tooluniverse-computational-biophysics

Solve quantitative problems in biophysics — pharmacokinetics (PK volume of distribution, clearance, half-life), epidemiology (R0, attack rate), toxicology (LD50, NOAEL), population genetics (Hardy-Weinberg, Fst), enzyme kinetics (Michaelis-Menten), thermodynamics. Use for first-principles quantitative biology calculations, dose calculations, exposure assessment, and biophysical-property estimation.

Quality

92%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

85%

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

The body is highly actionable with executable templates, a verification checkpoint, and well-organized one-level-deep script references, but it carries pedagogical framing in its early sections that restates knowledge Claude already has.

Suggestions

Trim Section 1 ('Recognize the Physical Process') and Section 2 ('Reasoning Patterns') to the domain-to-formula mappings, removing restatements of what half-life, dilution, and exponential decay are.

Cut the generic MC test-taking lore in Section 5 (e.g., 'All/None of the above correct ~25% of the time', 'longest option more often correct') and keep only the process steps specific to this skill.

Consider moving the per-script formula reference tables (Section 6) into a single short reference file to reduce inline length while keeping the overview in SKILL.md.

Dimension	Reasoning	Score
Conciseness	Mostly actionable but Sections 1–2 ('Recognize the Physical Process', 'Reasoning Patterns') and the MC traps lore pedagogically restate concepts Claude already knows (half-life, dilution, exponential decay), and the ~270-line body could be tightened.	2 / 3
Actionability	Provides fully executable Python templates (numpy/scipy) and copy-paste-ready script invocations with complete argument examples and formulas for every bundled tool.	3 / 3
Workflow Clarity	Computation pattern is explicitly sequenced with a validation checkpoint (extract givens → identify unknown → write script → run → 'VERIFY: substitute your answer back'), and batch MC processing adds a feedback loop.	3 / 3
Progressive Disclosure	SKILL.md is an overview with clearly signaled one-level-deep references to real bundled scripts (all 9 referenced paths verified to exist), each documented with usage, types, and formulas rather than inlined.	3 / 3
	Total	11 / 12 Passed

Description

100%

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

The description is specific, trigger-rich, and complete with an explicit 'Use for' clause in third person, covering a well-defined computational-biophysics niche. It does not over-claim or pad with fluff.

Dimension	Reasoning	Score
Specificity	Lists many specific concrete capabilities with named sub-quantities ('PK volume of distribution, clearance, half-life', 'R0, attack rate', 'LD50, NOAEL', 'Hardy-Weinberg, Fst', 'Michaelis-Menten'), matching the 'lists multiple specific concrete actions' anchor.	3 / 3
Completeness	Explicitly answers both 'what' (solve quantitative problems across the listed domains) and 'when' via a 'Use for first-principles quantitative biology calculations, dose calculations, exposure assessment...' trigger clause.	3 / 3
Trigger Term Quality	Covers natural domain terms a biophysics user would say — pharmacokinetics, epidemiology, dose calculations, exposure assessment, enzyme kinetics, thermodynamics — with broad coverage rather than only jargon.	3 / 3
Distinctiveness Conflict Risk	Clear computational-biophysics niche with domain-specific triggers (PK, R0, LD50, Fst, Michaelis-Menten) unlikely to fire for unrelated skills.	3 / 3
	Total	12 / 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-computational-biophysics/SKILL.md
Commit: 089eb8e

Reviewed: about 8 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.