AB whisky-search
Search and retrieve whisky information from WhiskySpace. Use this skill when users ask about whisky bottles, brands, distilleries, prices, ratings, regions, cask types, filters, recommendations, or WhiskySpace page links/URLs/addresses for whisky or brand pages. Trigger for requests like "find a whisky", "tell me about Macallan", "show me Islay whiskies", "what's the price of", "compare these whiskies", "give me the details page URL", "give me the brand page URL", or "where did this link come from". Supports 8 languages: English, Chinese (zh), Japanese (ja), Spanish, French, German, Korean, Portuguese.
As a process B 68/100 · Nearly there — weak spots: inputs and preconditions, progress reporting
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: 2. 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 68/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 50When it triggers. No condition that starts the skill
- 60Tools and files. Uses tools (web) that frontmatter does not declare
- 60Result and completion. Output format stated, no completion criterion
- 100Steps. 78 steps
- 100Failures and branches. 9 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1687 tokens
- 100Running it twice. No mutating operations
- 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)
- +1No license
- +2Single-language instructions
- +5Description quotes 8 example trigger phrases
- +3Description length 609: enough signal without eating the budget
- +4Structure: 26 headings
- +3Step-by-step instructions: 78 items
- +3Output format is stated explicitly
- +4Has examples (10 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 92.