, and what skill to offer next.
Sub-agents
7 specialized reviewer personas (engineer, designer, executive, legal, UX researcher, skeptic, customer voice) that review your work and catch blind spots.
Two global protocols tie everything together: Context Acquisition (read freely from your context library before producing output) and Knowledge Capture (propose write-backs to the right location, never auto-write). A persistent memory system remembers key facts across sessions via a lightweight hook.
How is it different from plain ChatGPT or Claude?
| Regular AI tools | PM Jarvis |
|---|---|
| Forgets your company context | Always knows your business, team, and stakeholders |
| Generic output | Matches your writing style automatically |
| One-shot responses | Evolves PRDs through multiple stages |
| Single perspective | Multi-agent reviews from 7 perspectives |
| No tool integration | Connects to your analytics, PM tools, and more via MCPs |
Example workflows
Commands chain together into workflows. Here are a few common ones:
Daily planning
Strategic Planning
Pre-Launch Risk
Design-Led Prototyping
Design Audit & Improve
Second Brain (compounding knowledge)
Build with AI (for PMs who code)
New Feature Research
All 73 commands
Every command is a single action you can run inside Claude Code. Click a category to browse, then expand any command to see its full instructions and copy it to your clipboard.