nWave-ai/nWave / nWave/skills/nw-discover
nw-discover
VerifiedTests whether a product problem and opportunity are real, then updates the durable product evidence authorities without creating delivery state.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 1.5 KB |
SKILL.md
View on GitHub---
name: nw-discover
description: "Tests whether a product problem and opportunity are real, then updates the durable product evidence authorities without creating delivery state."
user-invocable: true
argument-hint: '[product-concept]'
---
# NW-DISCOVER
## Purpose
Reduce product uncertainty before requirements or architecture investment.
Use customer evidence, assumption tests and counterexamples; never promote a
founder belief to fact by repetition.
## Workflow
1. State the opportunity, riskiest assumptions and falsification thresholds.
2. Gather evidence with source, sample size, date and confidence. Separate
observation, inference and hypothesis.
3. Test problem severity, current workaround, triggering context and willingness
to change. Seek disconfirming evidence.
4. Decide `VALIDATED`, `PIVOT`, `MORE_EVIDENCE` or `STOP`.
5. Update the existing durable product authority that owns the result: vision,
jobs, journey evidence or KPI baseline. Preserve provenance and stable ids.
Return changed authority paths, evidence citations, confidence and the next
unresolved question. Do not create a feature directory, manual handover,
wave report, plan or progress artifact.
## Human-readable authority
When discovery changes product facts, return those facts to the Product Owner;
do not edit generated briefs. Use current full briefs and HTML when useful,
with `nw-doc-as-artifact` for collaborative reading. Discovery evidence alone
does not create delivery state, prove completion or require an HTML view.
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| finishing-a-development-branchobra/superpowersUse when implementation is complete, all tests pass, and you need to decide how to integrate the work | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| systematic-debuggingobra/superpowersUse when encountering any bug, test failure, or unexpected behavior, before proposing fixes | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| test-driven-developmentobra/superpowersUse when implementing any feature or bugfix, before writing implementation code | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| skill-creatoranthropics/skillsCreate new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy. | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |