continuous-discovery
Skill8 starsChanged 9 months agoMITView on GitHub
Applies Teresa Torres's continuous discovery habits to help product teams discover products that create customer and business value. Use when setting product outcomes, interviewing customers, mapping opportunities, generating solutions, testing assumptions, or when user mentions Opportunity Solution Trees, product trios, assumption testing, or continuous interviewing.
6 other projects use a version of this.
Adopted by
Most recently taken up by
- fahadnari/Claude-skillsword for word, first seen Oct 20, 2026
- Adhamxon/claude-code-skillstheir own version, first seen Jul 30, 2026
- wondelai/skillstheir own version, first seen Jul 16, 2026
- RefoundAI/lenny-skillstheir own version, first seen Jul 15, 2026
- deciqAI/knowledge-skillstheir own version, first seen Jul 7, 2026
- luisabwk/krakentheir own version, first seen Mar 11, 2026
Other versions6 projects use a version of this.
Word for word · 1
- fahadnari/Claude-skills★ 0100% same
Edited · 0
None found.
Wrote their own version · 5
- wondelai/skills★ 2.6ksame name
- RefoundAI/lenny-skills★ 1.3ksame name
- deciqAI/knowledge-skills★ 13same name
- Adhamxon/claude-code-skills★ 2same name
- luisabwk/kraken★ 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 repository4 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- jobs-to-be-doneSkill
- shape-upSkill
- story-mappingSkill
The file
We split this skill into the rules it gives an agent
3 rules. 0 are common, 2 are distinctive, and 1 is very specific to this project.
0
Common
Most of the 4 edited versions we read keep these.
2
Distinctive
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 26
Don't start with solutions.
- Distinctive: line 30
Never fall in love with one idea.
- Very specific: line 38
Use the AskUserQuestion tool to determine what the user needs:
“Common” is measured: kept by at least 6 in 10 of the 4 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
Continuous Discovery
I help product teams build the habits needed to continuously discover products that create customer value and business value. Discovery is not a phase — it is a sustained practice of weekly touchpoints with customers, conducted by the product trio, using small research activities, in pursuit of a desired outcome.
Essential Principles
Discovery Is Continuous, Not a Phase
Discovery doesn't happen before delivery — it happens alongside it, every week. Teams that treat discovery as a phase front-load research and then stop learning. Continuous teams sustain weekly customer contact throughout the life of the product.
Outcomes Over Outputs
Shipping features is not the goal. Creating value is. Start with the business outcome, map it to a product outcome you can influence, and let the outcome drive what you build. If you can't connect a feature to an outcome, you shouldn't build it.
The Product Trio Decides Together
Product managers, designers, and software engineers make discovery decisions as a trio — not sequentially, not in silos. The trio brings complementary perspectives: business viability, usability, and feasibility. If one voice is missing, you're making incomplete decisions.
Opportunities, Not Solutions
Don't start with solutions. Start with customer needs, pain points, and desires — opportunities. Map the opportunity space before generating solutions. The best solutions come from deeply understanding the problem.
Compare, Don't Choose
Never fall in love with one idea. Generate at least three solutions for every target opportunity. Compare them against each other. Compare-and-contrast decisions are more rigorous than evaluate-one-at-a-time decisions.
Test Assumptions, Not Ideas
Ideas are bundles of assumptions. Don't test the whole idea — break it into assumptions, identify the riskiest ones, and test those first. Small, fast assumption tests reduce risk before you commit to building.
Intake
Use the AskUserQuestion tool to determine what the user needs:
Question: "Where are you in your discovery process?"
Options:
- Set or negotiate a product outcome — Define what success looks like and align with leadership
- Discover and map opportunities — Interview customers and build an Opportunity Solution Tree
- Generate and compare solutions — Ideate, compare, and select solutions for a target opportunity
- Test assumptions — Identify, prioritize, and run assumption tests
Routing
| Response | Workflow |
| 1, "outcome", "goal", "metric", "OKR", "negotiate" | workflows/set-outcomes.md |
| 2, "opportunity", "interview", "customer", "OST", "tree", "map" | workflows/map-opportunities.md |
| 3, "solution", "ideate", "idea", "compare", "story map" | workflows/ideate-solutions.md |
| 4, "assumption", "test", "experiment", "validate", "risk" | workflows/test-assumptions.md |
| other | Clarify intent, then route appropriately |
After identifying intent, read the matching workflow and follow it exactly.
Note: If the user's discovery task involves code changes — instrumenting metrics, building prototypes, setting up recruiting tools — recommend
EnterPlanModebefore proceeding with the workflow.
Framework Selection
Different frameworks apply to different discovery activities:
| Discovery Activity | Primary Reference | Key Frameworks |
| Setting outcomes, aligning with leadership | core-thesis.md, frameworks.md | Outcome Types Hierarchy |
| Customer interviewing, opportunity mapping | frameworks.md, techniques.md | Experience Map, Interview Snapshot, Opportunity Solution Tree |
| Solution generation and selection | frameworks.md, techniques.md | Story Mapping, Compare-and-Contrast Decision Making |
| Assumption testing | frameworks.md, techniques.md | Assumption Mapping |
For any discovery activity, read the relevant reference files before proceeding.
References
Core Knowledge:
- core-thesis.md — Central argument and prerequisite mindsets
- frameworks.md — All 8 discovery frameworks with application guidance
- principles.md — 12 guiding principles for effective discovery
- techniques.md — 11 step-by-step methods for discovery activities
Quality and Voice:
- anti-patterns.md — 28 anti-patterns organized by discovery phase
- voice.md — Terminology precision guide
Workflows
| Workflow | Purpose |
| set-outcomes.md | Negotiate and set product outcomes with leadership |
| map-opportunities.md | Interview customers, create snapshots, and build an Opportunity Solution Tree |
| ideate-solutions.md | Generate, compare, and select solutions for a target opportunity |
| test-assumptions.md | Identify, prioritize, and test riskiest assumptions |
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.

