Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →yogsoth-ai/hypothesis-formation-scoring-matrix-construction
Tactic: orchestrate multi-dimensional scoring SOPs to build a comprehensive assessment matrix for all gaps
Passed 13 of 22 test cases with the skill, and 5 of 22 without it.
and 11 more in the full report
8 fixed5 passed either way9 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 8 test cases the skill fixed. Same model, same prompt, with and without the skill.
Our clinical research team has outlined three potential healthcare gaps concerning targeted drug delivery for pediatric oncology. We need a rigorous multi-criteria evaluation to compare them. Please synthesize the appropriate scoring SOPs into a consolidated matrix table that rates each gap across relevant criteria, including clinical framework aspects if applicable. Ensure every cell has a numeric score plus a brief supporting reason, along with a weighted total score. Afterwards, include a narrative summary paragraph for each clinical gap and a final yield report summarizing score distributions, dimension variance, and literature support levels.
| Checked | Without skill | With skill |
|---|---|---|
| Evaluates clinical gaps on a 0-10 numeric scale in every matrix cell. | Missed | Passed |
| Includes importance, feasibility, novelty, impact, and ahrq-picme-assessment as scoring dimensions. | Missed | Passed |
| Appends a structured PiCMe clinical assessment section for the healthcare gaps. | Missed | Passed |
The instructions your model reads when the skill loads.
Orchestrate multiple scoring-dimension SOPs to build a multi-dimensional comprehensive assessment matrix for each gap, serving as the quantitative basis for ranking decisions.
Single-dimension scoring is prone to bias (e.g., ranking purely by "importance" ignores feasibility). This tactic invokes each scoring SOP in parallel or serial, comparing the multiple dimension scores of all gaps within a single matrix, so that priority judgments rest on systematic evidence rather than intuition.
CC selects the number of dimensions to cover based on topic tier; each dimension's scoring is handled by a dedicated SOP; once scoring is complete, CC consolidates the SOP outputs into a single matrix format.
| SOP | Responsibility | When to invoke |
|---|---|---|
| importance-scoring | Assess a gap's strategic importance to the field (0-10) | Required for all tiers |
| feasibility-scoring | Assess the feasibility of attacking a gap with currently available resources/methods (0-10) | Required for all tiers |
| novelty-scoring | Assess the research novelty and original-contribution potential of a gap (0-10) | Required for all tiers |
| impact-scoring | Assess the potential citation/application impact of the research output (0-10) | Added at M/L tier |
| ahrq-picme-assessment | Use the AHRQ PiCMe framework for a structured assessment of clinical/applied gaps | At L tier or when the biomedical/health domain is involved |
Simplified (S tier, 3 dims)
Default (M tier, 4 dims)
Deep (L tier, 5 dims + PiCMe)
test cases passed, vs 5 / 22 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.