prd-development
Skill0 starsChanged 8 months agoMITView on GitHub
Guide PMs through structured PRD creation: problem framing, user research synthesis, solution definition, success criteria, and user stories. 8 phases over 2-4 days. Triggers: "write a PRD", "PRD for", "product requirements", "requirements document".
8 other projects use a version of this, 3 of them edited.
Adopted by
Most recently taken up by
- vijaysuperpositionist/skillsedited, first seen Nov 1, 2026
- deanpeters/Product-Manager-Skillstheir own version, first seen Oct 25, 2026
- The-Utopia-Studio/skillsedited, first seen Oct 13, 2026
- NinjaSln-labs/agent-skillsedited, first seen Oct 2, 2026
- ZeroTokenClaw/agents-skillstheir own version, first seen Sep 21, 2026
- agrivisionai/claude-skillstheir own version, first seen Jul 14, 2026
Used with
Projects with it also use company-intel.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
varunk130Skillcompany-intel
Deep research on any company by scanning their public website to extract customers, partners, case studies, testimonials, key metrics, and competitive positioning. Produces a polished 1-slide PowerPoint summary. Use when: research a company, find customers, who are their customers, company research, company overview, customer list, company intel, customer logos, competitive research on company, scan website for customers.
Also in 3 projects that use this
Other versions8 projects use a version of this.
Word for word · 0
None found.
Edited · 3
- The-Utopia-Studio/skills★ 611% same
- NinjaSln-labs/agent-skills★ 111% same
- vijaysuperpositionist/skills★ 011% same
Wrote their own version · 5
- deanpeters/Product-Manager-Skills★ 7.7ksame name
- DIAL-Studio/pm-agent-harness-kit★ 12same name
- agrivisionai/claude-skills★ 1same name
- nandanosql/all_in_one_pm_skills★ 1same name
- ZeroTokenClaw/agents-skills★ 1same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository20 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- ci-watchSkill
- commitSkill
- discovery-interview-prepSkill
- doc-generateSkill
- incident-responseSkill
- opportunity-solution-treeSkill
- polarisSkill
- prioritization-advisorSkill
- reviewSkill
- roadmapSkill
- security-auditSkill
- session-wrapSkill
- spec-updateSkill
- tddSkill
- tech-debt-auditSkill
- test-runnerSkill
- user-storySkill
- uxSkill
- workshop-facilitationSkill
The file
We split this skill into the rules it gives an agent
7 rules. 1 is common, 3 are distinctive, and 3 are very specific to this project.
1
Common
Most of the 8 edited versions we read keep these.
3
Distinctive
This author's own choices. Worth a look.
3
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 46
When running this workflow as a guided conversation, use workshop-facilitation as the interaction protocol.
- Common: line 54
Write first (forces clarity), refine last (after other sections complete)
- Very specific: line 59
Use discovery-interview-prep skill output if available
- Very specific: line 73
When context collection (Phases 1-4) is complete, read prd-development/phases-5-8.md for the output phases:
- Distinctive: line 156
Fix: Keep Phase 5 high-level; let design own UI details.
- Distinctive: line 160
Fix: Always define primary metric (what you're optimizing for) + guardrail metrics.
- Distinctive: line 163
Symptom: No section on what's NOT being built
“Common” is measured: kept by at least 6 in 10 of the 8 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Purpose
Guide product managers through structured PRD (Product Requirements Document) creation by orchestrating problem framing, user research synthesis, solution definition, and success criteria into a cohesive document. Use this to move from scattered notes and Slack threads to a clear, comprehensive PRD that aligns stakeholders and serves as a source of truth.
This is not a waterfall spec -- it's a living document that captures strategic context, customer problems, proposed solutions, and success criteria, evolving as you learn through delivery.
Key Concepts
PRD Structure (Standard Template)
# [Feature/Product Name] PRD
## 1. Executive Summary
## 2. Problem Statement
## 3. Target Users & Personas
## 4. Strategic Context
## 5. Solution Overview
## 6. Success Metrics (Primary / Secondary / Guardrail)
## 7. User Stories & Requirements
## 8. Out of Scope
## 9. Dependencies & Risks
## 10. Open QuestionsKey Concept: Guardrail Metrics
Beyond primary and secondary metrics, define guardrail metrics -- things that should NOT get worse:
- Example: "Sign-up conversion rate must not decrease" when adding onboarding friction
- Prevents tunnel vision on primary metric at the cost of other important metrics
Anti-Patterns
- Not a detailed spec: PRDs frame the problem and solution; they don't specify UI pixel-by-pixel
- Not waterfall: PRDs evolve as you learn; not frozen contracts
- Not a substitute for collaboration: PRDs complement conversation, not replace it
Facilitation Source of Truth
When running this workflow as a guided conversation, use workshop-facilitation as the interaction protocol.
Application
This workflow orchestrates 8 phases over 2-4 days.
Phase 1: Executive Summary (30 min)
- Format: "We're building [solution] for [persona] to solve [problem], which will result in [impact]."
- Write first (forces clarity), refine last (after other sections complete)
Phase 2: Problem Statement (60 min)
- Frame the customer problem with evidence
- Include: Who has this problem? What is it? Why is it painful? Evidence (quotes, data, tickets)
- Use
discovery-interview-prepskill output if available
Phase 3: Target Users & Personas (30 min)
- Define primary and secondary personas
- Include: role, goals, pain points, behaviors, tech savviness
Phase 4: Strategic Context (45 min)
- Link to business goals (OKRs)
- Market opportunity (TAM/SAM/SOM if applicable)
- Competitive landscape
- "Why now?" rationale
Phases 5-8: Output Phases
When context collection (Phases 1-4) is complete, read prd-development/phases-5-8.md for the output phases:
- Phase 5: Solution Overview (60 min)
- Phase 6: Success Metrics (30 min)
- Phase 7: User Stories & Requirements (90-120 min)
- Phase 8: Out of Scope & Dependencies (30 min)
Workflow Timeline
Day 1:
|- Phase 1: Executive Summary (30 min)
|- Phase 2: Problem Statement (60 min)
|- Phase 3: Target Users & Personas (30 min)
|- Phase 4: Strategic Context (45 min)
Day 2:
|- Phase 5: Solution Overview (60 min)
|- Phase 6: Success Metrics (30 min)
|- Phase 7: User Stories & Requirements (90-120 min)
Day 3:
|- Phase 8: Out of Scope & Dependencies (30 min)
|- Review & Refine (60 min)
Day 4 (Optional):
|- Stakeholder Review & ApprovalTime estimates:
- Fast track: 1.5-2 days (straightforward feature, clear requirements)
- Typical: 2-3 days (includes discovery synthesis, stakeholder review)
- Complex: 3-4 days (major initiative, multiple personas)
Examples
Example: Problem Statement Section
## 2. Problem Statement
### Who has this problem?
Non-technical small business owners who sign up for our SaaS product.
### What is the problem?
60% of users abandon onboarding within 24 hours because they see an empty
dashboard with no guidance.
### Evidence
- Interviews: 8/10 churned users said "I didn't know what to do first"
- Analytics: 60% of signups complete 0 actions within 24 hours
- Support: "How do I get started?" is #1 question (350 tickets/month)
- Quote: "I logged in, saw an empty dashboard, and thought 'now what?'"Example: Success Metrics Section
## 6. Success Metrics
### Primary Metric
Activation rate (% users completing first action within 24h): 40% -> 60%
### Secondary Metrics
- Time-to-first-action: 3 days -> 1 day
- Checklist completion rate: 80%
- Support tickets "How to start?": 350/mo -> 175/mo
### Guardrail Metrics
- Sign-up conversion rate: maintain at 10% (don't add friction)Common Pitfalls
Pitfall 1: PRD Written in Isolation
Symptom: PM writes PRD alone, presents finished doc Fix: Collaborate with design + eng on Phase 7 (user stories). Review draft before finalizing.
Pitfall 2: No Evidence in Problem Statement
Symptom: "We believe users have this problem" (no data, no quotes) Fix: Include customer quotes, analytics, support tickets. Run discovery first if needed.
Pitfall 3: Solution Too Prescriptive
Symptom: PRD specifies exact UI, pixel dimensions, button colors Fix: Keep Phase 5 high-level; let design own UI details.
Pitfall 4: No Success Metrics
Symptom: PRD defines problem + solution but no metrics Fix: Always define primary metric (what you're optimizing for) + guardrail metrics.
Pitfall 5: Out of Scope Not Documented
Symptom: No section on what's NOT being built Fix: Explicitly document out of scope in Phase 8 to prevent scope creep.
References
Related Skills
user-story-- User stories with acceptance criteria (Phase 7)discovery-interview-prep-- Validates problem statement (Phase 2)prioritization-advisor-- Helps prioritize features in roadmap contextopportunity-solution-tree-- Generates solution hypotheses (pre-PRD)
External Frameworks
- Martin Eriksson, "How to Write a Good PRD" (2012)
- Marty Cagan, Inspired (2017)
- Amazon, "Working Backwards" (PR/FAQ format)
Credit
- Adapted from Dean Peters, Product Manager Skills (CC BY-NC-SA 4.0).
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.

