BC category-allocation-best-response
Computes the best-response allocation of roster resources across categories in a Head-to-Head Categories matchup. Given our per-category capacity, the opponent's projected output, per-category win probabilities (from matchup-win-probability-sim), and a K-of-N winning threshold, classifies categories into pushed / contested / conceded buckets, emits per-category leverage weights for downstream lineup and streaming decisions, computes the resulting K-of-N win probability, and writes a plain-English rationale. Domain-neutral — portable to any fantasy sport with H2H Cats scoring (MLB 10-cat, NBA 9-cat, NHL 10-cat). Use when you need push/punt decisions, dominated-strategy elimination, leverage weights per cat, or best-response allocation; or when the user mentions "category allocation", "push or punt", "K of N cats", "dominated strategy elimination", "best response allocation", "Blotto fantasy", "leverage weights per cat", or "which cats to push".
Computes the best-response allocation of roster resources across categories in a Head-to-Head Categories matchup.
As a process C 53/100 · Has gaps — weak spots: result and completion, inputs and preconditions, failures and branches
How to improve
- Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
- A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.
Guard findings · 0
✓ No critical or high findings
Files scanned: 4. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
✓ No remarks against the Agent Skills spec
Process rating: all ten parameters 53/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Failures and branches. Linear process with no failure handling
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 19 mutating operations with no state check
- 70When it triggers. States when to use, but not when not to
- 70Execution cost. Instruction body is 4500 tokens
- 85Steps. 97 steps, 2 vague phrases
- 100Tools and files. No external tools needed
- 100Consistency. Name and required fields are in place
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.
Quality signals
- +4Description does not say when NOT to use the skill (false activations)
- +3Description length 957: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +5Description quotes 8 example trigger phrases
- +4Structure: 7 headings
- +3Step-by-step instructions: 97 items
- +4Has examples (3 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 86.