tooluniverse-chemical-safety

Chemical safety and toxicology assessment integrating ADMET-AI predictions, CTD toxicogenomics, PubChemTox experimental data, GHS/IARC hazard classification, and exposure-context analysis. Use for chemical hazard identification, occupational/consumer-product toxicity, dose-response evaluation, and acute (LD50) vs chronic toxicity assessment. Distinguishes drug toxicity from environmental chemical toxicity.

Quality

88%

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

85%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 highly actionable, well-sequenced toxicology workflow with concrete tool calls, validation checkpoints, and a completeness checklist. The main defect is progressive disclosure: the body points to five bundle files that are not present in the skill bundle, breaking the reference chain.

Suggestions

Ship the referenced bundle files (phase-procedures-detailed.md, report-templates.md, evidence-grading.md, phase-details.md, test_skill.py) under references/ or scripts/, or remove the dangling references from the body.

Trim the redundant restatement at the end of the intro and the final 'Summary' section, whose 'Best for' and 'Outputs' duplicate the 'When to Use This Skill' content.

Consolidate phase-details.md and phase-procedures-detailed.md if their content overlaps, to keep references one level deep and avoid navigation ambiguity.

Dimension	Reasoning	Score
Conciseness	Largely lean and operational (tool lists, phase map, risk matrix, checklist) assuming Claude's competence, with only minor padding — e.g. the 'Comprehensive chemical safety analysis integrating...' line and the final 'Summary' section restate material already covered. Not a 5 due to those redundant restatements.	4 / 5
Actionability	Provides concrete, copy-paste-ready tool calls with exact parameters (e.g. 'ADMETAI_predict_toxicity (smiles: list[str])', 'CTD_get_chemical_gene_interactions (input_terms: str)') covering the common cases across all phases.	5 / 5
Workflow Clarity	Clear 8-phase sequence with Phase 0 marked 'ALWAYS FIRST', explicit validation steps (get_tool_info param verification, mandatory evidence grading), feedback loops (fallback to STRING/CTD+PubChemTox on failure, defer to experimental data on conflict), and a mandatory completeness checklist.	5 / 5
Progressive Disclosure	The body is well-sectioned and clearly signals one-level-deep references ('See phase-procedures-detailed.md', 'report-templates.md', 'evidence-grading.md', 'phase-details.md', 'test_skill.py'), but no references/, scripts/, or assets/ bundle directories exist, so every referenced file is a dead end and the detailed procedures the overview points to are effectively missing.	3 / 5
	Total	17 / 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, third-person description that clearly states both capability and trigger conditions with concrete, domain-specific actions and explicit drug-vs-environmental disambiguation. Only minor gap is a few natural keyword synonyms.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete capabilities — 'integrating ADMET-AI predictions, CTD toxicogenomics, PubChemTox experimental data, GHS/IARC hazard classification, and exposure-context analysis' plus 'hazard identification, ... dose-response evaluation, and acute (LD50) vs chronic toxicity assessment' — comprehensive and specific rather than abstract.	5 / 5
Completeness	Explicitly answers both what ('Chemical safety and toxicology assessment integrating...') and when ('Use for chemical hazard identification, occupational/consumer-product toxicity, dose-response evaluation, and acute (LD50) vs chronic toxicity assessment') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Good natural-term coverage ('chemical safety', 'toxicity', 'hazard identification', 'occupational/consumer-product toxicity', 'LD50', 'acute vs chronic') users would actually say, but misses common synonyms/variations like SMILES or file/identifier cues. Not clearly a 5 since a few natural phrasings are absent.	4 / 5
Distinctiveness Conflict Risk	Clear niche (chemical safety/toxicology) with distinct triggers and an explicit disambiguation ('Distinguishes drug toxicity from environmental chemical toxicity'), minimizing overlap with other skills.	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-chemical-safety/SKILL.md
Commit: 7fe234c

Reviewed: 3 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.