AC sichuan-cuisine
Ultimate Sichuan cuisine (川菜) knowledge base with 45+ classic recipes spanning cold dishes, hot dishes, soups, snacks, hot pot/maocai/gan guo, and banquet dishes. Covers all 24 flavor profiles, complete ingredient encyclopedia, and comprehensive cooking techniques. Use when users ask about Sichuan recipes, cooking methods, flavor profiles, ingredient substitutions, meal planning, Sichuan food culture, or any 川菜-related questions. Triggers include keywords like 川菜, 回锅肉, 麻婆豆腐, 鱼香, 宫保, 水煮, 麻辣, 红油, 担担面, 酸辣粉, 口水鸡, 夫妻肺片, 灯影牛肉, 樟茶鸭, 东坡肘子, 火锅, 冒菜, 干锅, 开水白菜, 菜谱, 四川菜, 成都美食 etc.
As a process C 55/100 · Has gaps — weak spots: result and completion, inputs and preconditions, consistency
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: 6. 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 55/100
- 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
- 40Consistency. Frontmatter name (sichuan-cuisine) differs from the folder (sichuan-cuisine-complete)
- 50When it triggers. No condition that starts the skill
- 55Failures and branches. 1 branches
- 85Steps. 24 steps, 1 vague phrases
- 100Tools and files. No external tools needed
- 100Execution cost. Instruction body is 807 tokens
- 100Running it twice. No mutating operations
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
- +4No input/output examples
- +1No license
- +2Single-language instructions
- +3Description length 574: enough signal without eating the budget
- +4Structure: 12 headings
- +3Step-by-step instructions: 24 items
- +4Reference files are cited in the instructions (4 of 4)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 84.