By howbuild
Transforms product ideas into structured PRDs, acceptance criteria, policies, decision logs, measurement plans, and wireframes through an AI-assisted product management workflow with review gates and completeness scoring.
Review a candidate feature before marking it as Must-have.
Check whether the current product documents are complete enough.
Inspect whether the current feature list is drifting from core intent.
Compare reference products and convert patterns into product questions.
Generate PRD, policy, measurement, AC, decision log, and review outputs.
Reviews whether reference or competitor patterns fit the current product without copying them; checks Core Intent, Must-have/Nice-to-have fit, policy impact, measurement impact, and user confirmation questions.
Creates Claude Design handoff briefs and Claude Design prompts from confirmed PRD, policy, measurement, AC, decision log, and structural wireframe details without expanding product scope.
Edits final product documents and question cards to remove AI-like wording while preserving practical terms such as PRD, AC, KPI, permission policy, state values, events, and logs.
Reviews whether user actions, state changes, operational records, and KPI connections have sufficient measurement and logging coverage.
Reviews product purpose, problem definition, core user, Must-have/Nice-to-have priority, and success indicators before final handoff.
Writes testable acceptance criteria using Given/When/Then, linking each AC to requirement, priority, operating intent, scalability, screen data-req-id, policy ID, and measurement/logging ID.
Extracts reusable patterns from competitor or reference examples without copying them, then rates Must-have/Nice-to-have fit as Green, Yellow, or Red.
Records why product decisions were made, including question, choices, user selection, recommendation, deferred alternatives, policy links, measurement links, and AC links.
Writes Claude Design handoff briefs and prototype prompts from confirmed product decisions, including screens, actions, states, policies, measurement requirements, Must-have/Nice-to-have priority, operating intent, scalability, and unresolved items.
Reads external domain packs or user-provided domain descriptions as question candidates, not confirmed policy, and marks unconfirmed items as assumptions or unresolved.
Modifies files
Hook triggers on file write and edit operations
Uses power tools
Uses Bash, Write, or Edit tools
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.
Idea to Product is a multi-runtime AI PM plugin that helps non-developers turn ideas into product-ready requirements.
Supported runtimes:
Supported operating systems:
Install Codex and Claude Code support with one command.
macOS, Linux, WSL, or Git Bash:
curl -fsSL https://raw.githubusercontent.com/howbuild/idea-to-product/main/install.sh | sh
Windows PowerShell:
irm https://raw.githubusercontent.com/howbuild/idea-to-product/main/install.ps1 | iex
Install only one runtime on macOS, Linux, WSL, or Git Bash:
curl -fsSL https://raw.githubusercontent.com/howbuild/idea-to-product/main/install.sh | sh -s -- --codex
curl -fsSL https://raw.githubusercontent.com/howbuild/idea-to-product/main/install.sh | sh -s -- --claude
Install only one runtime on Windows PowerShell:
$env:ITP_INSTALL_TARGET="codex"; irm https://raw.githubusercontent.com/howbuild/idea-to-product/main/install.ps1 | iex; Remove-Item Env:ITP_INSTALL_TARGET
$env:ITP_INSTALL_TARGET="claude"; irm https://raw.githubusercontent.com/howbuild/idea-to-product/main/install.ps1 | iex; Remove-Item Env:ITP_INSTALL_TARGET
For local testing after cloning the repo:
./install.sh
.\install.ps1
The installer registers idea-to-product-marketplace, installs idea-to-product, and refreshes an existing install when the marketplace already exists.
The installer is a convenience wrapper around the marketplace flow. It still uses the runtime marketplace system internally.
marketplace add and plugin add / plugin install yourself.It is not a PRD generator and it is not a loose collection of skills. The plugin is built around PM workflow orchestration, command entrypoints, hook-based review gates, and specialist reviewer agents. Skills are small reusable helpers used inside that workflow.
Idea to Product helps non-developers participate in product design by working from a structural HTML wireframe, product questions, A/B/C/D choices, recommendation cards, policy decisions, state definitions, event/log design, AC, and final documentation.
The core value is that a non-developer naturally learns product thinking while shaping a buildable requirement set. The plugin does not think instead of the user. It works more like an AI PM partner that asks grounded questions, explains tradeoffs, and keeps product scope from drifting.
Questions are written so the decision is easy to understand at first read, while useful product terms such as PRD, AC, KPI, permission policy, state values, events, logs, and data-req-id are kept.
The workflow also uses a Core User Flow:
Users learn by:
AI tools can quickly create HTML prototypes, but those prototypes often miss the PM layer that developers need before implementation:
Without those, the screen may look plausible but still be hard to build, test, operate, or maintain.
workflows/: defines the PM process from idea intake to final outputcommands/: user-facing entrypoints for starting, adding features, generating docs, and reviewshooks/: automatic quality gates for scope drift, wireframe changes, policy consistency, measurement coverage, completeness, consistency, and final writingagents/: specialist reviewers for PM, scope, product flow, policy, measurement, QA, tech, and human writingskills/: small reusable helpers called by workflows, hooks, commands, or agentsdomains/: domain-pack injection structure and templatestemplates/: output templates for PRD, AC, policy, measurement, decision log, completeness, and review reportsmcp/: suggested MCP integrations and example configurationClaude Design handoff: brief and prompt templates for visualizing product structure without expanding scopeIdea to Product helps users create:
npx claudepluginhub howbuild/idea-to-product --plugin idea-to-productHarness-native ECC operator layer - 67 agents, 271 skills, 92 legacy command shims, reusable hooks, rules, selective install profiles, and production-ready workflows for Claude Code, Codex, OpenCode, Cursor, and related agent harnesses
Comprehensive feature development workflow with specialized agents for codebase exploration, architecture design, and quality review
Upstash Context7 MCP server for up-to-date documentation lookup. Pull version-specific documentation and code examples directly from source repositories into your LLM context.
A growing collection of Claude-compatible academic workflow bundles. Covers scientific figures, manuscript writing and polishing, reviewer assessment, citation retrieval, data availability, paper reading, literature search, response letters, paper-to-PPTX conversion, and evidence-grounded Chinese invention patent drafting. Rules are organized as reusable skill folders with explicit workflows and quality checks.
Core skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques
Comprehensive skill pack with 66 specialized skills for full-stack developers: 12 language experts (Python, TypeScript, Go, Rust, C++, Swift, Kotlin, C#, PHP, Java, SQL, JavaScript), 10 backend frameworks, 6 frontend/mobile, plus infrastructure, DevOps, security, and testing. Features progressive disclosure architecture for 50% faster loading.