← ClaudeAtlas

product-requirements-doclisted

Optional PRD methodology — loaded by the questioner agent when a feature request is vague or complex enough to warrant a structured product spec alongside task.md. Produces a PRD artifact that downstream design-author work can ground decisions in.
bostonaholic/team · ★ 11 · Web & Frontend · score 75
Install: claude install-skill bostonaholic/team
# Product Requirements Document A PRD translates a vague or complex feature request into a structured artifact that complements `task.md`. The questioner produces it when intent is rich enough to need explicit scope, acceptance criteria, and constraints, rather than a one-page task summary alone. The goal is precision, not exhaustive documentation: clear scope, unambiguous acceptance criteria, and explicit boundaries that prevent scope creep when the design-author later turns the task into an approach. Write the prose this skill governs at a seventh-grade reading level, in STE-flavored mode — short sentences, common words, no unexplained jargon. Full methodology: `writing-prose`. Before you finalize prose this skill governs, call the Skill tool with `writing-prose` and apply its `## Self-lint` checklist. ## When to Write a PRD The questioner produces a PRD (in addition to the standard `task.md` and `questions.md`) when the feature request is: - **Vague or underspecified** — the request does not say what "done" looks like ("improve the onboarding experience" has no clear scope boundary) - **Complex with multiple user stories** — more than one user type, more than one distinct workflow, or multiple independent but related capabilities - **Cross-cutting** — the feature touches multiple subsystems and the interaction between them needs explicit specification - **Replacing or significantly changing existing behavior** — where the scope of "existing" needs to be defin