AB personal-fit-coach
Build and maintain an isolated local personal fitness context for body weight, fat loss, diet, meals, calories, protein, hunger, fasting, food options near work or home, delivery choices, exercise preferences, workouts, sleep, body signals, daily logs, weekly reviews, and lightweight editable diet/exercise plans. Use when the user explicitly invokes /fit, fit, personal-fit-coach, 健康记录, 减脂记录, 体重记录, 饮食计划, 运动计划, 计划表, 今日记录, 周复盘, 饮食条件, 公司附近吃什么, 全家, 超级碗, 轻食, 外卖选择, 在家有氧, 不去健身房, or similar clear personal fitness tracking keywords. Slash commands and keywords are the reliable trigger path.
As a process B 72/100 · Nearly there — weak spots: result and completion, inputs and preconditions
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 72/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 70Failures and branches. 15 branches
- 100Tools and files. No external tools needed
- 100Steps. 77 steps
- 100When it triggers. States when to use and when not to
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 3957 tokens
- 100Running it twice. Mutating operations check current state
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 17 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)
- +3Output format is not stated: the model decides each time
- +2Single-language instructions
- +3Description length 587: enough signal without eating the budget
- +4Structure: 35 headings
- +3Step-by-step instructions: 77 items
- +4Has examples (21 code blocks)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 85.