Overview
Before committing to building, break the product idea into small verifiable bets. Pin one measurable outcome (baseline and target horizon), then grow an opportunity-solution tree: under the outcome, opportunities backed by user evidence; under those, candidate solutions; under those, the fastest-learning experiments — at least three distinct opportunities before converging.
Then put assumptions on the table: do users want it, does the business hold, can it be built, is it usable — each scored by risk and uncertainty, tested from the riskiest outward. On the problem side, interviews confirm frequency, pain and willingness to act, and weak signals die early; on the solution side, prototypes test concept and value by watching behavior, not stated preference.
The cadence is a one-to-two-week discovery loop with explicit hypotheses, daily evidence reviews and a closing call: proceed, pivot or stop. What stays in your workspace is the tree, the assumption map and the loop plan — not another report nobody rereads.
Where it helps
- Build an Opportunity Solution Tree for a feature direction and mark evidence gaps
- Turn 'I feel we should build this' into a risk-scored assumption map
- Design an interview guide that tests frequency, severity and willingness
- Plan a two-week discovery sprint with proceed/pivot/stop criteria
#discovery#hypothesis#validation#evidence
Examples
Examples describe the request and the shape of the expected deliverable; they are not completed run results.
01Example prompt
Direction 'handwriting annotation for iPad users': give the outcome metric and an opportunity-tree skeleton, attach every opportunity to one of the three interview quotes I supplied, and mark gaps plainly.
Expected output
A tree with an evidence map: every opportunity points back to your interview material, unsupported spots flagged, not back-filled.
02Example prompt
Assumption-map that tree: list all four assumption classes, score by risk and uncertainty, and give the three riskiest each a small experiment finishable within two weeks.
Expected output
A scored assumption table plus three experiments — hypothesis, measure, sample, pass bar — with a two-week plan.
Requirements and limits
- Install platforms
- iOS: iOS · Android: Android
- Script runtime
- No script runtime (guidance and workflow)
- Minimum app version
- iOS: 1.7.59
Reviewed permission scope
iOS · Android
- Capabilities
- Read workspace filesWrite workspace files
- Review decision
- Approved
- Review stage
- Static content review
- Reviewed on
- 2026-10-28
Implementation and runtime details
- Adaptation stage
- frozen
iOS
- Capabilities
- Read workspace filesWrite workspace files
Android
- Capabilities
- Read workspace filesWrite workspace files
License and source
Source and trace details
License
MIT
MIT (root LICENSE)
The pinned skill subtree and shipped references were audited; full applicable license and per-file adaptation/asset notes are preserved under references/licenses/ and references/PROVENANCE.md.
- Source
- https://github.com/alirezarezvani/claude-skills
- Upstream path
- product-team/skills/product-discovery
- Source checked
- 2026-10-26
- Publisher
- JiangNanGenius
- Publication commit (retrieval)
- 25e07dbeeb6cc93c2fe83ddc72a34302cc40832a
- Audited source commit
- 84c524b6fb483e4cad94db076e7d9c9962966c19
- Signed catalog digest
- iOS 46196ba57ed7ea7f22085e74b113207f31193e820ab8983cf7a60eee953f2340 · Android 16de89d019e2057804a40f215485ccb09d5495a25864b34d681168eeaf8f9697
- Publication snapshot (UTC)
- 2026-10-31
Publication commit 25e07dbeeb, audited source 84c524b6fb; catalog digest iOS 46196ba57ed7… · Android 16de89d019e2….
Versions and status
Version records ship with the signed catalog; the target and released versions are shown below.
- Adaptation
- Ready
- Publication state
- Curated skills are available
- Released version
- 1.0.1