Skip to main content
skill CX Codex

claude-pm-skills — Claude Code skill: what it does, how to install

claude-pm-skills — a set of 15 skills for product decisions, from problem clarity to launch review and post-launch learning. Use it when choosing what to build matters.

MIT 202 installs ★ 35 updated 2026-10-21

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓
npx skills add podo/design-agent-skills --skill claude-pm-skills -a claude-code
Open on GitHub

What claude-pm-skills does

claude-pm-skills breaks product decisions into focused steps. The set covers problem clarity, outcome definition, assumption mapping, JTBD extraction, prioritization, trade-offs, roadmap checks, experiment design, and adoption analysis. Other skills review PRDs, stakeholder alignment, launch readiness, retention drops, and post-launch learning.

The package installs 15 separate skills. Each one is short and opinionated, with a purpose, usage guidance, a few steps, a fixed response structure, and a final verdict or recommendation. They can be picked up from ordinary product questions or called by skill name. This keeps the prompts compact, but gives them less depth than larger PM suites.

experiment-design conflicts with the skill of the same name from assimovt-productskills; installing both overwrites the earlier version. The package is released under the MIT license.

What it helps with

  • clarify which user problem deserves attention
  • define the outcome a product change should create
  • rank features by value versus effort
  • design an experiment for a product assumption
  • check whether a launch is ready

Example prompts for the agent

  • Help me decide whether this user problem is worth solving and separate assumptions from evidence.
  • Compare these features by value and effort, then recommend an order.
  • Review launch readiness and list the risks that still need attention.

How to install claude-pm-skills

1Skills CLI (Vercel)

npx skills add podo/design-agent-skills --skill claude-pm-skills -a claude-code

2Manually: put the files in place

~/.claude/skills/claude-pm-skills/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/claude-pm-skills/

Step by step, with commands for each platform: How to install skills in Claude Code: five ways

Questions about claude-pm-skills

How do I install claude-pm-skills in Claude Code?

Run npx skills add podo/design-agent-skills --skill claude-pm-skills -a claude-code, then check ~/.claude/skills/claude-pm-skills/SKILL.md.

What does claude-pm-skills do?

It provides product decision skills for clarifying problems, defining outcomes, testing assumptions, prioritizing work, planning experiments, and reviewing launches. The package contains 15 short skills.

Does claude-pm-skills conflict with another skill?

Its experiment-design skill has the same name as one from assimovt-productskills. Installing both causes one version to overwrite the earlier one.

Source text

SKILL.md · MIT
---
name: claude-pm-skills
description: |
  Product-management decision skills for solo founders and startup PMs: problem
  clarity, outcome definition, assumption mapping, prioritization, experiment design,
  PRD critique, launch readiness, and post-launch learning. Focused on deciding
  what is worth building rather than writing documents faster.
triggers:
  - "claude PM skills"
  - "pratikshadake PM"
  - "product management skill"
  - "product thinking"
das:
  category: product-pm
  upstream: "https://github.com/pratikshadake/claude-product-management-skills"
  version: latest
  install: false
---

# claude-pm-skills

> Catalogue stub — full package: [pratikshadake/claude-product-management-skills](https://github.com/pratikshadake/claude-product-management-skills)

<!-- das:install:start — generated from stub.yaml by `npm run generate`; edit stub.yaml, not this block -->
## Decision tree

1. **Is the full skill already installed?**
   This package installs 15 skills (`problem-clarity`, `outcome-definition`, `assumption-mapper`, `jtbd-extractor`, `value-vs-effort`, `user-segment-prioritizer`, `tradeoff-articulator`, `roadmap-reality-checker`, `experiment-design`, `feature-adoption-analyzer`, `retention-drop-diagnoser`, `prd-critic`, `stakeholder-alignment-checker`, `launch-readiness`, `post-launch-learning`); checking the first.
   - Global: `f=~/.agents/skills/problem-clarity/SKILL.md; [ -f "$f" ] && ! grep -q "^das:" "$f" && echo "installed" || echo "pointer"`
   - Project: `f=.agents/skills/problem-clarity/SKILL.md; [ -f "$f" ] && ! grep -q "^das:" "$f" && echo "installed" || echo "pointer"`
   - `installed` → the skill is installed as `problem-clarity`, invoke it and proceed
   - `pointer` → go to step 2

2. **Detect scope, then install:**

   ```bash
   [ -e ~/.agents/skills/claude-pm-skills ] && echo "global" || echo "project"
   ```

   **Global:**
   ```bash
   npx skills add pratikshadake/claude-product-management-skills --skill problem-clarity outcome-definition assumption-mapper jtbd-extractor value-vs-effort user-segment-prioritizer tradeoff-articulator roadmap-reality-checker experiment-design feature-adoption-analyzer retention-drop-diagnoser prd-critic stakeholder-alignment-checker launch-readiness post-launch-learning -g -y
   ```

   **Project:**
   ```bash
   npx skills add pratikshadake/claude-product-management-skills --skill problem-clarity outcome-definition assumption-mapper jtbd-extractor value-vs-effort user-segment-prioritizer tradeoff-articulator roadmap-reality-checker experiment-design feature-adoption-analyzer retention-drop-diagnoser prd-critic stakeholder-alignment-checker launch-readiness post-launch-learning -y
   ```
   > **Claude Code:** send a command as a chat message starting with `!` to run it without leaving the conversation.

**Heads-up**

- **License:** MIT
- **Name collision:** `experiment-design` is also written by `assimovt-productskills` (its install or its catalogue pointer); installing both overwrites the earlier one.
<!-- das:install:end -->

## Invoke after install

Each skill installs under its own name and is picked up automatically from a normal product question ("Is this problem worth solving?", "Which feature first?", "Why is retention dropping?"), or call it explicitly:

- Problem discovery: `problem-clarity`, `outcome-definition`, `assumption-mapper`, `jtbd-extractor`
- Prioritization and strategy: `value-vs-effort`, `user-segment-prioritizer`, `tradeoff-articulator`, `roadmap-reality-checker`
- Validation and learning: `experiment-design`, `feature-adoption-analyzer`, `retention-drop-diagnoser`
- Delivery and launch: `prd-critic`, `stakeholder-alignment-checker`, `launch-readiness`, `post-launch-learning`

## What it does

A set of short, opinionated product-management skills by pratikshadake. Each one is a compact decision prompt (purpose, when to use, a few steps, a fixed output template ending in a verdict or recommendation, and a worked example) rather than a long methodology. The package is aimed at solo founders and startup PMs who want help deciding what to build and whether it worked. The skills are small, so they cost little context but also carry far less depth than the larger PM suites.

## When NOT to use

- Deep frameworks and templates (journey maps, opportunity-solution trees, story mapping, PRD process) → use `deanpeters-pm-skills`
- Full Triple Diamond methodology → use `pm-skills`
- UX research and journey mapping → use `phuryn-pm-skills`
- Marketing and CRO tasks → use `coreyhaines-marketing`

© podo · MIT · podo/design-agent-skills

Similar skills

All skills for Agent setup: memory, context, orchestration →

From the same set108

The whole set →
cc-slidev cc-slidev — a skill for conference and developer talks built on Slidev: hard limits on slide layout, and a path from outline to export. CX Codex +1 202installs lenny-skills Product management frameworks and checklists from Lenny Rachitsky's podcast archive. Helps teams draft PRDs, refine onboarding, and design AI-native UX. CX Codex +1 202installs software-mansion-skills Eleven React Native and Expo skills from the Software Mansion team: Reanimated patterns, gesture handling, faster native builds, Radon IDE debugging, Pulsar haptics, Detour links. CX Codex +1 202installs marp-slide-quality marp-slide-quality evaluates Marp Markdown presentations via SlideGauge scoring, detecting layout, accessibility, and density issues directly in source files. CX Codex +1 202installs excalidraw-agents365 excalidraw-agents365 turns a plain description of a system or a flow into an .excalidraw file, then exports it to SVG or PNG. CX Codex +1 202installs webgpu-claude-skill Gives the agent working knowledge of Three.js on WebGPU: TSL node materials, compute shaders, post-processing, WGSL. Useful when a scene needs GPU compute. CX Codex +1 202installs softaworks-agent-toolkit softaworks-agent-toolkit — a set of seven skills for diagrams, Marp slides, database schemas, and design systems. Add it when an agent needs these design and documentation tasks. CX Codex +1 202installs markdown-viewer-skills markdown-viewer-skills — a router skill for diagrams written as Markdown text: PlantUML for UML and networks, Vega-Lite and ECharts for charts, HTML/CSS for infographics and cards. Useful when docs need figures. CX Codex +1 202installs

Project sponsors

Companies that keep this analytics open