Install any skill in seconds. Free to start, no credit card required.
Get Started Free →nwave-ai/nw-discovery-methodology
Question-first approach to understanding user journeys. Load when starting a new journey design or when the discovery phase needs deepening.
Passed 16 of 22 test cases with the skill, and 10 of 22 without it.
and 9 more in the full report
10 fixed6 passed either way2 still failing4 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 10 test cases the skill fixed. Same model, same prompt, with and without the skill.
We want to add a multi-factor authentication prompt to our CLI login command `cloud-cli login`. How should we start handling this request?
| Checked | Without skill | With skill |
|---|---|---|
| Asks questions to understand the full journey context before designing the command layout | Missed | Passed |
The instructions your model reads when the skill loads.
Discover journeys through deep questioning before any sketching. The sketch is proof of understanding, not the starting point.
Focus: What is the user trying to accomplish?
Questions:
After collecting goal, trigger, and success criteria, output a rough draft sketch showing what the journey might look like. Mark unknowns with ???. Purpose: make value visible immediately so the user sees progress, not just questions.
[Trigger: ???] → [Step 1: ???] → [Step 2: ???] → [Goal: {stated goal}]
Feels: ??? Sees: ??? Sees: ??? Feels: {success criteria}
Artifacts: ??? Artifacts: ??? Artifacts: ???
This is a working hypothesis, not a commitment. Update it after each phase as understanding deepens. The sketch gives the user something concrete to react to — "no, step 2 happens before step 1" is more productive than abstract discussion.
Focus: What does the user EXPECT to see?
Questions:
Focus: How should the user FEEL?
test cases passed, vs 10 / 22 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.