How to Install the AI Product Manager Claude Plugin (Cowork & Code)

Don't want to install anything? You don't have to. The free web tools for AI product managers on The AI Career Lab give you the same pre-built workflows in your browser — five runs a day on a free account, no terminal, no install. Create a free account if you'd rather skip straight to the tools.

The AI Product Manager Claude plugin from The AI Career Lab is the fastest way to turn Claude into an AI-PM-aware co-worker. It bundles 4 pre-built slash commands and 2 auto-activating skills that already know what working AI PMs actually do — feature specs with negative acceptance criteria, pre-legal regulatory screens, staged rollouts with quantitative kill criteria, and user feedback synthesis that splits model issues from product issues.

The plugin works in both runtimes Claude offers:

• Claude Cowork — the chat product at claude.ai. The easiest path. No terminal, no install of anything else. Requires a paid Claude plan (Pro, Max, Team, or Enterprise) to access plugins.
• Claude Code — the terminal CLI for power users and developers. Requires Node.js + npm. Free or paid Claude account both work.

What this plugin gives you

A normal Claude session is a blank chat window. A plugin replaces that with slash commands — pre-built shortcuts that contain the structure, formatting rules, and AI-PM conventions for a specific task.

In this plugin you get:

• /ai-feature-spec — generates a structured spec with positive + negative acceptance criteria, offline + online eval plan, and risk register
• /regulatory-screen — runs a pre-legal directional screen against EU AI Act, GDPR, US state AI laws, and sector-specific guidance. Produces questions for legal counsel
• /rollout-plan — designs a 4-6 phase staged rollout with quantitative kill criteria and enforceable cohort exclusions
• /feedback-synthesis — clusters user feedback into themes and splits model-quality issues from product-design issues from expectation issues

Which runtime should you use?

Use Claude Cowork if:

• You already use claude.ai for chat work
• You prefer a graphical interface to a terminal
• You don't want to install anything else on your machine
• You have a paid Claude plan (Pro, Max, Team, or Enterprise)

Use Claude Code if:

• You're already comfortable in a terminal
• You want to script workflows alongside your codebase (e.g., scheduled feedback synthesis runs, eval automation)
• You're on a free Claude account (Claude Code plugin install does not require a paid plan)

Path A: Install in Claude Cowork (easiest, no command lines)

1. Open claude.ai in your browser and sign in.
2. Make sure you're on a paid plan (Pro, Max, Team, or Enterprise). The plugin marketplace is gated to paid plans.
3. Open the plugin settings and click Add marketplace.
4. In the modal, paste this into the URL field:

alexclowe/awesome-claude-cowork-plugins

5. Click Sync. Claude Cowork pulls the marketplace catalog from the public alexclowe/awesome-claude-cowork-plugins repo.
6. Browse the marketplace. Find the AI Product Manager plugin and click Install.

The commands and skills are now available in your Cowork chats.

Path B: Install in Claude Code (terminal CLI, two commands)

One-time Claude Code setup

1. Install Claude Code. Open a terminal and run:

npm install -g @anthropic-ai/claude-code

If you don't have npm, install Node.js first (download the LTS version, run the installer).

2. Sign in once. Run claude in your terminal and follow the sign-in flow.

Install the plugin

Inside Claude Code, run these two commands:

/plugin marketplace add alexclowe/awesome-claude-cowork-plugins
/plugin install product-manager-ai@awesome-claude-cowork-plugins

To verify, type /help and you should see the new commands listed alongside Claude Code's built-ins.

Your first command

After install, the most useful command to try first depends on what you're working on. For most AI PMs, the highest-leverage starting point is the spec command:

/ai-feature-spec

When you run it, Claude asks for your feature brief, model type, user surface, data inputs, and risk tolerance. The output is a structured spec with positive and negative acceptance criteria, an eval plan covering offline and online evaluation, and a risk register addressing hallucination, prompt injection, data leakage, and regulatory category.

The spec is the artifact you send to engineering. The eval plan is what your team builds out in Braintrust, LangSmith, or your eval platform of choice. The risk register is what you bring to security and legal.

First 4 workflows to try after install

1. AI feature spec — /ai-feature-spec in the plugin, or /tools/product-manager-ai-feature-spec on the web. Run this for any new AI feature in early design
2. Pre-legal regulatory screen — /regulatory-screen in the plugin, or /tools/product-manager-ai-regulatory-screen on the web. Run this before the legal intake meeting
3. Staged rollout plan — /rollout-plan in the plugin, or /tools/product-manager-ai-rollout-plan on the web. Run this before launch sign-off
4. Feedback synthesis — /feedback-synthesis in the plugin, or /tools/product-manager-ai-feedback-synthesis on the web. Run this 2-3 weeks post-launch

Skills you get for free

This plugin also includes Claude Skills that activate automatically when you're working on relevant tasks:

• Negative Acceptance Discipline — when you're drafting any AI feature spec, prompts you for the behavior the model must NOT exhibit, not just positive acceptance criteria
• Pre-Legal Framing — when regulatory questions come up, automatically frames the output as "directional, not legal advice" with explicit "consult counsel" framing throughout

The first time the pre-legal framing skill auto-activates and refuses to give you a confident "yes this is EU AI Act compliant" judgment, you'll see the difference between using Claude generically and using Claude as an AI PM's co-worker.

Where to go from here

• Claude Cowork playbook for AI PMs — the full setup guide with the prompt structures behind the slash commands
• Free web tools for AI PMs — same workflows, browser-based, no install required
• Best AI Tools for AI Product Managers in 2026 — the broader landscape including Claude, eval platforms (Braintrust, LangSmith), and product analytics
• AI for AI Product Managers guide — the working playbook for the role

Common issues

I don't see the "Add marketplace" option in Claude Cowork. You need to be on a paid plan. If you're on a free plan, install via Claude Code instead — it's free.

The marketplace sync failed in Claude Cowork. Double-check the URL field has exactly alexclowe/awesome-claude-cowork-plugins — a GitHub owner/repo format, no https://, no trailing slash.

The slash commands aren't showing up after install. Start a new chat (Cowork) or type /help (Claude Code). If you see the built-in commands but not the new ones, the install didn't complete — re-run the install.

I want to use this without installing anything. Use the free web tools instead. Same workflows, browser-based, no install or paid plan.

Ready to try it without installing

Create your free AI Career Lab account and try the AI PM tools today. No credit card required.

---

This article is general guidance for AI product managers. Regulatory frameworks (EU AI Act, GDPR, US state AI laws including the Colorado AI Act and NYC AEDT, sector-specific obligations such as FDA SaMD and EEOC AI guidance) are evolving and jurisdiction-specific. The Regulatory Risk Screen tool is a pre-legal directional screen, not legal advice. Consult your legal counsel for any specific applicability question.