domains / families / business / idea-to-blueprint

idea-to-blueprint

authentic

Turn a raw product, app, bot or feature idea into one evidence-backed build blueprint (researched stack, epics, Given/When/Then criteria, tests) that coding agents build one epic per session.

When to use

• Use when someone shares a product, app, bot or feature idea (even 2–3 lines) and wants a PRD, spec, backlog, epics, user stories, roadmap or MVP plan, even without saying "PRD".
• Use when the user wants deep web research, market research or competitor benchmarking before anything is built.
• Use when the user wants an architecture or tech-stack recommendation with justification and pinned versions, or code-quality and review standards for a new product.
• Use when the user asks for "a plan for Claude Code/Codex" that a coding agent can execute one epic at a time.
• Prefer it over lighter PRD skills when research depth, rigor or zero hallucination matters.
• Do not use it to review an existing PRD, to compare two frameworks in isolation, or to write a single piece of UX copy.

When not to use

• Needs web search to meet its no-hallucination bar. Without web access the blueprint is delivered with every external fact marked `[UNVERIFIED]` and a warning on the cover.
• A whole product typically takes 20–60 searches and a long writing phase, so it is slow and token-heavy compared with a quick PRD.
• Legal, tax and regulatory questions are flagged as Open Questions for a professional, never answered.
• The prebuilt localisation pack covers Iran; other markets get their localisation built from research during the run.
• `scripts/lint_blueprint.py` checks structure and cross-references, not whether the research is correct; the human read-through in Phase 4 is still required.
• The skill plans the build; the code is written later in separate coding sessions that follow the blueprint.

Skill page

Source