Not in the top 1,000 by GitHub stars

ankitjha67/product-architect

The most comprehensive open-source product development system. 80 AI agents. 36 frameworks. Solo founder Day 0 → IPO.

History

Review weekly changes to SKILL.md before updating. Dates mark the weeks in which we observed each version; checks apply to the recorded commits.

View weekly changes

SKILL.md

Week of Nov 2, 2026 · Line counts unavailable

Before Not checked yet → After Network or broad shell

First observation → 285537be1ea7

No earlier version was observed for comparison.

Compare on GitHub

View on GitHubAdd to my skills

Verified commit 285537be1ea7147dfe8e6ad1933a791b2dd6dc7d

117GitHub stars
-1star in 7 days
1skill in this repository
0commits in 30 days

Heat

0.2
  • Star growth, last 7 daysNot available
  • Star growth, last 24 hoursNot available
  • Rank movement, last 7 daysNot available
  • Commits, last 30 daysNot available
  • Accounts asking about it through MCP, last 7 daysNot available
  • Hot votes this weekNot available

Heat never changes the order by stars, and sponsorship never touches it. How heat works

Stars over time

Oct 25, 2026Nov 3, 2026118

30-day change not yet available: not enough history.

Individual skills in this repository

How it works

product-architect

When your agent uses it

Complete product development system with 80 agents and 36 frameworks. Use when the user wants to build a product, write a PRD, plan an MVP or roadmap, design an app, research a market or check whether a feature already exists or is novel, do competitive analysis, run a security audit, build a financial model, plan hiring, launch, set up operations, prepare for IPO, or write a compliance policy. Also triggers on market research, does this exist, product marketing, positioning, pricing, packaging, sales, RevOps, partnerships, developer relations, user research, growth, PLG, data engineering, data governance, privacy, DPO, DSAR, incident management, OKRs, program management, docs, localization, investor relations, M&A, procurement, RAG, LangGraph, AI agents, LLM features, customer support, backend and distributed systems, enterprise architecture, developer productivity, FinOps and cloud cost, business continuity, physical security, facilities, regulatory affairs, hardware, internal comms, vendor risk, market expansion, accessibility, data science and experimentation, unit economics, SOP, or checklist for X. Do NOT use for general knowledge questions, coding tutorials, or creative writing unrelated to product development.

What it loads into context

Frontmatter

363 tokens

Always available to the agent

SKILL.md

5,028 tokens

When the skill is activated

Reference documents

1,141,341 tokens

Loaded on request

Token counts are estimates. Scripts run separately; they are not counted as reference context.

The playbook

  1. Depth Promise: Research-First, Never Surface-Level
  2. Critical: Read SMART-LOADER.md First
  3. Instructions
  4. Agent Directory
  5. Framework Directory
  6. Examples
  7. Troubleshooting
  8. Important

Scripts executed separately

  • tools/navigator.jsx
  • tools/validate_repo.py

Files

  • .github/ISSUE_TEMPLATE/bug.mddoc631 bytes
  • .github/ISSUE_TEMPLATE/content-gap.mddoc834 bytes
  • .github/pull_request_template.mddoc1,609 bytes
  • .github/workflows/validate.ymlasset636 bytes
  • .gitignoreasset19 bytes
  • CHANGELOG.mddoc9,431 bytes
  • CONTRIBUTING.mddoc4,106 bytes
  • ENHANCEMENTS.mddoc11,838 bytes
  • LICENSEasset1,087 bytes
  • README.mddoc15,990 bytes
  • SKILL.mdcore20,430 bytes
  • SKILL.mdcore20,430 bytes
  • SMART-LOADER.mddoc50,081 bytes
  • START-HERE.mddoc15,279 bytes
  • agents/00-chief-reviewer.mddoc36,771 bytes
  • agents/01-proactive-advisor.mddoc36,749 bytes
  • agents/02-discovery.mddoc54,390 bytes
  • agents/03-strategy.mddoc41,354 bytes
  • agents/04-prd.mddoc34,539 bytes
  • agents/05-design.mddoc30,118 bytes
  • agents/06-engineering.mddoc71,861 bytes
  • agents/07-testing-qa.mddoc28,258 bytes
  • agents/08-devops-sre.mddoc65,299 bytes
  • agents/09-security.mddoc81,375 bytes
  • agents/10-legal-ip.mddoc39,692 bytes
  • agents/11-compliance-ethics.mddoc68,298 bytes
  • agents/12-trust-safety.mddoc41,065 bytes
  • agents/13-fraud-operations.mddoc39,769 bytes
  • agents/14-launch-gtm.mddoc30,956 bytes
  • agents/15-marketing-sales.mddoc37,066 bytes
  • agents/16-analytics.mddoc42,595 bytes
  • agents/17-customer-success.mddoc40,917 bytes
  • agents/18-finance.mddoc46,858 bytes
  • agents/19-operations.mddoc47,152 bytes
  • agents/20-bau.mddoc41,467 bytes
  • agents/21-innovation-programs.mddoc34,678 bytes
  • agents/22-people-hr.mddoc48,814 bytes
  • agents/23-learning-development.mddoc46,680 bytes
  • agents/24-wellness-performance.mddoc45,901 bytes
  • agents/25-pr-communications.mddoc47,475 bytes
  • agents/26-governance-ipo.mddoc55,004 bytes
  • agents/27-esg-sustainability.mddoc44,418 bytes
  • agents/28-government-relations.mddoc30,648 bytes
  • agents/29-data-ai-strategy.mddoc62,402 bytes
  • agents/30-platform-ecosystem.mddoc49,711 bytes
  • agents/31-product-marketing.mddoc47,977 bytes
  • agents/32-sales-revops.mddoc49,937 bytes
  • agents/33-partnerships-bizdev.mddoc51,212 bytes
  • agents/34-developer-relations.mddoc49,994 bytes
  • agents/35-user-research.mddoc38,682 bytes
  • agents/36-pricing-monetization.mddoc53,821 bytes
  • agents/37-growth.mddoc45,192 bytes
  • agents/38-data-engineering.mddoc45,827 bytes
  • agents/39-privacy-dpo.mddoc50,276 bytes
  • agents/40-it-corporate-engineering.mddoc41,784 bytes
  • agents/41-technical-program-management.mddoc40,375 bytes
  • agents/42-content-docs.mddoc41,228 bytes
  • agents/43-localization-i18n.mddoc41,415 bytes
  • agents/44-investor-relations.mddoc45,524 bytes
  • agents/45-corporate-development.mddoc53,495 bytes
  • agents/46-procurement-supply-chain.mddoc49,196 bytes
  • agents/47-deep-research.mddoc23,934 bytes
  • agents/48-mobile-engineering.mddoc76,188 bytes
  • agents/49-ml-engineering.mddoc79,508 bytes
  • agents/50-frontend-web-platform.mddoc81,667 bytes
  • agents/51-solutions-engineering.mddoc39,806 bytes
  • agents/52-professional-services.mddoc42,663 bytes
  • agents/53-customer-education.mddoc43,483 bytes
  • agents/54-community.mddoc42,338 bytes
  • agents/55-billing-monetization-engineering.mddoc47,699 bytes
  • agents/56-revenue-accounting.mddoc48,514 bytes
  • agents/57-tax.mddoc58,062 bytes
  • agents/58-treasury.mddoc53,824 bytes
  • agents/59-internal-audit-risk.mddoc44,053 bytes
  • agents/60-talent-acquisition.mddoc55,332 bytes
  • agents/61-total-rewards.mddoc63,093 bytes
  • agents/62-chief-of-staff-bizops.mddoc57,289 bytes
  • agents/63-ai-evaluation-red-teaming.mddoc52,241 bytes
  • agents/64-customer-support.mddoc65,932 bytes
  • agents/65-backend-distributed-systems.mddoc70,395 bytes
  • agents/66-enterprise-architecture.mddoc61,455 bytes
  • agents/67-developer-productivity-platform.mddoc67,011 bytes
  • agents/68-finops-cloud-economics.mddoc58,903 bytes
  • agents/69-business-continuity-resilience.mddoc55,014 bytes
  • agents/70-corporate-physical-security.mddoc63,972 bytes
  • agents/71-workplace-facilities.mddoc61,466 bytes
  • agents/72-regulatory-affairs-quality.mddoc65,301 bytes
  • agents/73-hardware-manufacturing.mddoc61,589 bytes
  • agents/74-internal-communications.mddoc58,045 bytes
  • agents/75-third-party-risk.mddoc61,216 bytes
  • agents/76-market-expansion.mddoc66,773 bytes
  • agents/77-design-research-ops.mddoc60,852 bytes
  • agents/78-accessibility-inclusive-design.mddoc63,745 bytes
  • agents/79-data-science-experimentation.mddoc66,309 bytes
  • frameworks/30-day-launch-engine.mddoc15,247 bytes
  • frameworks/ab-testing-framework.mddoc26,992 bytes
  • frameworks/accessibility-i18n.mddoc7,106 bytes
  • frameworks/ai-department-playbooks.mddoc25,585 bytes
  • frameworks/ai-engineering-stack.mddoc14,915 bytes
  • frameworks/brand-messaging.mddoc12,988 bytes
  • frameworks/compensation-bands.mddoc13,421 bytes
  • frameworks/competitive-war-room.mddoc7,279 bytes
  • frameworks/consulting-frameworks.mddoc8,822 bytes
  • frameworks/continuous-improvement.mddoc10,684 bytes
  • frameworks/corporate-scaling.mddoc8,775 bytes
  • frameworks/coverage-audit.mddoc9,032 bytes
  • frameworks/customer-journey.mddoc15,927 bytes
  • frameworks/data-governance.mddoc14,132 bytes
  • frameworks/deep-research-protocol.mddoc19,848 bytes
  • frameworks/enterprise-edge-cases.mddoc18,632 bytes
  • frameworks/founders-playbook.mddoc17,554 bytes
  • frameworks/global-compliance.mddoc21,877 bytes
  • frameworks/growth-model.mddoc20,353 bytes
  • frameworks/incident-management.mddoc12,601 bytes
  • frameworks/institutional-memory.mddoc13,019 bytes
  • frameworks/mvp-framework.mddoc24,068 bytes
  • frameworks/okr-goal-setting.mddoc14,731 bytes
  • frameworks/partnership-framework.mddoc12,490 bytes
  • frameworks/physical-ops-pmi.mddoc7,753 bytes
  • frameworks/prd-framework.mddoc16,059 bytes
  • frameworks/pricing-packaging.mddoc16,910 bytes
  • frameworks/product-lifecycle.mddoc6,384 bytes
  • frameworks/risk-matrix.mddoc11,395 bytes
  • frameworks/roadmap-framework.mddoc24,562 bytes
  • frameworks/sales-playbook.mddoc14,771 bytes
  • frameworks/scenario-playbooks.mddoc143,819 bytes
  • frameworks/sop-process-maps.mddoc36,844 bytes
  • frameworks/stress-test-framework.mddoc25,815 bytes
  • frameworks/universal-checklists.mddoc11,800 bytes
  • frameworks/user-flows-framework.mddoc8,330 bytes
  • references/DISCLAIMER.mddoc7,421 bytes
  • references/agent-standards.mddoc19,971 bytes
  • references/compliance/eu.mddoc14,036 bytes
  • references/compliance/india.mddoc17,240 bytes
  • references/compliance/sea.mddoc14,682 bytes
  • references/compliance/uk.mddoc12,164 bytes
  • references/compliance/us.mddoc15,193 bytes
  • references/github-readme.mddoc14,328 bytes
  • references/industry-references.mddoc7,317 bytes
  • tools/navigator.jsxruns24,170 bytes
  • tools/validate_repo.pyruns11,460 bytes
Read SKILL.md

# Product Architect

80 specialized agents covering every department from solo founder Day 0 to IPO.
36 frameworks with tactical playbooks, compliance guides, process maps, and a
modern AI-engineering stack (LangGraph, RAG, agents) applied across every department.

## Depth Promise: Research-First, Never Surface-Level

This system goes deep "until the Mariana Trench." Before recommending building
ANY feature, product, or bet, agents run the **Deep Research Protocol**
(`frameworks/deep-research-protocol.md`, owned by Agent 47): they investigate the
market end to end and return a grounded verdict - **"this already exists, here are
the competitors + citations, refine it"** or **"this is white-space, no competition
or citations found in this niche"** (with the honest caveat that absence of evidence
View the complete source on GitHub

Skills included

  • product-architect

Repository facts

License
MIT
Created
Mar 11, 2026
Last pushed
Sep 2, 2026
Forks
23
Open issues
0
Project activity
Slowing

Before you install

Network or broad shell

Automated signals, not a guarantee

Checked Nov 6, 2026

Not fully analyzed: some files were too long, unreadable or missing. This never lowers the level.

Show 1 note
  • SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
Show all 61 signals by file

CHANGELOG.md

  • Network accessline 3
    All notable changes to Product Architect. Format follows [Keep a Changelog](https://keepachangelog.com/);

README.md

  • Network accessline 7
    > **This is a [Claude Skill](https://docs.anthropic.com/en/docs/agents-and-tools/skills).** Claude reads `SKILL.md`. This README is for human visitors.
  • Network accessline 62
    git clone https://github.com/ankitjha67/product-architect.git
  • Network accessline 224
    *Built through iterative human-AI collaboration using Claude (Anthropic). Compliant with [Anthropic's official skill guide](https://docs.anthropic.com/en/docs/agents-and-tools/skills). 25/25 skill compliance checks passed.*

SKILL.md

  • Network accessline 9
    category: product-development   tags: [product-management, startup, prd, strategy, compliance, finance, operations, hiring, launch, saas, marketplace]   repository: https://github.com/ankitjha67/product-architect
  • Network accessline 10
    tags: [product-management, startup, prd, strategy, compliance, finance, operations, hiring, launch, saas, marketplace]   repository: https://github.com/ankitjha67/product-architect ---
  • Network accessline 11
    repository: https://github.com/ankitjha67/product-architect

START-HERE.md

  • Network accessline 14
    You have access to a system of 80 specialized agents and 36 frameworks hosted at: https://github.com/ankitjha67/product-architect
  • Network accessline 15
    https://github.com/ankitjha67/product-architect
  • Network accessline 63
    > the specialized agent file. Could you go to: > > **https://github.com/ankitjha67/product-architect/blob/main/agents/[XX-name].md**
  • Network accessline 64
    > > **https://github.com/ankitjha67/product-architect/blob/main/agents/[XX-name].md** >
  • Network accessline 65
    > **https://github.com/ankitjha67/product-architect/blob/main/agents/[XX-name].md**
  • Network accessline 96
    > "For the best results, I also need the [framework name] file: > **https://github.com/ankitjha67/product-architect/blob/main/frameworks/[name].md**
  • Network accessline 97
    > **https://github.com/ankitjha67/product-architect/blob/main/frameworks/[name].md**

agents/06-engineering.md

  • Dangerous shell operationline 328
    - Insecure output handling: model output flowing into SQL/shell/eval()/HTML must be

agents/08-devops-sre.md

  • Access to secretsline 281
    [Credential-related source omitted]

agents/09-security.md

  • Dangerous shell operationline 281
    □ Validate & escape model output before it flows into eval(), SQL, shell, or HTML

agents/15-marketing-sales.md

  • Access to secretsline 339
    [Credential-related source omitted]

agents/24-wellness-performance.md

  • Access to secretsline 64
    [Credential-related source omitted]

agents/34-developer-relations.md

  • Network accessline 70
    |------------------|-------------------|-------------------------------|-----------| | Docs → signup <8% | Signup gated behind sales or a credit card; no free tier | Self-serve signup, GitHub OAuth, free tier with real limits, a "get your k
  • Network accessline 71
    | Docs → signup <8% | Signup gated behind sales or a credit card; no free tier | Self-serve signup, GitHub OAuth, free tier with real limits, a "get your key" CTA above the fold on every docs page | 2-4 weeks | | Signup → first call <60%/24
  • Network accessline 72
    | Signup → first call <60%/24h | No key at signup; quickstart starts with an SDK install | Auto-provision `sk_test_` visible in 10s + a prefilled curl the dev can paste; curl-first quickstart | 1-3 weeks |
  • Network accessline 121
    - One canonical quickstart per language that hits TTFHW < 5 min. - Pre-filled test API key for logged-in readers (no "go generate a key" detour). - Curl-first, then the SDK - developers trust curl because it has no hidden magic.
  • Network accessline 123
    - Curl-first, then the SDK - developers trust curl because it has no hidden magic.
  • Network accessline 172
    "message": "Missing required param: 'amount'. Provide an integer in paise.",            "param": "amount",            "doc_url": "https://docs.acme.dev/errors/parameter_missing",
  • Network accessline 173
    "param": "amount",            "doc_url": "https://docs.acme.dev/errors/parameter_missing",            "request_id": "req_1a2b3c"
  • Network accessline 174
    "doc_url": "https://docs.acme.dev/errors/parameter_missing",
  • Network accessline 271
    1. Sign up (email/GitHub OAuth - offer GitHub, devs hate forms) 2. Land on dashboard with TEST key already visible + curl snippet pre-filled with it
  • Network accessline 272
    2. Land on dashboard with TEST key already visible + curl snippet pre-filled with it

agents/42-content-docs.md

  • Network accessline 540
    fixing the REFERENCE (add `amount` description, units = paise, runnable example). 3. Generate reference from the OpenAPI spec (with Agent 34); hand-write the how-to with    real cURL + Node + Python samples that run in CI so they can't go s
  • Network accessline 541
    3. Generate reference from the OpenAPI spec (with Agent 34); hand-write the how-to with    real cURL + Node + Python samples that run in CI so they can't go stale. 4. Add an error-message contract for the common failure (refund > captured a
  • Network accessline 542
    real cURL + Node + Python samples that run in CI so they can't go stale.

agents/48-mobile-engineering.md

  • Access to secretsline 213
    [Credential-related source omitted]
  • Network accessline 308
    □ Frequency caps per user per week, quiet hours in the user's local timezone (Agent 43), an in-app preference centre. Uninstall punishes spam. DEEP LINKS - get this wrong and every campaign leaks users to the store: □ iOS Universal Links: a
  • Network accessline 309
    DEEP LINKS - get this wrong and every campaign leaks users to the store: □ iOS Universal Links: apple-app-site-association at https://domain/.well-known/, served as application/json, no redirects, no auth. Android   App Links: assetlinks.js
  • Network accessline 310
    □ iOS Universal Links: apple-app-site-association at https://domain/.well-known/, served as application/json, no redirects, no auth. Android
  • Access to secretsline 346
    [Credential-related source omitted]
  • Access to secretsline 347
    [Credential-related source omitted]
  • Access to secretsline 368
    [Credential-related source omitted]
  • Access to secretsline 375
    [Credential-related source omitted]

agents/65-backend-distributed-systems.md

  • Network accessline 97
    | Style | Best fit | Real strengths | Real costs | |---|---|---|---| | **REST / JSON over HTTP** | Public APIs, partner integrations, anything a stranger must call from curl | Ubiquitous tooling, cacheable via HTTP semantics, debuggable by 
  • Network accessline 98
    |---|---|---|---| | **REST / JSON over HTTP** | Public APIs, partner integrations, anything a stranger must call from curl | Ubiquitous tooling, cacheable via HTTP semantics, debuggable by anyone, no client library needed | Verbose, weakly 
  • Network accessline 99
    | **REST / JSON over HTTP** | Public APIs, partner integrations, anything a stranger must call from curl | Ubiquitous tooling, cacheable via HTTP semantics, debuggable by anyone, no client library needed | Verbose, weakly typed without a sc

frameworks/ai-engineering-stack.md

  • Dangerous shell operationline 200
    LLM02 Insecure output       - model output flows into eval()/SQL/shell/HTML. Validate &

frameworks/prd-framework.md

  • Dangerous shell operationline 282
    | ML or LLM in the user path              | AI eval (63), Privacy (39)   | AI eval (63)   |

frameworks/scenario-playbooks.md

  • Network accessline 1152
    DAY 3 - FIX THE TOP 3 (ranked by seconds lost): □ Test key: auto-provision an `sk_test_` key on signup, visible in 10s, pre-filled   into a runnable curl snippet on the dashboard ("Run this →" button).
  • Network accessline 1153
    □ Test key: auto-provision an `sk_test_` key on signup, visible in 10s, pre-filled   into a runnable curl snippet on the dashboard ("Run this →" button). □ Quickstart: rewrite curl-first, then the SDK. One canonical quickstart per language.
  • Network accessline 1154
    into a runnable curl snippet on the dashboard ("Run this →" button).
  • Network accessline 1361
    DAY 3 - WRITE THE 5-MINUTE QUICKSTART: □ Curl-first, then the SDK (devs trust curl - no hidden magic). Copy-paste must run
  • Network accessline 1362
    □ Curl-first, then the SDK (devs trust curl - no hidden magic). Copy-paste must run
  • Instruction override signalline 1436
    ⛔ Rewriting only the happy path - empty/error/loading states are where users actually rage-quit ⛔ Clever copy that adds a beat of "wait, what?" - onboarding is not the place for jokes ⛔ Generic errors ("something went wrong") that don't tel
  • Instruction override signalline 1437
    ⛔ Clever copy that adds a beat of "wait, what?" - onboarding is not the place for jokes ⛔ Generic errors ("something went wrong") that don't tell the user what to fix ⛔ Changing copy AND layout together (you'll never know which moved the me
  • Instruction override signalline 1438
    ⛔ Generic errors ("something went wrong") that don't tell the user what to fix
  • Access to secretsline 2535
    [Credential-related source omitted]

references/github-readme.md

  • Network accessline 11
    Product Architect is a multi-agent skill system for [Claude](https://claude.ai) that transforms any product idea into a complete, executable blueprint. It covers **every department, function, process, and policy** that exists in a world-cla

tools/navigator.jsx

  • Executable scriptline 1
    Executable file
  • Network accessline 183
    <div style={{ minHeight: "100vh", background: C.bg, color: C.text, fontFamily: "'Inter', system-ui, -apple-system, sans-serif" }}>       <style>{`         @import url('https://fonts.googleapis.com/css2?family=Inter:wght@300;400;500;600;700&
  • Network accessline 184
    <style>{         @import url('https://fonts.googleapis.com/css2?family=Inter:wght@300;400;500;600;700&family=JetBrains+Mono:wght@400;500&display=swap');
  • Network accessline 185
    @import url('https://fonts.googleapis.com/css2?family=Inter:wght@300;400;500;600;700&family=JetBrains+Mono:wght@400;500&display=swap');

tools/validate_repo.py

  • Executable scriptline 1
    #!/usr/bin/env python3
  • Possible obfuscationline 43
    first = content.splitlines()[0].lstrip("<U+FEFF>").strip()

How the signals fit together

Facts from a static read of the files at the pinned commit. They describe what the code does, not why.

Declared and executed: 1 fact
  • Contacts fonts.googleapis.com, which SKILL.md, the README and the plugin manifest do not mentiontools/navigator.jsx:185High confidence
Signal confidence: 61 facts

and 11 more

Works with

Agent compatibility, from the files in this repository
AgentStatusEvidenceInstall to
Claude CodeCompatibleStandard SKILL.md SKILL.md.claude/skills/<skill-name>/
CodexCompatibleStandard SKILL.md SKILL.md.agents/skills/<skill-name>/
CursorCompatibleStandard SKILL.md SKILL.md.cursor/skills/<skill-name>/
Gemini CLICompatibleStandard SKILL.md SKILL.md.gemini/skills/<skill-name>/
GitHub CopilotCompatibleStandard SKILL.md SKILL.md.github/skills/<skill-name>/
OpenCodeCompatibleStandard SKILL.md SKILL.md.opencode/skills/<skill-name>/
  • Native The repository ships a manifest, folder or frontmatter field for this agent.
  • Compatible A standard SKILL.md that this agent can read.
  • Unknown No evidence either way.

Derived automatically from paths, manifests and frontmatter. Not tested on each agent.