tooluniverse-adverse-outcome-pathway

Map environmental and industrial chemicals to adverse outcome pathways (AOPs) — molecular initiating event to organ-level toxicity. Uses AOPWiki, GHS classification, IARC carcinogen status, and LD50 data. Use for environmental/industrial chemical risk assessment, regulatory-grade hazard characterization, and AOP stressor mapping. Distinct from drug-safety analysis (use tooluniverse-pharmacovigilance for drugs).

Quality

83%

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

75%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 well-structured, highly actionable tool-orchestration skill with a clear phased workflow and concrete examples. The main weakness is conciseness — the Reasoning Framework over-explains domain concepts Claude already knows.

Suggestions

Trim the Interpretation Guidance section: remove definitions Claude already knows (e.g., 'LD50 values indicate acute toxicity (lower = more toxic)', IARC group meanings, GHS category ranges) and keep only skill-specific interpretation rules.

Add an explicit validate/retry checkpoint in Phase 1 for when PubChem_get_CID_by_compound_name returns no CID (e.g., try alternate names or fall back to CTD's name-based input_terms) instead of only noting CTD accepts names directly.

Consider moving the dense Tool Parameter Reference table and Reasoning Framework into a references/ file, keeping SKILL.md as a lean overview with well-signaled one-level-deep links.

Dimension	Reasoning	Score
Conciseness	Mostly efficient with tool-call examples, but the Reasoning Framework re-explains concepts Claude already knows (LD50 meaning, IARC group definitions, 'lower = more toxic', GHS category ranges), which could be trimmed.	3 / 5
Actionability	Provides concrete, executable tool invocations with parameters, named response fields, and copy-paste-ready parsing patterns like [s["name"] for s in aop["data"]["stressors"]] covering the common cases.	5 / 5
Workflow Clarity	Clear four-phase sequence with a Phase 1 dependency checkpoint (resolve CID before PubChemTox calls) and a fallback-chains table, but lacks explicit validate/retry feedback loops for failed CID resolution or empty tool responses.	4 / 5
Progressive Disclosure	Well-organized single-file skill with clear section headers and no nested references; the inline Tool Parameter Reference and Reasoning Framework are dense but appropriately placed, with only minor organization gaps.	4 / 5
	Total	16 / 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, specific description that clearly defines capabilities, explicit use triggers, and clean separation from sibling skills. Minor room for improvement in adding lay synonyms alongside the domain jargon.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — mapping chemicals to AOPs, GHS classification, IARC carcinogen status, and LD50 data — with comprehensive coverage of the skill's capabilities.	5 / 5
Completeness	Explicitly answers 'what' (map chemicals to AOPs and hazard data) and 'when' via a concrete 'Use for environmental/industrial chemical risk assessment...' clause.	5 / 5
Trigger Term Quality	Includes natural phrases like 'environmental/industrial chemical risk assessment' and 'hazard characterization', but leans heavily on domain jargon (AOP, GHS, IARC, LD50) and misses some common synonyms like 'toxicity' or 'ecotox'.	4 / 5
Distinctiveness Conflict Risk	Carves a clear niche (environmental/industrial chemicals) and explicitly disambiguates from the drug-safety skill ('Distinct from drug-safety analysis'), minimizing 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-adverse-outcome-pathway/SKILL.md
Commit: 1b02920

Reviewed: 1 day 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.