Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →yogsoth-ai/hypothesis-formation-gap-prioritization
Campaign: Systematically assess and rank research gaps, determining the targets most worth attacking
Passed 5 of 15 test cases with the skill, and 3 of 15 without it.
and 8 more in the full report
6 fixed2 passed either way12 still failing2 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.
We are evaluating research directions for solid-state battery electrolytes. Here are our two identified gaps: 1. High interfacial resistance between solid electrolyte and lithium anode (domain: materials science; exists due to poor physical contact). 2. Low ionic conductivity at sub-zero temperatures (domain: electrochemistry; exists due to high activation energy). Our goal is to achieve all-climate electric vehicle operation. Please rank these gaps and produce an attack strategy matrix.
| Checked | Without skill | With skill |
|---|---|---|
| Stop processing because fewer than 3 gaps were provided | Missed | Passed |
| Inform that at least 3 research gaps must be provided before prioritization can begin | Missed | Passed |
The instructions your model reads when the skill loads.
Systematically assess and rank research gaps — answering "which gaps are most worth attacking?"
Not met → stop, and inform the user that upstream work must be completed first.
Turn a batch of unranked research gaps into a prioritized attack list. The output is not "discovering new gaps" but "making decisions about existing gaps."
| Strategy | When to use | Default |
|---|---|---|
| multi-criteria-ranking | Moderate number of gaps (5-20), systematic assessment needed | ✓ |
| evidence-based-prioritization | Gaps from rigorous literature review, with ample supporting evidence | |
| stakeholder-weighted-ranking | Research involves multiple stakeholders | |
| portfolio-optimization | Large number of gaps (20+), portfolio-level decisions needed | |
| rapid-triage | Very large number of gaps (50+), rapid coarse screening needed first |
CC autonomously selects a strategy based on gap count, evidence sufficiency, and stakeholder complexity. Strategies can be combined (e.g., rapid-triage to screen first → multi-criteria-ranking for fine ranking).
| Tier | Number of gaps | Assessment dimensions | Scoring rounds | Final output |
|---|---|---|---|---|
| S | 3-5 | ≥3 | 1 | Ranking + top 2 attack suggestions |
| M | 6-20 | ≥4 | ≥2 (incl. sensitivity testing) | Ranking + top 3-5 attack suggestions |
| L | 20+ | ≥5 | ≥3 (incl. portfolio optimization) | Ranking + top 5-8 attack suggestions + portfolio analysis |
test cases passed, vs 3 / 15 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.