Help users articulate problems clearly before pursuing solutions, using frameworks from 91 product leaders.
Works with
Guides users through understanding current framing, identifying struggling moments, separating problems from solutions, and validating problem urgency
Covers eight core principles including avoiding the shiny object trap, prototyping to define problems, and spending more time on problem understanding than solution design
Includes diagnostic questions to uncover user context, wo
AI-first code editor with Composer
Before installing skills in Cursor, ensure your development environment meets these requirements:
node --versionproblem-definitionExecute the skills CLI command in your project's root directory to begin installation:
Fetches problem-definition from refoundai/lenny-skills and configures it for Cursor.
The CLI shows a list of agents. Use arrow keys and space to select Cursor:
Confirm successful installation by checking the skill directory location:
Restart Cursor to activate problem-definition. Access via /problem-definition in your agent's command palette.
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 environment. Always review source, verify the publisher, and test in isolation before production.
Submit your Claude Code skill and start earning
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
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
Evaluate features using frameworks (RICE, ICE, Kano) and create prioritized backlogs
Example
Score 20 feature ideas using RICE framework, generate prioritized roadmap with rationale
0
total installs
0
this week
616
GitHub stars
0
upvotes
Run in your terminal
0
installs
0
this week
616
stars
Help the user define problems clearly before jumping to solutions using frameworks from 91 product leaders.
When the user asks for help with problem definition:
Bret Taylor: "Why use this instead of the Yellow Pages? It was a digital version of something that had come before." Simply digitizing an analog predecessor often fails because it lacks a native reason to exist on the new platform. Ask "why should a customer give this the time of day?"
Jake Knapp + John Zeratsky: "This idea of getting unstuck and turning maybe some abstract ideas or some concepts that you've been discussing, turning that into a concrete prototype, something that you can look at and you can click around." Moving from abstract concepts to concrete prototypes is the fastest way to define and solve a problem.
Marily Nika: "There is something called the shiny object trap, and I'm always telling people, 'Hey, don't do AI for the sake of doing AI.' Make sure there is a problem there." Ensure AI (or any new technology) is used to solve a specific, validated user pain point rather than for its own sake.
Bob Moesta: "A struggling moment causes demand. And you start to realize that in some cases that struggling moment exists and can exist for a long time and nobody solved it." Demand is created by a specific "struggling moment" in a user's life, not by the product itself. Study the context that makes users' behavior rational.
Ryan Singer: "We are not going to start something unless we can see the end from the beginning. We're not going to take a big concept and then say, 'What's the estimate for this thing?'" Ensure the team can visualize the completed feature before committing resources. Avoid starting with fuzzy concepts.
Marty Cagan: "People don't buy the problem, they buy your solution. Obviously they don't buy it if it's not solving something they care about, but there are many products that are solving what they care about." While understanding the problem is necessary, competitive advantage comes from the quality of the solution. Don't over-rotate on problem validation if the problem is well-understood.
Christopher Lochhead: "Spend more time on the problem than the solution." Deeply understanding the customer's perspective of the problem is more valuable than internal product brainstorming. Listen to hear their perspective rather than just pitching your solution.
Christopher Miller: "I don't know that we even talk about problems without a qualifier. Are we talking about a business problem? Are we talking about a customer problem?" Effective problem definition requires distinguishing between business needs and customer pain points to avoid "customer-hostile" solutions.
For all 123 insights from 91 guests, see references/guest-insights.md
Make data-driven prioritization decisions faster
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
Prerequisites
Time Estimate
30-60 minutes to see productivity improvements
Steps
Common Pitfalls
✓ Do
✗ Don't
💡 Pro Tips
✓ 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.
mattpocock/skills
parcadei/continuous-claude-v3
cursor/plugins
ailabs-393/ai-labs-claude-skills
pproenca/dot-skills
mattpocock/skills
Useful defaults in problem-definition — fewer surprises than typical one-off scripts, and it plays nicely with `npx skills` flows.
Useful defaults in problem-definition — fewer surprises than typical one-off scripts, and it plays nicely with `npx skills` flows.
Solid pick for teams standardizing on skills: problem-definition is focused, and the summary matches what you get after install.
problem-definition has been reliable in day-to-day use. Documentation quality is above average for community skills.
problem-definition fits our agent workflows well — practical, well scoped, and easy to wire into existing repos.
Useful defaults in problem-definition — fewer surprises than typical one-off scripts, and it plays nicely with `npx skills` flows.
problem-definition has been reliable in day-to-day use. Documentation quality is above average for community skills.
problem-definition has been reliable in day-to-day use. Documentation quality is above average for community skills.
I recommend problem-definition for anyone iterating fast on agent tooling; clear intent and a small, reviewable surface area.
We added problem-definition from the explainx registry; install was straightforward and the SKILL.md answered most questions upfront.
showing 1-10 of 50