AC biohub
Access the user's biohub — WHOOP, Oura, Fitbit, Apple Health, and Garmin biometrics (recovery, sleep, strain, HRV, SpO₂); FreeStyle Libre continuous glucose (time-in-range, GMI); blood-panel biomarkers; supplement stack and intake history; daily nutrition; body composition (calipers / scale / DEXA) with a 3D anatomical simulator driven by FFMI + BF % + 7-site caliper data; a WHOOP-Age-style biological-age estimate; and user-defined tracking phases (bulks, cuts, supplement courses). Use when the user asks about their recovery score, sleep quality, HRV trends, training readiness, blood-work results, supplement effects, glucose / time-in-range, biological age, body composition, fat loss, what they would look like at a target body fat, or wants a health status update grounded in their own biometric data. Multi-source design — queries on `daily_metrics` are source-agnostic. Not medical advice.
Access the user's biohub — WHOOP, Oura, Fitbit, Apple Health, and Garmin biometrics (recovery, sleep, strain, HRV, SpO₂); FreeStyle Libre continuous glucose…
As a process C 58/100 · Has gaps — weak spots: result and completion, inputs and preconditions, running it twice
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: 3. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- note
frontmatter-keyunknown frontmatter key "homepage"
Process rating: all ten parameters 58/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 30Running it twice. 4 mutating operations with no state check
- 60Tools and files. Uses tools (bash, python) that frontmatter does not declare
- 70When it triggers. States when to use, but not when not to
- 70Failures and branches. 4 branches
- 100Steps. 27 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 2389 tokens
- 100Progress reporting. Reports progress
- 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)
- +3Description length 901: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +4Structure: 13 headings
- +3Step-by-step instructions: 27 items
- +4Has examples (3 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 80.