1---2name: prd3description: Purpose4---56## Purpose78Use this skill to lock scope before implementation starts.910## Trigger1112- Requirements are ambiguous or too broad13- Team needs measurable done criteria14- Scope creep risk is high1516## Workflow17181. Write a concise problem statement.192. Define in-scope and explicit non-goals.203. Define acceptance criteria with evidence requirements.214. Capture constraints and dependencies.225. Produce handoff notes for execution and verification.2324## Output Template2526```markdown27## Problem Statement28- ...2930## Scope / Non-goals31- ...3233## Acceptance Criteria34| Criterion | Evidence Needed | Owner |35| --- | --- | --- |3637## Constraints38- ...3940## Handoff41- ...42```
Run npx skillmds@latest add joonghyun-lee-frieren/prd in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.
Purpose It is listed under Product & Planning on SkillMD.
This skill has not completed SkillMD's automated safety review yet. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.
This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.
Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.
Joonghyun-Lee-Frieren (@joonghyun-lee-frieren) published this skill. Their other Agent Skills are listed on their SkillMD profile.