AC wc-clean-sheet-model
Computes clean-sheet probability and defensive-returns EV for a team in a specific fixture from team defensive strength (xGA) against opponent attacking strength (xG), then models the STACK CORRELATION that turns a Clean-Sheet Spine (BB2) — GK + k same-team defenders — into a single correlated bet rather than k independent draws. Returns p_cs(team,fixture), a stack_corr_bonus capturing the amplified joint ceiling and shared downside (sign interacts with the rank objective θ — amplify when chasing, discount when protecting), and expected_ga with its conceding-points downside. Use when sizing a defensive stack, valuing a GK/DEF pick, scoring a candidate's BB2, or weighing the Clean Sheet Shield chip — called by wc-squad-architect, wc-matchday-tactician, wc-fitness-eval, and the strategists.
Computes clean-sheet probability and defensive-returns EV for a team in a specific fixture from team defensive strength (xGA) against opponent attacking…
As a process C 57/100 · Has gaps — weak spots: when it triggers, 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: 1. 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 57/100
- 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
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 2 mutating operations with no state check
- 60Result and completion. Output format stated, no completion criterion
- 70Execution cost. Instruction body is 4235 tokens
- 100Tools and files. No external tools needed
- 100Steps. 26 steps
- 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
- +5Description has no quoted example phrases that should trigger the skill
- +4Description does not say when NOT to use the skill (false activations)
- +1No license
- +2Single-language instructions
- +3Description length 799: enough signal without eating the budget
- +4Structure: 10 headings
- +3Step-by-step instructions: 26 items
- +3Output format is stated explicitly
- +4Has examples (8 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 87.