amazon-working-backwards▌
robdefeo/agent-skills · updated May 12, 2026
MDX-style export adds YAML metadata + attribution linking explainx.ai and this canonical listing URL.
Guide ideas through Amazon's Working Backwards process, from 5 Questions to PR-FAQ.
- ›Supports six entry points: drafting 5Q answers from a rough idea, refining existing answers, verifying answers with probing questions, generating a PR-FAQ document, reviewing an existing PR-FAQ, or clarifying any process element
- ›The 5 Questions phase forces clarity on customer, problem, benefit, validation, and experience before any document writing
- ›The PR-FAQ phase transforms solid 5Q answers into a
Amazon Working Backwards
The Working Backwards process moves from idea to PR-FAQ in two phases: first answer the 5 Questions to force clarity of thinking, then write a PR-FAQ document that brings the idea to life for readers.
Workflow
Determine the entry point based on what the user provides:
Starting from a rough idea or proposal? → Follow the "5 Questions Phase" below Have 5Q answers to refine/verify? → Read references/five-questions-guide.md and apply the verification checklist Ready to write a PR-FAQ? → Follow the "PR-FAQ Phase" below Have a PR-FAQ to review? → Read references/prfaq-template.md and evaluate against the writing standards and common rejection reasons Want to clarify a specific element? → Read the relevant reference file for that phase
Output Convention
Always write to a file from the start. Do not draft in chat.
- 5Q answers: Write to
YYYY-MM-DD - [Product Name] 5Q.md - PR-FAQ: Write to
YYYY-MM-DD - [Product Name] PR-FAQ.md - Iterations: Edit the file in place; summarize changes in chat
- Word format: If the user requests .docx, use the
docxskill to produce a formatted document
When asking clarifying questions or presenting feedback, respond in chat. All substantive content (5Q answers, PR-FAQ drafts) goes to file.
5 Questions Phase
The 5 Questions force clarity before any document writing begins:
- Who is the customer?
- What is the customer problem or opportunity?
- What is the most important customer benefit?
- How do we know what the customer needs or wants?
- What does the customer experience look like?
Drafting 5Q Answers
- Read references/five-questions-guide.md for the quality bar and pitfalls for each question
- Read references/examples.md to see a worked example from idea through 5Q to PR-FAQ
- Ask clarifying questions if the user's idea is too vague to answer any question well — ask one question at a time
- Draft all 5 answers, following the "What a strong answer looks like" guidance for each
- Write answers to the 5Q file; summarize in chat and ask for feedback; iterate by editing the file
Verifying 5Q Answers
When reviewing or verifying answers (user's own or previously drafted):
- Read references/five-questions-guide.md
- Apply the verification checklist (coherence, specificity, customer obsession, intellectual honesty)
- Use the probing questions from the guide to challenge weak areas
- Present specific, actionable feedback — not generic praise
PR-FAQ Phase
Once 5Q answers are solid, generate the PR-FAQ document.
- Read references/prfaq-template.md for the exact structure and quality bar
- Read references/examples.md if not already loaded
- Write the Press Release section, mapping: Q2 → problem paragraph, Q3 → solution paragraph, Q5 → experience paragraph, Q1 → customer quote persona
- Write External FAQ (5-10 customer questions)
- Write Internal FAQ (5-10 stakeholder questions)
- Write to the PR-FAQ file; summarize in chat and ask for feedback; iterate by editing the file
Reviewing an Existing PR-FAQ
- Read references/prfaq-template.md, paying attention to the "Common Rejection Reasons" section
- Evaluate each section of the PR-FAQ against the writing standards
- Check that the PR-FAQ is internally consistent (problem → benefit → experience alignment)
- Provide specific, section-by-section feedback with concrete suggestions for improvement
How to use amazon-working-backwards on Cursor
AI-first code editor with Composer
Prerequisites
Before installing skills in Cursor, ensure your development environment meets these requirements:
- ›Cursor installed and configured on your development machine
- ›Node.js version 16.0+ with npm package manager (verify with
node --version) - ›Active project directory or workspace where you want to add amazon-working-backwards
Execute installation command
Execute the skills CLI command in your project's root directory to begin installation:
The skills CLI fetches amazon-working-backwards from GitHub repository robdefeo/agent-skills and configures it for Cursor.
Select Cursor when prompted
The CLI will show a list of available agents. Use arrow keys to navigate and space to select Cursor:
Verify installation
Confirm successful installation by checking the skill directory location:
Reload or restart Cursor to activate amazon-working-backwards. Access the skill through slash commands (e.g., /amazon-working-backwards) or your agent's skill management interface.
Security & Verification Notice
We perform automated surface-level scans (Gen AI Scanner, Socket, Snyk) during installation. These checks detect common vulnerabilities but do not guarantee complete security. Always review skill source code and verify the publisher's reputation before production use.
Skills execute code in your development environment. Always verify the publisher's identity, review recent commits, and test in isolated environments before production deployment.
List & Monetize Your Skill
Submit your Claude Code skill and start earning
Use Cases▌
User Story & Requirements Generation
Create detailed user stories, acceptance criteria, and feature specs
Example
Generate user stories for 'password reset feature' with acceptance criteria, edge cases, and test scenarios
Reduce spec writing time by 50%, ensure comprehensive coverage
Competitive Analysis
Research competitors, compare features, identify gaps
Example
Analyze 5 competitor products, create feature comparison matrix, suggest differentiation opportunities
Complete competitive research in 2 hours instead of 2 days
Roadmap Prioritization
Evaluate features using frameworks (RICE, ICE, Kano) and create prioritized backlogs
Example
Score 20 feature ideas using RICE framework, generate prioritized roadmap with rationale
Make data-driven prioritization decisions faster
Stakeholder Communication
Draft PRDs, status updates, and stakeholder presentations
Example
Create executive summary of Q3 roadmap, monthly progress report, feature launch announcement
Save 3-5 hours/week on communication overhead
Implementation Guide▌
Prerequisites
- ›Claude Desktop or compatible AI client
- ›Access to product documentation and roadmap tools (Jira, Notion, etc.)
- ›Understanding of product management frameworks (RICE, Jobs-to-be-Done, etc.)
- ›Stakeholder contact information and communication channels
Time Estimate
30-60 minutes to see productivity improvements
Installation Steps
- 1.Install product management skill
- 2.Start with user story generation for known feature
- 3.Progress to competitive analysis: research 2-3 competitors
- 4.Use for roadmap prioritization: apply RICE/ICE scoring
- 5.Draft stakeholder communications and refine based on feedback
- 6.Build template library for recurring PM tasks
- 7.Share effective prompts with product team
Common Pitfalls
- ⚠Not validating competitive research—verify facts before sharing
- ⚠Accepting user stories without involving engineering team
- ⚠Over-relying on frameworks without qualitative judgment
- ⚠Not customizing outputs to company culture and communication style
- ⚠Skipping stakeholder validation of generated requirements
Best Practices▌
✓ Do
- +Validate research and competitive analysis with real data
- +Collaborate with engineering when generating technical requirements
- +Customize frameworks and templates to your company context
- +Use skill for first drafts, refine with stakeholder input
- +Document successful prompt patterns for PM tasks
- +Combine AI efficiency with human judgment and intuition
✗ Don't
- −Don't publish competitive analysis without fact-checking
- −Don't finalize user stories without engineering review
- −Don't make prioritization decisions solely on AI scoring
- −Don't skip customer validation of generated requirements
- −Don't ignore company-specific context and culture
💡 Pro Tips
- ★Provide context: company goals, constraints, customer feedback
- ★Ask for alternatives: 'Show 3 ways to prioritize this roadmap'
- ★Request stakeholder-specific formatting: 'Executive summary vs. engineering spec'
- ★Use skill for 70% generation + 30% customization to company needs
When to Use This▌
✓ Use When
Use for user story writing, competitive research, roadmap prioritization, stakeholder communication, and PRD drafting. Best for reducing repetitive documentation and research work.
✗ Avoid When
Avoid for strategic product vision (requires deep customer empathy), pricing decisions (needs market and financial expertise), or when face-to-face customer discovery is more valuable than speed.
Learning Path▌
- 1Basic: user stories, feature specs, status updates
- 2Intermediate: competitive analysis, prioritization frameworks, PRDs
- 3Advanced: product strategy, go-to-market planning, OKR setting
- 4Expert: product vision, market positioning, business model innovation
Discussion
Product Hunt–style comments (not star reviews)- No comments yet — start the thread.
Ratings
4.7★★★★★57 reviews- ★★★★★Ganesh Mohane· Dec 24, 2024
Solid pick for teams standardizing on skills: amazon-working-backwards is focused, and the summary matches what you get after install.
- ★★★★★Kwame Choi· Dec 16, 2024
I recommend amazon-working-backwards for anyone iterating fast on agent tooling; clear intent and a small, reviewable surface area.
- ★★★★★Lucas Singh· Dec 12, 2024
amazon-working-backwards has been reliable in day-to-day use. Documentation quality is above average for community skills.
- ★★★★★Shikha Mishra· Dec 4, 2024
amazon-working-backwards reduced setup friction for our internal harness; good balance of opinion and flexibility.
- ★★★★★Mia Gupta· Dec 4, 2024
Keeps context tight: amazon-working-backwards is the kind of skill you can hand to a new teammate without a long onboarding doc.
- ★★★★★Lucas Sanchez· Nov 23, 2024
I recommend amazon-working-backwards for anyone iterating fast on agent tooling; clear intent and a small, reviewable surface area.
- ★★★★★Sakshi Patil· Nov 15, 2024
We added amazon-working-backwards from the explainx registry; install was straightforward and the SKILL.md answered most questions upfront.
- ★★★★★Lucas Shah· Nov 7, 2024
Keeps context tight: amazon-working-backwards is the kind of skill you can hand to a new teammate without a long onboarding doc.
- ★★★★★Henry Agarwal· Nov 7, 2024
amazon-working-backwards reduced setup friction for our internal harness; good balance of opinion and flexibility.
- ★★★★★Hana Ghosh· Nov 3, 2024
amazon-working-backwards fits our agent workflows well — practical, well scoped, and easy to wire into existing repos.
showing 1-10 of 57