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

92%

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%

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

A high-quality, executable toxicology skill with clear phased workflow, concrete tool examples, and good fallback handling. The only weakness is mild verbosity in the reasoning-framework section, which leans on explanatory domain prose that could be trimmed.

Suggestions

Tighten the "Reasoning Framework for Result Interpretation" section: convert the KER-strength and regulatory-context paragraphs into a compact checklist or fold the essentials into the evidence-grading table to cut tokens.

Consider moving the detailed "Tool Parameter Reference" table into a bundled reference file if the skill grows, keeping SKILL.md as an overview pointing one level deep.

The body mentions "tooluniverse-toxicology" as the drug-safety sibling while the description names "tooluniverse-pharmacovigilance" — align the sibling-skill name to avoid confusion.

Dimension	Reasoning	Score
Conciseness	Mostly efficient with executable tool calls and tables, but the "Reasoning Framework for Result Interpretation" section (evidence grading table, KER strength, regulatory context) is lengthy explanatory prose that risks restating domain knowledge Claude could be assumed to know; it could be tightened.	2 / 3
Actionability	Provides concrete, executable tool calls with real parameters (e.g. `PubChem_get_CID_by_compound_name(name="benzo[a]pyrene")` -> `cid: 9153`), a parameter reference table, and copy-paste-ready Python patterns — fully actionable.	3 / 3
Workflow Clarity	Four phases are explicitly sequenced (identity resolution -> AOP discovery -> hazard quantification -> toxicogenomics) with a parallel-call checkpoint in Phase 3 and cross-referencing guidance, plus a fallback-chain table for error recovery.	3 / 3
Progressive Disclosure	Single self-contained file with well-organized sections (When to Use, Key Tools, Workflow, Tool Parameter Reference, Common Patterns, Reasoning Framework, Fallback Chains); no bundle files to link, so the clean section structure earns the top anchor for a self-contained skill.	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.

A strong, specific description that answers what, when, and how it differs from sibling skills, all in concise third-person voice. No significant weaknesses; every dimension lands at the top anchor.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — "Map environmental and industrial chemicals to adverse outcome pathways (AOPs)", "GHS classification", "IARC carcinogen status", and "LD50 data" — matching the score-3 anchor of multiple specific concrete actions.	3 / 3
Completeness	Clearly states what (maps chemicals to AOPs using AOPWiki/GHS/IARC/LD50) and when ("Use for environmental/industrial chemical risk assessment, regulatory-grade hazard characterization, and AOP stressor mapping"), satisfying both halves explicitly.	3 / 3
Trigger Term Quality	Covers natural terms a researcher would say — "risk assessment", "hazard characterization", "AOP stressor mapping", "carcinogen", "GHS", "LD50" — with good breadth of natural vocabulary.	3 / 3
Distinctiveness Conflict Risk	Explicit disambiguation — "Distinct from drug-safety analysis (use tooluniverse-pharmacovigilance for drugs)" — carves a clear niche unlikely to trigger the wrong skill.	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-adverse-outcome-pathway/SKILL.md
Commit: 089eb8e

Reviewed: about 7 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.