Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →yogsoth-ai/evidence-based-prioritization
Strategy: evidence-strength-based AHRQ PiCMe assessment — drive gap prioritization with the quality of literature evidence
Passed 14 of 21 test cases with the skill, and 12 of 21 without it.
and 6 more in the full report
6 fixed9 passed either way3 still failing4 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 5 test cases the skill fixed. Same model, same prompt, with and without the skill.
To ensure continuity across workflow rounds, what specific assessment data must be recorded in the context checkpoint following a prioritization round?
| Checked | Without skill | With skill |
|---|---|---|
| Records the PiCMe assessment matrix and composite scores in the context checkpoint. | Missed | Passed |
The instructions your model reads when the skill loads.
Evidence-strength-based prioritization: use the six dimensions of the AHRQ PiCMe framework to systematically assess the quality of the literature evidence behind each gap, surfacing the gaps where evidence is weakest and impact is greatest.
Core principle: a gap's priority depends not only on how important it is, but also on how weak the existing evidence is. The weaker the evidence and the higher the importance, the higher the priority.
The AHRQ PiCMe six-dimension assessment framework:
Final score = importance score × (1 − evidence sufficiency). Gaps with more sufficient evidence get lower priority (because others are already working on them).
Key insight: this framework naturally favors "neglected important problems" over "popular but already crowded problems."
| Tier | Number of gaps | PiCMe dimensions | Literature check | Final output |
|---|---|---|---|---|
| S | 3–8 | all 6 dimensions | ≥2 supporting references per gap | ranking table + evidence-void report |
| M | 9–15 | all 6 dimensions | ≥3 supporting references per gap | ranking table + evidence-void report + attack suggestions for top 3 gaps |
| L | 16–20 | all 6 dimensions | ≥5 supporting references per gap | ranking table + detailed evidence map + attack suggestions for top 5 gaps |
gap-normalization SOP: standardize the gap format and extract the list of supporting references for each gapahrq-picme-assessment SOP: run the six-dimension assessment on each gaptest cases passed, vs 12 / 21 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.