deliver-prd
Creates a comprehensive Product Requirements Document that aligns stakeholders on what to build, why, and how success will be measured. Use when specifying features, epics, or product initiatives for engineering handoff.
product-on-purpose · AI review on file
Installation
Read the source and dependencies before running a command. Copying does not install or execute anything.
npx skills add product-on-purpose/pm-skills --skill deliver-prdAbout this skill
name: deliver-prd description: Creates a comprehensive Product Requirements Document that aligns stakeholders on what to build, why, and how success will be measured. Use when specifying features, epics, or product initiatives for engineering handoff. license: Apache-2.0 metadata: phase: deliver version: "3.0.0" updated: 2026-08-21 category: specification frameworks: [triple-diamond, lean-startup, design-thinking] author: product-on-purpose
Product Requirements Document (PRD)
A Product Requirements Document is the primary specification artifact that communicates what to build and why. It bridges the gap between problem understanding and engineering implementation by providing clear requirements, success criteria, and scope boundaries. A good PRD enables engineering to build the right thing while maintaining flexibility on implementation details.
When to Use
- After problem and solution alignment, before engineering work begins
- When specifying features, epics, or product initiatives for handoff
- When multiple teams need to coordinate on a shared deliverable
- When stakeholders need to approve scope before investment
- As reference documentation during development and QA
When NOT to Use
- The problem is still unframed or contested -> use
define-problem-statementfirst; a PRD assumes an agreed problem - You need a one-page pitch to align stakeholders on an approach -> use
develop-solution-brief; the PRD comes after that alignment - You only need the work broken into tickets for a sprint -> use
deliver-user-stories - You are recording a technical or architectural decision -> use
develop-adr
Instructions
When asked to create a PRD, follow these steps:
-
Summarize the Problem Start with a brief recap of the problem being solved. Link to the problem statement if available. Ensure readers understand why this work matters before diving into what to build.
-
Define Goals and Success Metrics Articulate what success looks like. Include specific, measurable metrics with baselines and targets. These metrics should connect directly to the problem being solved.
-
Outline the Solution Describe the proposed solution at a high level. Focus on user-facing functionality and key capabilities. Include enough detail for stakeholders to evaluate the approach without over-specifying implementation.
-
Detail Functional Requirements Break down what the system must do. Use user stories or requirement statements. Each requirement should be testable - someone should be able to verify if it's met.
-
Link AI Behavior to Evidence (only when the feature's output comes from a model) Skip this step entirely for deterministic features. When a model produces the output, the behavior varies run to run, so "it works" is a claim that needs evidence attached. Name the behaviors that are requirements of this release and, for each one, how it will be shown to hold and at what threshold. Refusal and abstention get their own rows: a model has no dependable default for either, so what the feature does when it should not answer is a requirement, not an implementation detail. Score each component of a multi-step feature separately, because an end-to-end pass rate hides which step failed. State how the case set was sized as a method, never as a borrowed number.
-
Define Scope Boundaries Explicitly state what's in scope, out of scope, and deferred to future iterations. Clear scope prevents scope creep and sets realistic expectations.
-
Address Technical Considerations Note any technical constraints, architectural decisions, or integration requirements. Don't design the system, but surface considerations engineering needs to know.
-
Write the Agent Execution Contract (only when an executor will implement this without the authoring context) Skip this step entirely when the implementers were in the room. A coding agent, an outside contractor, or a team picking this up cold cannot infer what you already know, so declare it: which sources are authoritative and which wins when two disagree, what must not be touched and why, how each FR-n is verified and by whom, and the conditions where the executor must stop and escalate rather than decide. Name an owner for every escalation; an escalation with no addressee becomes a guess. A requirement with no verification is not ready to hand off, because nothing distinguishes "done" from "the executor believes it is done".
-
Identify Dependencies and Risks List external dependencies, assumptions, and risks that could impact delivery. Include mitigation strategies where applicable.
-
Propose Timeline and Milestones Outline key phases and checkpoints. This helps stakeholders understand the delivery plan without committing to specific dates prematurely.
Project Memory Contract
Active only when .claude/pm-skills.local.md exists. With no file, ignore this section entirely
and behave exactly as described above.
- Reads:
active_initiative, and anyinterpretationartifacts recording personas or research findings. Use them instead of asking for context that has already been produced. If none exist, ask as normal and never invent a persona to fill the gap. - Writes: the PRD as a
decisionartifact, and its committed scope boundaries and success metrics to the## Decisionssection. - Posture: propose the entry and wait for confirmation before writing, unless
memory_auto_append: trueis set, in which case append and echo what was written. - Write discipline: re-read the file immediately before writing, never from the copy that produced the proposal. If it changed in between, merge your entry into the current state and re-propose rather than overwriting; add only your own entry and leave every other field and section byte-identical. Nothing enforces