CB wc-chip-timing
Scores the deployment leverage of all five FIFA World Cup Fantasy boosters (Wildcard, 12th Man, Maximum Captain, Clean Sheet Shield, Qualification Booster) across the remaining tournament horizon — computing, for each chip and each candidate round, the EXTRA expected points the chip yields in that round versus an average round, then turning the leverage surface into a fire/hold call per chip this round plus a maintained earmark table (chip -> earmarked round -> trigger -> fallback). This is the math engine behind wc-chip-strategist. Reads the round's player-ev, clean-sheet, fixture/progression, ownership and captain-ladder signals plus tournament-state (chips remaining, phase, surviving nations); never re-derives them. Enforces the golden rule — never reach the semis with chips unused. Use whenever a chip decision is live (the chip-check prompt, the group->KO transition, or any round where a chip is earmarked or leverage spikes). Emits a chip-plan signal.
Scores the deployment leverage of all five FIFA World Cup Fantasy boosters (Wildcard, 12th Man, Maximum Captain, Clean Sheet Shield, Qualification Booster)…
As a process B 73/100 · Nearly there — weak spots: inputs and preconditions, running it twice, progress reporting
How to improve
- The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
- 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
- warning
body-longSKILL.md body ≈ 7645 tokens (recommended < 5000); move details to references/
Process rating: all ten parameters 73/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 8 mutating operations with no state check
- 60Result and completion. Output format stated, no completion criterion
- 70When it triggers. States when to use, but not when not to
- 70Execution cost. Instruction body is 7645 tokens
- 100Tools and files. No external tools needed
- 100Steps. 32 steps
- 100Failures and branches. 1 branches, has a failure section
- 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)
- +3Description length 969: 120–800 characters recommended
- -5TODO / placeholder text left in the skill
- +1No license
- +2Single-language instructions
- +4Structure: 15 headings
- +3Step-by-step instructions: 32 items
- +3Output format is stated explicitly
- +4Has examples (15 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 69.