CB fitness-coach
TRIGGER when: user asks about workout plans, exercise routines, fat loss, muscle gain, body recomposition, meal planning for fitness, calorie or macro tracking, home or gym training, hydration or sleep tracking, smartwatch/workout data analysis, or weekly fitness progress reviews. DO NOT TRIGGER when: user asks for medical diagnosis, physical therapy prescriptions, clinical disease nutrition, urgent symptom triage, eating disorder treatment, pregnancy/postpartum programming, minor-specific coaching, mental health counseling, or sports competition prep. FIRST ASK: if no profile exists, collect height, weight, target weight, age, goal, training location, days per week, city, diet restrictions, and injuries/medical conditions before generating a plan.
TRIGGER when: user asks about workout plans, exercise routines, fat loss, muscle gain, body recomposition, meal planning for fitness, calorie or macro…
As a process B 66/100 · Nearly there — weak spots: result and completion, inputs and preconditions, consistency
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: 8. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
body-longSKILL.md body ≈ 5528 tokens (recommended < 5000); move details to references/ - note
frontmatter-keyunknown frontmatter key "command-dispatch"
Process rating: all ten parameters 66/100
- 0Result and completion. Does not say what the result is
- 30Inputs and preconditions. Does not say what the process needs to start
- 40Consistency. Frontmatter name (fitness-coach) differs from the folder (fit-mate)
- 70When it triggers. States when to use, but not when not to
- 70Execution cost. Instruction body is 5528 tokens
- 85Steps. 272 steps, 1 vague phrases
- 100Tools and files. No external tools needed
- 100Failures and branches. 8 branches, has a failure section
- 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 10 top-level sections: this looks like several domains in one skill
- low The response is described with custom markup (4 tags): a typed call is more reliable
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 758: enough signal without eating the budget
- +4Structure: 25 headings
- +3Step-by-step instructions: 272 items
- +4Reference files are cited in the instructions (6 of 6)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 73.