Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →nwave-ai/nw-pdr-review-criteria
Evidence quality validation and decision gate criteria for product discovery reviews
Passed 20 of 21 test cases with the skill, and 10 of 21 without it.
and 13 more in the full report
11 fixed10 passed either way1 still failing0 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.
An audio audit of discovery interviews revealed that the interviewer spoke for 45% of the total session duration, giving long explanations before asking short questions. What anti-pattern and severity level apply?
| Checked | Without skill | With skill |
|---|---|---|
| Identifies the talking greater than listening anti-pattern. | Passed | Passed |
| Identifies the severity level as medium. | Missed | Passed |
The instructions your model reads when the skill loads.
"Tell me about the last time..." | "When did you last..." | "What happened when..." | "Walk me through how you..." | "What did you try..." | "How much have you spent on..." Specific dates, dollar amounts, named tools, concrete examples, emotional frustration language
"Would you use/pay/like..." | "Do you think..." | "Imagine if..." | "What if we..." Flag and reject if >20% of evidence is future-intent.
| Phase | Minimum | High Confidence | Notes |
|---|---|---|---|
| 1: Problem | 5 | 10 | Interviews required |
| 2: Opportunity | 10 | 20 | Quantitative supplements, not replaces |
| 3: Solution | 5 per iteration | 3 iterations max | Before decision |
| 4: Viability | 5 | -- | Stakeholder review required |
Pivot decision rule: min 5 consistent signals. Block decisions on fewer.
Proceed: 5+ confirm pain + willingness to pay | Pivot: differs from expected | Kill: <20% confirm Checks: 5+ interviews, >60% confirmation, customer words, 3+ examples
Proceed: top 2-3 score >8 (0-20) | Pivot: new opportunities | Kill: all low-value Checks: OST complete with 5+, scores correct (Importance + Max(0, Importance - Satisfaction)), top >8/20
Proceed: >80% task completion, usability validated | Pivot: needs refinement | Kill: fundamental blocks
test cases passed, vs 10 / 21 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.