Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →yogsoth-ai/full-ranking
Produce a complete ordering of all candidates using PROMETHEE I/II, ELECTRE III, or MAVT methods.
Passed 6 of 22 test cases with the skill, and 17 of 22 without it.
2 fixed2 passed either way17 still failing1 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 2 test cases the skill fixed. Same model, same prompt, with and without the skill.
We have 12 candidate IT infrastructure projects with estimated costs and expected ROI scores. Our capital budget cap is strictly $10 million. Selecting the top-ranked individual project is insufficient because we need to find the combination of projects that maximizes cumulative ROI without exceeding the $10M budget limit. Please solve this as a 0-1 knapsack capital budgeting optimization.
| Checked | Without skill | With skill |
|---|---|---|
| Solves the constrained portfolio selection problem to maximize cumulative ROI within the $10M budget cap. | Missed | Passed |
| Does not force a simple linear rank ordering as the primary final recommendation. | Passed | Passed |
The instructions your model reads when the skill loads.
Purpose: Produce a complete priority ranking of all candidate alternatives, supporting PROMETHEE I/II, ELECTRE III, MAVT, and other ranking methods.
When to use:
| Base SOP | Target | ±10% Range |
|---|---|---|
| criterion-definition | 5-8 criteria | 4-9 |
| weight-elicitation-sop | 1 weight vector | 1 |
| alternative-scoring | 1 score matrix | 1 |
| normalization | 1 normalized matrix | 1 |
| rank-comparison | 1 agreement matrix | 1 |
| scoring-synthesis | 1 full ranking | 1 |
strategy: full-ranking
status: pending
criteria_defined: false
weights_computed: false
scores_computed: false
ranking_produced: false
methods_compared: false
result: null
test cases passed, vs 17 / 22 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.