How do I install the Prd skill?

Run npx skillmds@latest add clairem0/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.

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.

Which AI agents work with Prd?

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.

clairem0 (@clairem0) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Prd by clairem0 — Agent Skill

Name: Prd
Author: clairem0

Prd

Create a concise product requirements document or specification from conversation and repository evidence. Use when the user asks for a PRD, feature definition, product spec, or product-and-engineering plan before implementation breakdown.

clairem0 94c123d 2.4 KB Updated Sep 17, 2026

File contents

PRD

Turn settled direction into a concise product contract that can govern implementation.

Synthesize: Preserve settled decisions from the conversation. Inspect current behavior, docs, code, and tests as needed to replace assumptions with evidence and use the project's language.
Ground: Define the actual user and problem. Trace each key journey from trigger or root cause through product state and experience to a successful next or recovery action.
Decide: State the desired outcome, scope, non-goals, proposed behavior, and important tradeoffs. Distinguish facts, decisions, assumptions, and unresolved questions.
Shape: Identify existing public interfaces, ownership seams, sequencing constraints, and risky assumptions. Reuse existing concepts and states; add new ones only when real journeys require them.
Prove: Write acceptance criteria as observable user or system behavior. Define validation through relevant public interfaces and real product journeys.
Resolve: Ask only when a missing decision would materially change the PRD. Ask one concise question at a time with a recommended answer.
Confirm: Review the proposed shape and key decisions with the user before saving it.
Record: Preserve an existing local PRD format; otherwise use the contract below in the repository's natural specifications location.

PRD Contract

Problem and user: Who is affected, what happens today, and why it matters
Outcome: What should become true
Current journeys: Real triggers, states, experiences, and recovery paths
Proposed behavior: The product experience and system response
Scope and decisions: In scope, out of scope, tradeoffs, and governing decisions
Engineering shape: Existing seams, sequencing constraints, risks, and assumptions
Acceptance and proof: Observable completion criteria and validation
Open decisions: Only questions that block a reliable implementation plan

Stop before implementation decomposition. The PRD is ready when another agent or collaborator can plan the next tranche without reopening product direction.

---name: prddescription: Create a concise product requirements document or specification from conversation and repository evidence. Use when the user asks for a PRD, feature definition, product spec, or product-and-engineering plan before implementation breakdown.---# PRDTurn settled direction into a concise product contract that can govern implementation.- **Synthesize:** Preserve settled decisions from the conversation. Inspect current behavior, docs, code, and tests as needed to replace assumptions with evidence and use the project's language.- **Ground:** Define the actual user and problem. Trace each key journey from trigger or root cause through product state and experience to a successful next or recovery action.- **Decide:** State the desired outcome, scope, non-goals, proposed behavior, and important tradeoffs. Distinguish facts, decisions, assumptions, and unresolved questions.- **Shape:** Identify existing public interfaces, ownership seams, sequencing constraints, and risky assumptions. Reuse existing concepts and states; add new ones only when real journeys require them.- **Prove:** Write acceptance criteria as observable user or system behavior. Define validation through relevant public interfaces and real product journeys.- **Resolve:** Ask only when a missing decision would materially change the PRD. Ask one concise question at a time with a recommended answer.- **Confirm:** Review the proposed shape and key decisions with the user before saving it.- **Record:** Preserve an existing local PRD format; otherwise use the contract below in the repository's natural specifications location.## PRD Contract- **Problem and user:** Who is affected, what happens today, and why it matters- **Outcome:** What should become true- **Current journeys:** Real triggers, states, experiences, and recovery paths- **Proposed behavior:** The product experience and system response- **Scope and decisions:** In scope, out of scope, tradeoffs, and governing decisions- **Engineering shape:** Existing seams, sequencing constraints, risks, and assumptions- **Acceptance and proof:** Observable completion criteria and validation- **Open decisions:** Only questions that block a reliable implementation planStop before implementation decomposition. The PRD is ready when another agent or collaborator can plan the next tranche without reopening product direction.

Frequently asked questions

Prd

File contents

PRD

PRD Contract

Related skills

Frequently asked questions

How do I install the Prd skill?

What does the Prd skill do?

Is Prd safe to use?

Which AI agents work with Prd?

Is Prd free to use?

Who published Prd?