Loadingβ¦
Use when harmonizing clinical results into a system's canonical units β applies the org's target units (mmol/L, umol/L, g/L, Celsius, kg), per-analyte rounding conventions, and ITS reference ranges for H/L/N flagging, instead of whatever unit the source used. Template: replace with your units and ranges.
| Test case | Without β With | Effect | Ξ tokens | Ξ turns |
|---|---|---|---|---|
| glu-boundary | Β·βΒ· | β Error | 260% | 0% |
| crea-normal | Β·βΒ· | β Error | 261% | 0% |
| glu-mgdl-low | Β·βΒ· | β Error | 260% | 0% |
| glu-mgdl-high | Β·βΒ· | β Error | 262% | 0% |
| crea-passthrough | Β·βΒ· | β Error | 261% | 0% |
βThe skill is a benign template for clinical unit harmonization, providing clear conversion rules and reference ranges for standard health metrics without requesting any external capabilities or sensitive data.β
> Template skill. The rules below are a worked example (a fictional "Acme"). Fork this skill and replace them with your organization's real rules β the agent then applies your policy instead of guessing. The measured lift demonstrates the shape works.
Report every result in the Acme canonical unit, with the analyte's rounding rule, then flag it against the Acme reference range. Output keys: value (number), unit (string), flag ("H"|"L"|"N").
Canonical units + rounding (convert when the source differs):
Acme reference ranges (flag AFTER converting; bounds inclusive = "N"):
Above range -> "H"; below -> "L"; within (inclusive) -> "N".