Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →yogsoth-ai/deep-insight-gap-prioritization
Score and rank validated gaps on importance, feasibility, novelty, and urgency. Multi-criteria decision analysis with stakeholder confirmation.
Passed 8 of 18 test cases with the skill, and 4 of 18 without it.
and 10 more in the full report
9 fixed1 passed either way8 still failing4 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 6 test cases the skill fixed. Same model, same prompt, with and without the skill.
Our oncology research consortium has validated four unaddressed clinical knowledge gaps regarding targeted immunotherapy resistance in solid tumors. We need to determine which project proposals to fund first. Please analyze these gaps and generate a priority ranking that includes individual dimension scores, composite evaluation scores, simulated stakeholder agreement across clinicians and drug developers, and a sensitivity assessment testing whether the rankings remain stable under alternative weighting models.
| Checked | Without skill | With skill |
|---|---|---|
| Begins the response with a state ledger enclosed in HARD-GATE tags. | Missed | Passed |
| Reports target budgets of 30 for web-search and 10 for web-research. | Missed | Passed |
The instructions your model reads when the skill loads.
Score validated gaps and produce a ranked research priority list.
Gaps have been validated as genuine — now determine which are most worth pursuing based on multiple criteria and stakeholder perspectives.
| Base SOP | Target | ±10% Range |
|---|---|---|
| web-search | 30 | 27–33 |
| web-research | 10 | 9–11 |
| paper-overview | 20 | 18–22 |
| paper-search | 15 | 13–17 |
| paper-research | 5 | 4–6 |
Print before every iteration:
<HARD-GATE>
| SOP | Done | Target | % |
|-----|------|--------|---|
| web-search | ? | 30 | ? |
| web-research | ? | 10 | ? |
| paper-overview | ? | 20 | ? |
| paper-search | ? | 15 | ? |
| paper-research | ? | 5 | ? |
Budget Gate: OPEN/CLOSED (>=80% required to exit)
</HARD-GATE>
test cases passed, vs 4 / 18 without
Published skills whose descriptions closely match this one, with their headline benchmark lift.
More skills from the same source and nearby in the registry, with their headline benchmark lift.