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

95%

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

100%

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

An excellent, lean skill body: executable examples, a clear sequenced workflow with explicit validation checkpoints, and one properly signaled bundle reference. No meaningful weaknesses found.

Dimension	Reasoning	Score
Conciseness	The body opens directly with 'When to use this' and uses dense tables plus executable bash, with no introductory fluff explaining what PK or AUC is in a padded way; every section adds operational guidance Claude would not reliably infer, matching the score-3 lean/efficient anchor.	3 / 3
Actionability	Provides fully executable, copy-paste-ready 'tu run NCA_compute_parameters' commands with complete JSON arguments and real numeric values, plus a real referenced script (scripts/nca_from_csv.py) and concrete tool signatures, matching the score-3 anchor.	3 / 3
Workflow Clarity	A clear five-step sequence (Prepare, Run NCA, Interpret, Bioavailability, Quality gotchas) with explicit validation thresholds ('>20% -> unreliable', 'r_squared >= ~0.95', 'F > 1 signals a data/dosing error') and error-recovery guidance, matching the score-3 anchor.	3 / 3
Progressive Disclosure	Well-organized sections with a single clearly-signaled one-level reference to scripts/nca_from_csv.py (confirmed present), and no deeply nested or monolithic-wall-of-text structure, matching the score-3 anchor.	3 / 3
	Total	12 / 12 Passed

Description

90%

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 with explicit what/when triggers and a clear exclusion that distinguishes it from a sibling skill. The only issue is second-person voice ('you have'), which caps the specificity dimension.

Suggestions

Rewrite the trigger clause in third person to match the judging guideline, e.g. 'Use when plasma/serum drug concentrations are measured over time after a dose and PK parameters are needed' instead of 'Use when you have... you need...'.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions (NCA for Cmax, Tmax, AUC, half-life, CL, Vd, MRT, F, one-compartment fitting), matching the score-3 anchor; reduced to 2 because the description uses second-person voice ('Use when you have... you need...'), which the judging guidelines explicitly penalize by lowering specificity by 1.	2 / 3
Completeness	Explicitly answers both what (the NCA parameter list and one-compartment fitting) and when ('Use when you have plasma/serum drug concentrations over time after a dose and need PK parameters'), with an explicit exclusion clause, matching the score-3 anchor.	3 / 3
Trigger Term Quality	Good coverage of natural terms a user needing PK analysis would say ('concentration-time data', 'plasma/serum drug concentrations', 'PK parameters', 'bioavailability'), matching the score-3 anchor rather than the partial-coverage score-2 anchor.	3 / 3
Distinctiveness Conflict Risk	Clear measured-data PK niche, distinguished from structure-based prediction via 'NOT for ADMET property prediction from structure (use tooluniverse-admet-prediction)', matching the score-3 anchor for a clear niche unlikely to conflict.	3 / 3
	Total	11 / 12 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: 089eb8e

Reviewed: about 9 hours 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.