Product
Plugin
product-architect
The most comprehensive open-source product development skill for Claude.
Plugin Signal75/100Solid
maintained73
capable92
documented75
adopted44
Install
$ npx -y skills add ankitjha67/product-architect --agent claude-code
Stats
118
Stars
23
Forks
Maintained
Maintenance
JavaScript
Language
MIT
License
1mo ago
Last commit
7mo ago
Created
3h ago
Added
In this plugin
- agents
- 00-chief-reviewer
- 01-proactive-advisor
- 02-discovery
- 03-strategy
- 04-prd
- 05-design
- 06-engineering
- 07-testing-qa
- 08-devops-sre
- 09-security
- 10-legal-ip
- 11-compliance-ethics
- 12-trust-safety
- 13-fraud-operations
- 14-launch-gtm
- 15-marketing-sales
- 16-analytics
- 17-customer-success
- 18-finance
- 19-operations
- 20-bau
- 21-innovation-programs
- 22-people-hr
- 23-learning-development
- 24-wellness-performance
- 25-pr-communications
- 26-governance-ipo
- 27-esg-sustainability
- 28-government-relations
- 29-data-ai-strategy
- 30-platform-ecosystem
- 31-product-marketing
- 32-sales-revops
- 33-partnerships-bizdev
- 34-developer-relations
- 35-user-research
- 36-pricing-monetization
- 37-growth
- 38-data-engineering
- 39-privacy-dpo
- 40-it-corporate-engineering
- 41-technical-program-management
- 42-content-docs
- 43-localization-i18n
- 44-investor-relations
- 45-corporate-development
- 46-procurement-supply-chain
- 47-deep-research
- 48-mobile-engineering
- 49-ml-engineering
- 50-frontend-web-platform
- 51-solutions-engineering
- 52-professional-services
- 53-customer-education
- 54-community
- 55-billing-monetization-engineering
- 56-revenue-accounting
- 57-tax
- 58-treasury
- 59-internal-audit-risk
- 60-talent-acquisition
- 61-total-rewards
- 62-chief-of-staff-bizops
- 63-ai-evaluation-red-teaming
- 64-customer-support
- 65-backend-distributed-systems
- 66-enterprise-architecture
- 67-developer-productivity-platform
- 68-finops-cloud-economics
- 69-business-continuity-resilience
- 70-corporate-physical-security
- 71-workplace-facilities
- 72-regulatory-affairs-quality
- 73-hardware-manufacturing
- 74-internal-communications
- 75-third-party-risk
- 76-market-expansion
- 77-design-research-ops
- 78-accessibility-inclusive-design
- 79-data-science-experimentation
- skills
What's inside
Agent(80 agents)
00-chief-reviewerYou are the Chief Product Officer conducting the final quality audit across EVERY phase and EVERY agent's output. You have VETO power. You find what 30 other agents missed.01-proactive-advisorYou are the trusted board advisor who has seen 500 products built, 300 fail, and 200 succeed. You know what kills products at each stage and what separates the top 1% from everyone else. Your job is to PROACTIVELY surface ideas, risks, opportunities, and best practices that the02-discoveryMcKinsey engagement manager conducting deep, hypothesis-driven discovery with MECE thinking. Agent 47 owns the research protocol; Agent 35 owns the STANDING research function (ResearchOps, panels, usability) once a product exists. You own the PRE-BUILD decision, time-boxed, per
- 03-strategy
- 04-prd
- 05-design
- 06-engineering
- 07-testing-qa
- 08-devops-sre
- 09-security
- 10-legal-ip
- 11-compliance-ethics
- 12-trust-safety
- 13-fraud-operations
- 14-launch-gtm
- 15-marketing-sales
- 16-analytics
- 17-customer-success
- 18-finance
- 19-operations
- 20-bau
- 21-innovation-programs
- 22-people-hr
- 23-learning-development
- 24-wellness-performance
- 25-pr-communications
- 26-governance-ipo
- 27-esg-sustainability
- 28-government-relations
- 29-data-ai-strategy
- 30-platform-ecosystem
- 31-product-marketing
- 32-sales-revops
- 33-partnerships-bizdev
- 34-developer-relations
- 35-user-research
- 36-pricing-monetization
- 37-growth
- 38-data-engineering
- 39-privacy-dpo
- 40-it-corporate-engineering
- 41-technical-program-management
- 42-content-docs
- 43-localization-i18n
- 44-investor-relations
- 45-corporate-development
- 46-procurement-supply-chain
- 47-deep-research
- 48-mobile-engineering
- 49-ml-engineering
- 50-frontend-web-platform
- 51-solutions-engineering
- 52-professional-services
- 53-customer-education
- 54-community
- 55-billing-monetization-engineering
- 56-revenue-accounting
- 57-tax
- 58-treasury
- 59-internal-audit-risk
- 60-talent-acquisition
- 61-total-rewards
- 62-chief-of-staff-bizops
- 63-ai-evaluation-red-teaming
- 64-customer-support
- 65-backend-distributed-systems
- 66-enterprise-architecture
- 67-developer-productivity-platform
- 68-finops-cloud-economics
- 69-business-continuity-resilience
- 70-corporate-physical-security
- 71-workplace-facilities
- 72-regulatory-affairs-quality
- 73-hardware-manufacturing
- 74-internal-communications
- 75-third-party-risk
- 76-market-expansion
- 77-design-research-ops
- 78-accessibility-inclusive-design
- 79-data-science-experimentation
README
Product Architect
The most comprehensive open-source product development skill for Claude.
80 agents · 36 frameworks · Research-first, AI-native, depth to the Mariana Trench · Solo founder Day 0 → IPO → public company
This is a Claude Skill. Claude reads
SKILL.md. This README is for human visitors.
About
Product Architect turns Claude into an entire product organization.
Most AI product advice is one generalist answering everything at surface level. This is the opposite: 80 specialized department heads covering Discovery, PRD, Engineering, Security, Privacy, Pricing, Growth, RevOps, Legal, Finance, Governance and more. Each carries a department-head-depth playbook, routed to your question by a context engine that loads only what's relevant.
Ask "should we build this?" and you don't get an opinion. You get a cited market verdict (does it already exist, who ships it, where's the gap), then a PRD with the edge cases, an architecture, a pricing model, a compliance read, and a launch plan. Each comes from the agent that owns that domain, cross-checked against the others.
What makes it different:
| 🔍 Research-first | Before recommending you build anything, it investigates the market and returns a verdict: "this exists; here are the competitors, refine it" or "white-space, and here's why the niche may be empty." It never fabricates a company, statistic, or URL. |
| 🧠 Reasons, doesn't template | Every agent works through frame → options → evidence → quantified trade-offs → recommendation → risks + the condition that would reverse it. Each carries its own decision framework for its hardest calls. |
| 🏢 Enterprise-grade | Regulated-industry, 1000+ person, multi-region depth: audit trails, SLAs, procurement gauntlets, change management, 3-year TCO. Not just startup advice. |
| 🤖 AI-native | A full LangGraph + RAG engineering stack, plus a concrete LLM/agent application mapped to all 80 departments. |
| ⚖️ Governed | A 5-level authority hierarchy (Compliance → Privacy → Security → Finance → Review) resolves conflicts between agents instead of letting them contradict each other. |
| 💾 Remembers | Key Decision Records survive chat compaction. Paste one into a new conversation and pick up exactly where you left off. |
Who it's for: solo founders who need a whole company's worth of expertise · product managers who want PRDs with every edge case · engineering leads needing architecture, security, and test strategy · teams operating at Fortune-500 caliber without Fortune-500 headcount.
Honest scope: this is an educational and operational framework built through
human-AI collaboration, not professional advice. Legal, financial, security, and HR
content requires qualified review before real-world use. See
references/DISCLAIMER.md.
Install
Claude.ai (Pro, Max, Team, or Enterprise)
Skills require a paid plan. Free tier does not have access to Skills, including "Add from GitHub."
- Download this repo as ZIP (Code → Download ZIP)
- Go to Claude.ai → Settings → Capabilities → Skills
- Upload the ZIP
- Test: Ask Claude "Help me build a product" or "Write a PRD for [feature]"
Claude Code
git clone https://github.com/ankitjha67/product-architect.git
# Place in your Claude Code skills directory (~/.claude/skills/)
API
Use the /v1/skills endpoint with the container.skills parameter. Requires Code Execution Tool beta.
Free Tier Workarounds
If you're on the free plan, you can still use everything in this repo:
-
Guided mode (recommended) - Open
START-HERE.mdon GitHub, click Raw, copy everything, paste into a new Claude chat. Describe your idea - Claude will ask what you're building, identify the right agents, give you exact GitHub URLs to paste them one at a time, and guide you through the entire product development process step by step. -
Projects - Create a Project in Claude.ai, paste
SKILL.md+SMART-LOADER.mdas project knowledge. Then paste individual agent/framework files as needed per conversation. -
Direct paste - Open any file on GitHub (e.g.
frameworks/founders-playbook.md), copy the raw content, and paste it into a regular Claude chat. Every file works standalone. -
Claude Code - If you have Claude Code access, clone the repo into your skills directory. Skills load automatically.
What's Inside
80 Specialized Agents
Organized by product lifecycle - each operates at department-head depth:
| Phase | Agents |
|---|---|
| Research & Audit | 47 Deep Research (exists-vs-novel verdict, research-first gate) · 00 Chief Reviewer (6-pass audit, veto power) · 01 Proactive Advisor (blind spots) |
| Product | 02 Discovery · 03 Strategy · 04 PRD · 05 Design · 06 Engineering · 35 User Research |
| Build & Test | 07 Testing & QA · 08 DevOps & SRE · 41 Technical Program Management |
| Protect | 09 Security · 10 Legal & IP · 11 Compliance (14 policies) · 12 Trust & Safety · 13 Fraud · 39 Privacy & Data Protection (DPO) |
| Launch & Grow | 14 Launch & GTM · 15 Marketing & Sales · 16 Analytics · 17 Customer Success · 31 Product Marketing · 37 Growth |
| Commercial | 32 Sales & RevOps · 33 Partnerships & BizDev · 36 Pricing & Monetization |
| Operate & Scale | 18 Finance · 19 Operations (24 SOPs) · 20 BAU · 21 Innovation · 46 Procurement & Supply Chain |
| People | 22 People & HR · 23 L&D · 24 Wellness & Performance |
| Corporate | 25 PR & Comms · 26 Governance & IPO · 27 ESG · 28 Govt Relations · 44 Investor Relations · 45 Corporate Development & M&A |
| Data & Platform | 29 Data & AI Strategy · 30 Platform & Ecosystem · 34 Developer Relations · 38 Data Engineering |
| Enablement | 40 IT & Corporate Engineering · 42 Content & Docs · 43 Localization & i18n |
| Engineering Specialisms | 48 Mobile Engineering · 49 ML Engineering (MLOps) · 50 Frontend & Web Platform |
| Customer-Facing Delivery | 51 Solutions Engineering (Pre-Sales) · 52 Professional Services · 53 Customer Education · 54 Community |
| Revenue Systems | 55 Billing & Monetization Engineering |
| Finance Specialisms | 56 Revenue Accounting & Controller · 57 Tax · 58 Treasury |
| Risk & Talent | 59 Internal Audit & Enterprise Risk · 60 Talent Acquisition · 61 Total Rewards |
| Executive & AI Assurance | 62 Chief of Staff & BizOps · 63 AI Evaluation & Red-Teaming |
| Support & Platform Engineering | 64 Customer Support · 65 Backend & Distributed Systems · 66 Enterprise Architecture · 67 Developer Productivity & Internal Platform |
| Infra Economics & Resilience | 68 FinOps & Cloud Economics · 69 Business Continuity & Enterprise Resilience |
| Corporate Security & Workplace | 70 Corporate & Physical Security · 71 Workplace, Facilities & Real Estate |
| Regulated Product & Hardware | 72 Regulatory Affairs & Quality Management · 73 Hardware Engineering & Manufacturing |
| Comms & Vendor Risk | 74 Internal Communications · 75 Third-Party & Vendor Risk |
| Expansion, Ops & Insight | 76 Market Expansion & Country Launch · 77 Design Ops & Research Ops · 78 Accessibility & Inclusive Design · 79 Data Science & Experimentation |
36 Frameworks
| Framework | What It Does |
|---|---|
| AI Engineering Stack | LangGraph agents, RAG (hybrid retrieval, rerank, GraphRAG), evals, guardrails, observability, and the maturity ladder - with Anthropic-native options |
| AI Department Playbooks | How every one of the 64 departments applies LLMs/RAG/agents - a specific use case, pattern, stack, and guardrail per function |
| Enterprise Edge Cases | What actually derails work in a large org: sponsor departure, reorg, budget cut, approval deadlock, change freeze, legal hold, vendor EOL, conflicting mandates, M&A freeze, scale pathologies. Each with trigger, first move, and structural fix, plus a pre-mortem sweep |
| Deep Research Protocol | End-to-end market existence/novelty engine: exists-vs-novel verdict, citation hygiene, anti-hallucination gate, per-agent depth map |
| Founder's Playbook | Week-by-week from Day 0 with costs, fundraising, IP, legal |
| 30-Day Launch Engine | Positioning, channel selection, day-by-day execution |
| Scenario Playbooks | 54 tactical guides across 31 departments (breach response, pivot, MEDDICC discovery call, DSAR runbook, secure offboarding, price increase, launch readiness, investor update, etc.) |
| SOP & Process Maps | 24 SOPs across 10 departments with automation opportunities |
| Compensation Bands | Salary by role/level/geography + equity + maintenance process |
| Consulting Frameworks | McKinsey 7S, Porter's, Blue Ocean, BCG, JTBD, PESTEL |
| Stress-Test Framework | Product-level failure: 165 checklist items across 18 failure classes, from idempotency and clock skew to money rounding, encoding, illegal state transitions and adversarial abuse, plus how to run the session and a severity triage rubric |
| OKRs & Goal-Setting | North Star metric, metrics tree, OKR cascade & cadence |
| Pricing & Packaging | Price-metric selection, Van Westendorp, discount governance |
| Growth Model | AARRR, growth loops, activation/retention, experiment engine |
| Sales Playbook | Sales stages, MEDDICC, discovery scripts, objection handling |
| Data Governance | Data contracts, quality SLAs, classification, lineage, catalog |
| Incident Management | Severity matrix, on-call, comms, blameless postmortems |
| Partnership Framework | Partner tiers, deal structures, co-sell, partner economics |
| Brand & Messaging | Positioning statement, messaging house, voice & tone, narrative |
| Customer Journey | Lifecycle map, moments of truth, retention/expansion loops |
| Institutional Memory | Decision archaeology, knowledge maps, context handoffs |
| Corporate Scaling | Solo founder → IPO with org charts per stage |
| Global Compliance | Regulatory overview for 30+ countries |
| + 13 more | PRD, MVP, roadmap, user-flows, risk-matrix, A/B testing, accessibility, product lifecycle, competitive intel, continuous improvement, physical ops, coverage audit, universal checklists |
Country Compliance Deep-Dives
India · US · EU · UK · Southeast Asia (Singapore, Indonesia, Thailand, Vietnam, Philippines, Malaysia)
Key Architecture
AI-Native - A modern AI-engineering layer runs through the whole system: the AI Engineering Stack framework (LangGraph orchestration, RAG with hybrid retrieval + reranking + GraphRAG, evals-in-CI, guardrails, observability, and the L0→L5 maturity ladder), plus AI Department Playbooks giving all 80 departments a concrete LLM/RAG/agent application. Defaults to the latest Claude models (Opus 4.8, Sonnet 5, Haiku 4.5) with adaptive thinking, MCP for integrations, and Security (09) + Privacy (39) sign-off on any AI feature touching untrusted input or personal data.
Research-First Depth - Before recommending building anything, agents run the Deep Research Protocol (Agent 47): an end-to-end market investigation that returns a grounded verdict - "this already exists, here are the competitors + citations, refine it" or "this is white-space, no competition/citations in this niche" (with the honest caveat that absence of evidence isn't proof of novelty, plus a "why is it empty?" analysis). Every agent inherits a Depth Rubric (L0 surface → L4 Mariana Trench), must grade itself L3+, and never fabricates a company, statistic, study, patent, or URL.
File tree
FAQ
product-architect is a Claude Code plugin with 1 hand-picked skill, indexed on Flowy in the Product category. Install it with the command on its page. It includes product-architect. Its skills do not fire on their own yet. Request auto-invocation to have Flowy route them as you prompt. Free and open source.
- What is product-architect?
- The most comprehensive open-source product development skill for Claude. 80 agents · 36 frameworks · Research-first, AI-native, depth to the Mariana Trench · Solo founder Day 0 → IPO → public company This is a Claude Skill. Claude reads SKILL.md.
- How do I install product-architect?
- Run these in Claude Code: npx -y skills add ankitjha67/product-architect --agent claude-code. Then prompt normally.
- Does product-architect auto-invoke its skills?
- Not yet. It is indexed on Flowy as a plain plugin. Request auto-invocation on its page and Flowy will route its skills for you as you prompt.
- Is product-architect free?
- Yes. Flowy is free and open source, with nothing gated. You can read every skill in full before you install.
Is this plugin yours?
Claim it with GitHubSubmit a pluginPromote it