BC nutrition-advisor
此 skill 用于计算食物热量并提供科学用餐建议。当用户说"计算热量"、"饮食建议"、"营养建议"、"吃什么"、"减脂食谱"、"增肌食谱"、"月经期饮食"、"生理期饮食"、"TDEE"、"BMR"、"卡路里"、"减肥"、"增肌"、"减脂"、"每日摄入"、"营养搭配"、"深夜饿了"、"没空做饭"、"压力大想吃"、"替换"、"冰箱里有"、"喝水"、"水分报告"、"饭后感受"、"习惯报告"、"月度总结"、"查热量"、"这个多少卡"、"一周食谱"、"外食指南"、"补剂建议"、"周期报告"、"来月经了"、"记录饮食"、"我吃了"、"今天吃了什么"、"今天吃什么"、"营养报告"、"调整目标"、"在外面吃"、"点外卖"、"聚餐"、"出差吃啥"、"聚餐怎么办"、"里程碑"、"读取档案"、"保存档案"、"更新档案"、"今天剩余"、"季节建议"、"夏天吃什么"、"冬天吃什么"、"平台期"、"碳水循环"、"什么时候吃"、"时间营养"、"晚餐建议"、"断食建议"、"间歇性断食"、"破食"、"断食+碳水循环"、"16:8"、"5:2"、"GI值"、"血糖管理"、"低GI"、"控糖"、"膳食纤维"、"肠道健康"、"益生菌食物"、"益生元"、"便秘"、"消化不好"、"助眠食物"、"睡前吃什么"、"失眠饮食"、"睡眠不好怎么吃"、"抗炎饮食"、"抗炎食物"、"促炎"、"皮质醇"、"压力饮食"、"反向饮食"、"恢复代谢"、"Diet Break"、"代谢恢复" 时触发。
As a process C 50/100 · Has gaps — weak spots: result and completion, when it triggers, inputs and preconditions
How to improve
- Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
- 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: 3. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
description-no-whendescription does not say WHEN to use the skill (no "use when") - warning
body-longSKILL.md body ≈ 14204 tokens (recommended < 5000); move details to references/
Process rating: all ten parameters 50/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Failures and branches. Linear process with no failure handling
- 0Progress reporting. Says nothing while it works
- 20When it triggers. No condition that starts the skill
- 40Execution cost. Instruction body is 14204 tokens: crowds the task out of the window
- 100Tools and files. No external tools needed
- 100Steps. 151 steps
- 100Consistency. Name and required fields are in place
- 100Running it twice. No mutating operations
- low 28 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
- +4Description does not say when NOT to use the skill (false activations)
- +3Output format is not stated: the model decides each time
- -2135 emoji in the instructions: noise for the model
- +1No license
- +2Single-language instructions
- +5Description quotes 4 example trigger phrases
- +3Description length 629: enough signal without eating the budget
- +4Structure: 155 headings
- +3Step-by-step instructions: 151 items
- +4Has examples (82 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 65.