This walks you through creating a PRD by asking questions one at a time, adapting to whether you're a vibe-coder with limited experience, a seasoned developer, or somewhere in between. It checks for existing research docs first, then guides you through defining your product, users, must-have features, and success metrics with different question sets per skill level. The verification echo at the end confirms understanding before generating a structured PRD document. What I like is the session continuity feature that reuses prior context instead of making you restart from scratch. It's Step 2 in a larger vibe-coding workflow, sitting between research and technical design. The level-specific questioning is smart, though developers comfortable writing their own PRDs might find it prescriptive.
- skills.sh installs
- 185
- GitHub stars
- 3.2K
- last updated
- Apr 19, 2026
Install
$ npx -y skills add khazp/vibe-coding-prompt-template --skill vibe-prd --agent claude-codeInstalls into .claude/skills of the current project.
Files
Product requirements
Use existing research, the user's request, and Handoff Context to define the product outcome. Do not repeat an interview whose answers are already known. Ask only for unresolved requirements that affect scope or acceptance; make reversible assumptions explicit and continue when the brief is sufficient.
Write a PRD proportional to the product. Cover the target user and problem, the core journey, MVP scope, out-of-scope work, meaningful failure states, constraints, and observable acceptance criteria. Include AI, accounts, payments, analytics, compliance, or automation only when the product needs them.
For a small project, a short document is enough. For a complex one, clarify dependencies and consequential decisions before they block implementation. Avoid fixed feature counts, mandatory personas, or market research that does not change the product decision. Distinguish agreed facts from assumptions.
Sponsors
Details
- Repository
- github.com/khazp/vibe-coding-prompt-template
- Categories
- AI & Agent Building, Productivity & Planning
- License
- MIT
- First seen
- Jun 11, 2026
