product-discovery
Skill4 starsChanged 3 months agoMITView on GitHub
Execute product discovery. Use when framing new problems, mapping actors, or synthesizing initial product hypotheses.
24 other projects use a version of this.
Adopted by
Most recently taken up by
- peterbamuhigire/chwezi-dev-enginetheir own version, first seen Nov 15, 2026
- darkweb19/skillstheir own version, first seen Nov 8, 2026
- snowfluke/tech-lead-skillstheir own version, first seen Nov 8, 2026
- ceeinbeta/pm-skillstheir own version, first seen Nov 1, 2026
- mcveloria/pm-skillstheir own version, first seen Oct 25, 2026
- vindreshsingh/engineering-skillstheir own version, first seen Oct 20, 2026
Other versions24 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 24
- magnus919/agent-skills★ 177same name
- nahid-sparktales/agent-dispatcher★ 59same name
- ncklrs/startup-os-skills★ 51same name
- peterbamuhigire/chwezi-dev-engine★ 31same name
- yannickYamo/skills★ 23same name
- Hassaan146/claude-skills★ 18same name
- ipavelm/ultimate-product-discovery-skill★ 15same name
- snowfluke/my-tech-lead-flow★ 8same name
- snowfluke/tech-lead-skills★ 8same name
- dkpapadopoulos/auto-claude-skills★ 6same name
14 more not listed
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 repository46 other files it gives its agents.
- accessibility-reviewSkill
- accessibility-runtime-auditSkill
- adaptive-component-behaviorSkill
- ai-feature-ux-patternsSkill
- behavioral-pricing-psychologySkill
- business-model-readingSkill
- business-model-thinkingSkill
- cognitive-load-heatmap-predictionSkill
- component-style-guideSkill
- cross-functional-reviewSkill
- dark-mode-theming-systemSkill
- dashboard-layout-patternsSkill
- dashboard-scaffolding-contractSkill
- design-drift-detectorSkill
- design-system-builderSkill
- design-to-code-handoffSkill
- design-tokensSkill
- error-boundary-resilience-designSkill
- flow-based-functional-testingSkill
- growth-impact-reviewSkill
- i18n-localization-strategySkill
- information-architectureSkill
- interactive-element-auditSkill
- kinematic-motion-choreographySkill
- micro-interaction-motion-designSkill
- module-registry-syncSkill
- mvp-scopingSkill
- perceived-performance-loadingSkill
- prd-traceability-matrixSkill
- product-strategySkill
- project-health-diagnosticsSkill
- qa-feedback-loop-orchestratorSkill
- responsive-breakpoint-strategySkill
- responsive-qa-auditSkill
- route-integrity-checkerSkill
- security-privacy-reviewSkill
- stakeholder-requirement-mappingSkill
- touch-gesture-interactionSkill
- typography-systemSkill
- usability-heuristics-checkSkill
- user-flow-mappingSkill
- user-research-synthesisSkill
- ux-chaos-monkeySkill
- visual-hierarchy-reviewSkill
- visual-responsive-regression-testingSkill
- visual-style-extractorSkill
The file
We split this skill into the rules it gives an agent
2 rules. 0 are common, 2 are distinctive, and 0 are very specific to this project.
0
Common
Most of the 22 edited versions we read keep these.
2
Distinctive
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 22
Document what users do *today* without your product: spreadsheets, WhatsApp groups, manual copy-pasting, custom scripts.
- Distinctive: line 36
Before committing engineering resources, define test mechanisms to validate riskiest assumptions:
“Common” is measured: kept by at least 6 in 10 of the 22 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
Product Discovery
Product discovery surfaces the bedrock truth of user pain before writing a single line of code. Everything built on false premises rots.
1. Frame the problem with Jobs-to-be-Done (JTBD)
State the core struggle without referencing potential features or technologies:
- Format as JTBD:
"When I [struggling situation], I want to [motivation/progress], so I can [expected functional and emotional outcome]." - Differentiate between the functional job ("send invoices"), the emotional job ("feel confident I am not being cheated"), and the social job ("look professional to clients").
- For live or simulated user interviews, utilize structured prompts from INTERVIEW-TEMPLATES.md.
2. Map the actors & decision dynamics
Identify every role interacting with or affected by the workflow:
| Persona / Role | Core Goal | Primary Frustration / Current Workaround | Decision Power (Buyer / Champion / User) | Frequency |
3. Inventory existing workarounds
Document what users do today without your product: spreadsheets, WhatsApp groups, manual copy-pasting, custom scripts. These workarounds demonstrate both real demand and the switching cost threshold your product must overcome.
4. Scan the competitive landscape & gaps
Map out direct alternatives and substitute behaviors:
- Where do existing market leaders leave underserved edge cases?
- What are the common complaints in customer reviews or support forums?
5. Prioritize assumptions (The 2x2 Matrix)
List all beliefs that must hold true for the product to succeed. Plot them on a matrix:
- X-axis: Known with high evidence ↔ High uncertainty / Guesswork
- Y-axis: Low operational impact ↔ Fatal if wrong (High risk)
The items in the High Uncertainty + Fatal if Wrong quadrant are your Riskiest Assumptions (feeds directly into
mvp-scoping).
6. Design lightweight validation experiments
Before committing engineering resources, define test mechanisms to validate riskiest assumptions:
- Smoke test / Fake-door: Landing page or in-app CTA button measuring conversion intent.
- Concierge / Wizard of Oz test: Fulfilling the service manually behind the scenes to test willingness to pay.
- Pass/Fail Criteria: Define measurable threshold before testing (e.g. "≥15% clickthrough on CTA indicates sufficient problem urgency").
Completion Criteria
- Problem framed in JTBD format (Situation -> Motivation -> Expected Outcome)
- Actor map completed with decision-making power and current workarounds
- Assumptions prioritized on the Uncertainty vs. Criticality matrix
- Top 3 riskiest assumptions isolated with quantitative pass/fail validation tests defined
- Synthesis captured in
discovery_synthesis.md
Output Format
A structured discovery_synthesis.md artifact detailing JTBD statements, actor maps, workaround inventories, assumption prioritization matrix, and validation experiment recipes.
Anti-patterns
- Skipping discovery because the founder or stakeholder "already knows what the market needs."
- Confusing a surface feature request ("add an export to CSV button") with the root problem ("reporting is fragmented").
- Leaving assumption exit criteria unquantified ("we will see if users like it").
- Generating unorganized 20-page interview transcripts without synthesizing actionable themes.
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.

