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

92%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 high-quality, expert-calibrated body: executable commands, returned-parameter documentation, and domain-specific validation thresholds with recovery actions, all in dense tables with no padding. Its only weakness is deliberate repetition of the apparent-CL and extrapolation caveats across three sections, which is defensible as checklist emphasis but costs a minor conciseness point.

Suggestions

State the apparent CL/F-Vd/F caveat once (e.g., in Step 3's table) and have Step 5 reference it rather than repeating it, trimming the route/CL/Vd explanation from Step 1's table.

Consolidate the >20% extrapolation rule and r_squared threshold so each appears in exactly one place — Step 3's sanity column — with Step 5 only listing them as report-checklist items.

Dimension	Reasoning	Score
Conciseness	Lean, dense tables with no filler and no explanation of concepts Claude already knows; every section carries operational knowledge (BLQ handling, '>20% → unreliable', flip-flop kinetics). Not 5 because the apparent CL/F-Vd/F caveat and the >20% extrapolation warning each appear three times (Steps 1, 3, and 5), which could be tightened to a single stated checklist.	4 / 5
Actionability	Copy-paste-ready commands with full JSON payloads ('tu run NCA_compute_parameters '{...}''), exact tool names (NCA_fit_one_compartment, NCA_calculate_bioavailability), named return fields with a 'units' block, and a real local script (scripts/nca_from_csv.py, verified present) for CSV profiles.	5 / 5
Workflow Clarity	Clear five-step sequence (prepare → run → interpret → F → gotchas) with explicit validation checkpoints and error-recovery loops: 'AUC_extrapolation_pct > 20% → report AUC0-last instead', 'r_squared_terminal_fit ≥ ~0.95', and 'F > 1 signals a data/dosing error (recheck units and doses)'. Step 5 acts as an explicit checklist to state in output.	5 / 5
Progressive Disclosure	The body is a well-organized overview with a single one-level-deep bundle reference (scripts/nca_from_csv.py, confirmed to exist and match its description), appropriately splitting the CSV/BLQ workflow out of SKILL.md. All inline content (parameter interpretation table, gotchas) is needed on every run, so nothing belongs in a separate file; a Related skills section aids navigation.	5 / 5
	Total	19 / 20 Passed

Description

95%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.

An exemplary description: concrete capability enumeration, explicit use-when triggers, and an explicit not-for boundary that disambiguates the closest sibling skill. The only flaw is second-person phrasing in the trigger clause ('Use when you have...'), which costs it the top specificity score under the third-person guideline.

Dimension	Reasoning	Score
Specificity	Enumerates concrete actions comprehensively — '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' — matching the comprehensive anchor. The trigger clause 'Use when you have plasma/serum drug concentrations' uses second person, so per the third-person guideline the score is reduced by 1 from 5.	4 / 5
Completeness	Explicitly answers both: what ('non-compartmental analysis (NCA) for Cmax, Tmax, AUC...') 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'). Also adds an explicit negative boundary ('NOT for ADMET property prediction from structure').	5 / 5
Trigger Term Quality	Natural user vocabulary with synonyms throughout: 'Pharmacokinetic (PK)', 'plasma/serum drug concentrations', 'concentration-time data', 'bioavailability', 'half-life', 'AUC' — a user needing PK parameters would say these exact terms. Not score 4 because coverage includes both the full term and abbreviation forms plus route-specific phrases ('IV + oral AUCs').	5 / 5
Distinctiveness Conflict Risk	Clear niche (measured concentration-time PK) with an explicit disambiguation clause 'NOT for ADMET property prediction from structure (use tooluniverse-admet-prediction)', which actively routes the nearest competing skill away. Minimal conflict risk.	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: 14c4186

Reviewed: 7 days 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.