BC wine-info-search
READ-ONLY wine and alcohol information lookup skill. Searches for wine details, ratings, and price comparisons across platforms. Does NOT make purchases, process payments, or modify any accounts. No OAuth tokens, no sensitive credentials required for core functionality. All operations are search and display only. Trigger scenarios include: looking up wine ratings, comparing wine prices across platforms (JD.com/Tmall/Wine-Searcher/etc.), checking vintage comparisons for a specific wine, getting detailed wine info (grape varieties, taste profile, food pairing), getting wine & winery background information, getting vintage recommendations by year, getting health-related drinking advice by age group and medical conditions, getting staple food and main dish pairing recommendations, getting drinking-window advice for aged wines, or identifying a wine from a label photo.
As a process C 60/100 · Has gaps — weak spots: when it triggers, inputs and preconditions, running it twice
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: 7. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
body-longSKILL.md body ≈ 5519 tokens (recommended < 5000); move details to references/ - note
frontmatter-keyunknown frontmatter key "homepage" - note
frontmatter-keyunknown frontmatter key "source" - note
frontmatter-keyunknown frontmatter key "capabilities" - note
frontmatter-keyunknown frontmatter key "optional_env"
Process rating: all ten parameters 60/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 1 mutating operations with no state check
- 60Tools and files. Uses tools (bash, web, python) that frontmatter does not declare
- 60Result and completion. Output format stated, no completion criterion
- 70Execution cost. Instruction body is 5519 tokens
- 100Steps. 118 steps
- 100Failures and branches. 6 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
- low 10 top-level sections: this looks like several domains in one skill
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 876: 120–800 characters recommended
- -41 reference files, but SKILL.md never points to them: the model will not open them
- +2Single-language instructions
- +4Structure: 23 headings
- +3Step-by-step instructions: 118 items
- +3Output format is stated explicitly
- +4Has examples (7 code blocks)
- +3All 1 scripts are documented
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 71.