tooluniverse-pharmacokinetics

Pharmacokinetic (PK) analysis of concentration-time data — non-compartmental analysis (NCA) for Cmax, Tmax, AUC (0-t and 0-∞), terminal half-life, clearance (CL), volume of distribution (Vd), MRT, and absolute bioavailability (F). Also one-compartment fitting. Use when you have plasma/serum drug concentrations over time after a dose and need PK parameters, or to compute bioavailability from IV + oral AUCs. NOT for ADMET property prediction from structure (use tooluniverse-admet-prediction).

Quality

94%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Quality

Content

96%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A tight, executable PK NCA workflow with copy-paste-ready commands, explicit quality/validation thresholds, and a clean sectioned structure backed by one real bundle script. The only gap is slightly less explicit navigation to the bundled script.

Dimension	Reasoning	Score
Conciseness	Lean and efficient throughout — no padded concept explanations, every table and step earns its place, and it assumes Claude's competence (e.g. it states thresholds and formulas without re-explaining basic PK).	5 / 5
Actionability	Fully executable, copy-paste-ready `tu run NCA_compute_parameters` and `NCA_calculate_bioavailability` commands with realistic JSON payloads, plus concrete formulas and numeric thresholds, covering the common IV/oral cases.	5 / 5
Workflow Clarity	A clear 5-step sequence (Prepare → Run → Interpret → Bioavailability → Quality gotchas) with explicit validation checkpoints and feedback loops: extrapolation >20% → report AUC0-last, r_squared <0.9 or <3 tail points → half-life unreliable, and oral data flagged as apparent CL/F.	5 / 5
Progressive Disclosure	Well-organized sections with one referenced bundle file (`scripts/nca_from_csv.py`, confirmed present) pointed to at the right moment and no nested references; it falls just short of 5 because the script reference is mentioned inline rather than gathered into a clearly signaled navigation/pointer block.	4 / 5
	Total	19 / 20 Passed

Description

92%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong, specific description that names concrete PK parameters and capabilities, gives explicit use-when trigger guidance, and disambiguates from a sibling ADMET skill via a clear negative boundary. Only minor keyword-synonym coverage is missing.

Dimension	Reasoning	Score
Specificity	Lists many concrete parameters — Cmax, Tmax, AUC (0-t and 0-∞), terminal half-life, clearance (CL), volume of distribution (Vd), MRT, absolute bioavailability (F) — plus one-compartment fitting, giving comprehensive concrete coverage rather than just 1-2 actions.	5 / 5
Completeness	Explicitly answers both what (NCA parameters, one-compartment fitting, bioavailability) and when ('Use when you have plasma/serum drug concentrations over time after a dose and need PK parameters, or to compute bioavailability from IV + oral AUCs') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Strong natural phrases a user would say — 'plasma/serum drug concentrations over time after a dose', 'PK parameters', 'bioavailability from IV + oral AUCs' — but lacks some common synonyms/extensions (e.g. explicit 'pharmacokinetics over time', file formats), keeping it just below the comprehensive anchor.	4 / 5
Distinctiveness Conflict Risk	Clear niche of measured-data PK/NCA with an explicit negative boundary ('NOT for ADMET property prediction from structure (use tooluniverse-admet-prediction)'), minimizing conflict with the related ADMET skill.	5 / 5
	Total	19 / 20 Passed

Validation

100%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: mims-harvard/ToolUniverse
Path: plugin/skills/tooluniverse-pharmacokinetics/SKILL.md
Commit: 1b02920

Reviewed: 1 day ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.