By Mehdibargach
Automate end-to-end product management workflows for discovery (personas, market sizing, competitor scans), build (PRDs, user stories, roadmaps, prioritization), measure (A/B tests, feedback/metrics analysis), and communicate (stakeholder updates, release notes, decision docs) using 20 specialized Claude Code skills that output structured Markdown files, tables, and Python/Bash analyses.
Design a complete A/B test or experiment from a hypothesis. Takes what you want to test and outputs a full experiment design with hypothesis, metrics, sample size, duration, and success criteria.
Quick competitive landscape scan for any product or market. Takes a product/market description and returns a competitive map with positioning, gaps, and opportunities.
Structure a product decision with options, trade-offs, and a clear recommendation. Takes a decision to make and outputs a concise decision document ready for stakeholder review.
Classify and analyze raw user feedback into themes, sentiment, and actionable insights. Takes pasted feedback text or a path to a CSV file and returns structured patterns and recommendations.
Generate a complete go-to-market checklist from a product description. Everything you need to launch.
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
20 production-ready skills for Product Managers using Claude Code.
No fluff. No generic prompts. Real PM workflows you can run with a /command.
| Skill | What it does |
|---|---|
/product-teardown | Analyze any product: business model, UX decisions, growth loops, moat |
/competitor-scan | Competitive landscape scan with positioning map and white space analysis |
/user-interview-prep | Research brief with hypotheses, interview guide, and Mom Test-compliant questions |
/feedback-analyzer | Classify raw feedback (CSV or text) by theme, sentiment, urgency + patterns |
/market-sizing | TAM/SAM/SOM estimation with top-down + bottom-up methodology |
/persona | Behavioral user personas that drive product decisions — not marketing fluff |
| Skill | What it does |
|---|---|
/prd | Concise PRD (1-2 pages max) that forces clarity on problem, users, scope, metrics |
/user-stories | Feature → user stories with acceptance criteria, edge cases, dependencies |
/technical-translator | Translate eng docs (API specs, RFCs) into PM-actionable language |
/release-notes | Git commits or tickets → user-facing release notes. B2B, B2C, or internal tone |
/launch-checklist | Product-specific go-to-market checklist with timing and owners |
/roadmap | Priorities → structured Now/Next/Later roadmap with themes, dependencies, trade-offs |
| Skill | What it does |
|---|---|
/ab-test-design | Full experiment design: hypothesis, metrics, sample size, guardrails, success criteria |
/metrics-analyzer | Analyze CSV data — trends, anomalies, segments, insights in plain English |
/prioritize | Score features with RICE, ICE, or custom framework. Ranked table + rationale |
/decision-doc | Structured decision: options, trade-offs, recommendation, reversibility |
/okr-writer | Business goals → OKRs with measurable Key Results and anti-goals |
| Skill | What it does |
|---|---|
/stakeholder-update | Raw notes → polished update (email, Slack, or deck bullets) |
/meeting-prep | 1-page brief: context, objectives, key questions, decisions expected |
/retro-facilitator | Run or synthesize a retro (4Ls, Start/Stop/Continue, Sailboat) |
# Clone the repo
git clone https://github.com/Mehdibargach/claude-code-pm-skills.git
# Copy the skills you want to your Claude Code skills directory
cp -r claude-code-pm-skills/skills/prd ~/.claude/skills/
cp -r claude-code-pm-skills/skills/decision-doc ~/.claude/skills/
# ... etc
git clone https://github.com/Mehdibargach/claude-code-pm-skills.git
cp -r claude-code-pm-skills/skills/* ~/.claude/skills/
/plugin marketplace add Mehdibargach/claude-code-pm-skills
/plugin install claude-code-pm-skills
After installing, restart Claude Code. Type / to see your new skills.
Each skill is triggered with a /command:
/prd A tool that helps PMs prioritize features using AI-assisted scoring
/product-teardown Notion
/ab-test-design Moving the CTA button above the fold on the pricing page
/feedback-analyzer /path/to/customer-feedback.csv
/decision-doc Should we build our own auth system or use Auth0?
Skills auto-detect context. If you paste a CSV and ask Claude to analyze feedback, it may trigger /feedback-analyzer automatically.
Found a bug? Want to improve a skill? PRs welcome.
Want to add a new skill? Follow the format in any existing SKILL.md and submit a PR.
Mehdi Bargach — Builder PM | AI Products | Ex-Disney, Ex-TF1+
MIT — use it, fork it, share it.
npx claudepluginhub mehdibargach/claude-code-pm-skillsCore PM skills: PRD Template, Meeting Notes, Stakeholder Update, User Research Synthesis, and Competitive Analysis. The 5 skills every PM needs first.
The Product Manager's Operating System. AI-powered skills for every PM workflow: PRDs, prioritization, competitive intel, stakeholder updates, launch planning, and more.
Agent-first PM toolkit with 9 specialist agents and 18 skills for solo developers and small teams
Product Manager Skills Pack - 37 skills across 5 modules: demand insight, solution design, growth iteration, risk management, and product strategy
PM 핵심 워크플로(PRD 작성·디스커버리 종합·경쟁사 배틀카드·실험 분석·KPI 카드)와 슬래시 명령을 한 번에 설치하는 플러그인
The AI-native PM operating system — deep, framework-grounded PM skills with live MCP tool integrations, chained sub-agent workflows, and persistent user memory. Built for solo PMs and founding PMs who need an AI partner that actually knows their product.