tooluniverse-chemical-safety

Comprehensive chemical safety and toxicology assessment integrating ADMET-AI predictions, CTD toxicogenomics, FDA label safety data, DrugBank safety profiles, and STITCH chemical-protein interactions. Performs predictive toxicology (AMES, DILI, LD50, carcinogenicity), organ/system toxicity profiling, chemical-gene-disease relationship mapping, regulatory safety extraction, and environmental hazard assessment. Use when asked about chemical toxicity, drug safety profiling, ADMET properties, environmental health risks, chemical hazard assessment, or toxicogenomic analysis.

Quality

88%

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

77%

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 concrete tool calls, parameters, and a well-sequenced validated workflow, but it is verbose and monolithic. Splitting reference material into bundle files and trimming redundant sections would improve token efficiency and progressive disclosure.

Suggestions

Move the 'Tool Parameter Reference', 'Output Report Structure', and 'Limitations & Known Issues' sections into separate reference files (e.g. references/tool-reference.md, references/report-templates.md) and link to them from SKILL.md to improve progressive disclosure.

Remove the trailing 'Summary' section, which restates the integrated databases and capabilities already covered in 'When to Use This Skill' and the phase descriptions.

Replace filled mock-data example output tables with compact schema/format skeletons (headers only) to cut length without losing the format guidance.

Dimension	Reasoning	Score
Conciseness	Mostly actionable and accurate, but ~730 lines includes padding: filled mock-data output tables, a trailing 'Summary' section that restates capabilities already covered, and tool parameters repeated per phase and again in a reference table.	2 / 3
Actionability	Provides concrete tool names, exact parameter names and types, copy-ready example calls (e.g. 'ADMETAI_predict_toxicity(smiles=[resolved_smiles])'), explicit decision logic, and output templates per phase.	3 / 3
Workflow Clarity	Clear 8-phase sequence with explicit ordering ('ALWAYS FIRST'), a Mandatory Completeness Checklist as a validation checkpoint, tool-parameter verification, and fallback strategies with feedback for failed phases.	3 / 3
Progressive Disclosure	No bundle files exist and the skill is a 730-line monolith; the tool parameter reference, output report templates, and limitations sections are inline content that would be better split into separate reference files.	2 / 3
	Total	10 / 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, complete, and distinctive, naming concrete capabilities and providing an explicit 'Use when' trigger clause with natural user terms. It is on the verbose side but every element is concrete and domain-relevant rather than fluff.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions in third person ('Performs predictive toxicology (AMES, DILI, LD50, carcinogenicity)', 'chemical-gene-disease relationship mapping', 'regulatory safety extraction', 'environmental hazard assessment') rather than vague language.	3 / 3
Completeness	Explicitly answers both what the skill does (integrating named databases and prediction endpoints) and when to use it via an explicit 'Use when...' clause with concrete triggers.	3 / 3
Trigger Term Quality	The 'Use when asked about chemical toxicity, drug safety profiling, ADMET properties, environmental health risks, chemical hazard assessment, or toxicogenomic analysis' clause covers natural phrases a user would actually say.	3 / 3
Distinctiveness Conflict Risk	Occupies a clear chemical-safety/toxicology niche with named databases (ADMET-AI, CTD, FDA, DrugBank, STITCH) and domain-specific triggers unlikely to fire for unrelated skills.	3 / 3
	Total	12 / 12 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (734 lines); consider splitting into references/ and linking	Warning

	Total	15 / 16 Passed

Repository: wu-yc/LabClaw
Path: skills/pharma/tooluniverse-chemical-safety/SKILL.md
Commit: df37802

Reviewed: 2 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.