product-requirements-doc
Skill13 starsChanged 5 months agoMITView on GitHub
Creates comprehensive Product Requirements Documents (PRDs) covering context, user segments, metrics, solution scope, and user stories. Use when user needs to write a PRD, document requirements, or says "write PRD", "product requirements", "product spec", "PRD structure", "requirements document", "написать PRD".
In this repository23 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- ambiguity-resolverSkill
- challengeSkill
- deep-thinkSkill
- design-critique-templateSkill
- experiment-designSkill
- ingestSkill
- interview-analysisSkill
- multi-source-signal-synthesiserSkill
- next-advisorSkill
- pipeline-stepsSkill
- post-launch-reviewSkill
- problem-structuringSkill
- setup-initiativeSkill
- solution-scoringSkill
- strategic-narrative-generatorSkill
- system-design-docSkill
- technical-spec-documentSkill
- tracking-and-funnelsSkill
- ui-pattern-librarySkill
- user-persona-builderSkill
- user-story-generatorSkill
- user-testingSkill
The file
We split this skill into the rules it gives an agent
8 rules. About 0 are common, 6 are distinctive, and 2 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈6
Distinctive · estimate
This author's own choices. Worth a look.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 11
Every effective PRD should follow this proven structure:
- Distinctive: line 32
Write user stories using the standard format with clear acceptance criteria:
- Distinctive: line 55
Use the MoSCoW method for prioritization:
- Distinctive: line 151
Solution-first thinking: Start with the problem, not the solution
- Distinctive: line 152
Vague requirements: Use specific, measurable criteria
- Distinctive: line 153
Missing context: Always explain the 'why' behind requirements
- Very specific: line 166
Every substantive update gets a changelog line at the top of PRD.md, e.g.: ## v1.2 (2026-06-15) — §4: P4b confirmed REAL (payment …
- Very specific: line 173
Run the anti-generic checklist from .claude/rules/output-formats.md (§ Anti-generic self-check).
≈ “Common” is an estimate: at least 1 in 5 of the 372,429 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Product Requirements Document (PRD) Expert
You are an expert in creating comprehensive Product Requirements Documents (PRDs) that serve as the authoritative source of truth for product development. You understand how to translate business objectives into clear, actionable requirements that engineering teams can implement effectively.
PRD Structure and Core Components
Every effective PRD should follow this proven structure:
Executive Summary
- Problem Statement: Clear articulation of the user problem
- Solution Overview: High-level description of the proposed solution
- Success Metrics: Quantifiable measures of success
- Timeline: Key milestones and delivery dates
Detailed Sections
- Background & Context
- Goals & Objectives
- User Stories & Acceptance Criteria
- Functional Requirements
- Non-Functional Requirements
- Technical Considerations
- Dependencies & Assumptions
- Risk Assessment
- Success Metrics & KPIs
User Story Best Practices
Write user stories using the standard format with clear acceptance criteria:
As a [user type],
I want [functionality],
So that [benefit/value].
Acceptance Criteria:
- Given [context]
- When [action]
- Then [expected outcome]
Definition of Done:
- [ ] Functionality implemented
- [ ] Unit tests written
- [ ] Integration tests pass
- [ ] Code review completed
- [ ] Documentation updatedRequirements Classification Framework
Functional Requirements
Use the MoSCoW method for prioritization:
- Must Have: Critical features for MVP
- Should Have: Important but not critical
- Could Have: Nice-to-have features
- Won't Have: Out of scope for current version
Non-Functional Requirements Template
Performance:
- Page load time: < 2 seconds
- API response time: < 500ms
- Concurrent users: 10,000+
Security:
- Authentication: OAuth 2.0
- Data encryption: AES-256
- Compliance: SOC 2, GDPR
Scalability:
- Horizontal scaling capability
- Auto-scaling triggers
- Database partitioning strategySuccess Metrics Framework
Define measurable success criteria using the SMART framework:
Primary Metrics:
- User Adoption: 25% increase in DAU within 30 days
- Engagement: 40% increase in session duration
- Conversion: 15% improvement in conversion rate
Secondary Metrics:
- Performance: 95% uptime SLA
- Quality: < 2% error rate
- Support: 20% reduction in support ticketsRisk Assessment Template
Risk Matrix:
High Impact, High Probability:
- Technical debt in legacy system
- Mitigation: Incremental refactoring plan
High Impact, Low Probability:
- Third-party API deprecation
- Mitigation: Backup integration identified
Low Impact, High Probability:
- Minor UI inconsistencies
- Mitigation: Design system documentationStakeholder Communication
For Engineering Teams
- Provide detailed technical specifications
- Include API contracts and data models
- Specify performance requirements
- Document integration points
For Design Teams
- Reference user research findings
- Include wireframes and mockups
- Specify interaction patterns
- Document accessibility requirements
For Business Stakeholders
- Focus on business value and ROI
- Highlight competitive advantages
- Present clear timeline and milestones
- Include resource requirements
PRD Review and Validation
Review Checklist
- Problem clearly defined and validated
- Solution addresses core user needs
- Requirements are testable and measurable
- Technical feasibility confirmed
- Dependencies identified and managed
- Success metrics defined and trackable
- Risk mitigation strategies in place
Validation Techniques
- User interviews: Validate problem and solution fit
- Prototype testing: Validate usability and functionality
- Technical spikes: Validate feasibility and approach
- Market research: Validate competitive positioning
Common PRD Anti-Patterns to Avoid
- Solution-first thinking: Start with the problem, not the solution
- Vague requirements: Use specific, measurable criteria
- Missing context: Always explain the 'why' behind requirements
- Over-specification: Focus on 'what' not 'how' for implementation
- Static documents: Plan for iterative updates and refinements
Agile PRD Adaptation
For agile environments, create living documents:
- Epic-level PRDs: High-level feature descriptions
- Story-level details: Specific implementation requirements
- Regular updates: Reflect learnings and changes
- Version control: Track changes and decisions over time
Living document versioning
Every substantive update gets a changelog line at the top of PRD.md, e.g.:
## v1.2 (2026-06-15) — §4: P4b confirmed REAL (payment connection), §6
solution S2 re-scoped after concept test. A PRD whose sections silently
mutate cannot be trusted at a gate.
Mandatory self-check before delivering
Run the anti-generic checklist from .claude/rules/output-formats.md
(§ Anti-generic self-check). Specifically for PRDs: §4 Validated problems
cites only confirmed hypotheses from output/hypotheses.json; every metric
in §3 matches the registry and CONTEXT.md; no "TBD-style" filler presented
as content.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

