Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →brycewang-stanford/clinical-pharmacology-guide
Clinical pharmacology principles for dosing, drug interactions, and patient s...
Passed 15 of 22 test cases with the skill, and 13 of 22 without it.
2 fixed13 passed either way7 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 2 test cases the skill fixed. Same model, same prompt, with and without the skill.
I am building a clinical reference guide for my pharmacology team. Please generate a summary table of narrow therapeutic index drugs detailing their therapeutic ranges, toxic threshold values, and monitoring schedules. In addition, outline dosing guidelines across special patient populations—such as renal impairment, liver dysfunction, pediatric, and elderly patients—and note relevant regulatory guidelines for clinical pharmacology studies.
| Checked | Without skill | With skill |
|---|---|---|
| Recommends allometric scaling using body weight to the power of 0.75 for pediatric dosing | Missed | Passed |
| Cites ICH guidelines E4, E5, E7, and E11 for clinical pharmacology study design | Missed | Passed |
| Lists vancomycin therapeutic range as AUC/MIC 400-600 | Passed | Passed |
The instructions your model reads when the skill loads.
A skill for applying clinical pharmacology principles to research and practice. Covers pharmacokinetic/pharmacodynamic modeling, drug interaction assessment, therapeutic drug monitoring, and special population dosing.
The most widely used PK/PD model relates drug concentration to effect:
import numpy as np
import matplotlib.pyplot as plt
def emax_model(concentration: np.ndarray, emax: float, ec50: float,
hill: float = 1, baseline: float = 0) -> np.ndarray:
"""
Sigmoid Emax (Hill) model.
Args:
concentration: Drug concentration array
emax: Maximum effect
ec50: Concentration producing 50% of Emax
hill: Hill coefficient (steepness)
baseline: Baseline effect (E0)
"""
effect = baseline + (emax * concentration**hill) / (ec50**hill + concentration**hill)
return effect
# Example: dose-response curve
conc = np.logspace(-2, 3, 200)
effect = emax_model(conc, emax=100, ec50=10, hill=1.5)
fig, ax = plt.subplots(figsize=(8, 5))
ax.semilogx(conc, effect)
ax.set_xlabel('Concentration (ng/mL)')
ax.set_ylabel('Effect (%)')
ax.set_title('Sigmoid Emax Model')
ax.axhline(y=50, color='gray', linestyle='--', alpha=0.5)
ax.axvline(x=10, color='gray', linestyle='--', alpha=0.5)
test cases passed, vs 13 / 22 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.