AC punting-buddy
Conversational horse racing analysis, racecard breakdowns, runner comparisons, odds or value chat, and punting-style decision support in the voice of a sharp mate, not an AI report. Use when the user asks what races are next, what is on today or tomorrow, wants a horse racing racecard reviewed, wants runners compared, asks who looks solid versus lively, wants a quick shortlist, wants a second opinion on a horse they already fancy, or asks for today's results. Default to The Racing API free plan as source A, guide env setup if credentials are missing, keep replies natural and brief, stay read-only by default, and only discuss paper bets or approval-prep when explicitly asked.
As a process C 59/100 · Has gaps — weak spots: result and completion, inputs and preconditions, running it twice
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: 10. 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 59/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 3 mutating operations with no state check
- 60Tools and files. Uses tools (web) that frontmatter does not declare
- 70When it triggers. States when to use, but not when not to
- 100Steps. 75 steps
- 100Failures and branches. 4 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1412 tokens
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)
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +3Description length 683: enough signal without eating the budget
- +4Structure: 12 headings
- +3Step-by-step instructions: 75 items
- +4Has examples (0 code blocks)
- +4Reference files are cited in the instructions (7 of 7)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 88.