CtrlK
BlogDocsLog inGet started
Tessl Logo

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.

69

Quality

85%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

SKILL.md
Quality
Evals
Security

Quality

Content

70%

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

The body is a well-structured, comprehensive workflow with clear sequencing and validation checkpoints, but it lacks executable code examples and references bundle files that are absent from the repository. Tightening redundancy and providing the missing referenced files would raise the weaker dimensions.

Suggestions

Provide the referenced bundle files (phase-procedures-detailed.md, evidence-grading.md, report-templates.md, phase-details.md, test_skill.py) in a references/ directory so the signaled progressive-disclosure links resolve.

Add at least one executable Python example in the COMPUTE, DON'T DESCRIBE section (e.g. a minimal pandas/scipy snippet operating on tool output) so the guidance is copy-paste ready rather than descriptive.

Trim repeated 'for pharmaceuticals only' / dependency notes by consolidating them into a single phase-applicability note to reduce token redundancy.

DimensionReasoningScore

Conciseness

Mostly dense, useful reference material (tables, tool lists, phases) with little concept-overhead, but some redundancy (e.g. repeated 'for pharmaceuticals only' notes and overlapping dependency/fallback comments) means it could be tightened.

2 / 3

Actionability

Tool signatures with parameters are concrete, but there are no executable code or copy-paste commands — the 'COMPUTE, DON'T DESCRIBE' section instructs Python use without giving an executable example, so guidance is incomplete.

2 / 3

Workflow Clarity

The 8-phase sequence is clearly ordered with explicit dependencies, phase-scoped fallbacks, and a Mandatory Completeness Checklist that functions as validation checkpoints (data or explicit 'No data' notes).

3 / 3

Progressive Disclosure

The body is well-organized and signals one-level-deep references (phase-procedures-detailed.md, evidence-grading.md, report-templates.md, phase-details.md, test_skill.py), but those bundle files do not exist in references/ — the references are broken.

2 / 3

Total

9

/

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, well-triggered, complete, and distinctive, with explicit 'Use for...' guidance and concrete data-source integrations. It is a strong, concise description with no fluff.

DimensionReasoningScore

Specificity

Lists multiple specific concrete actions and integrations ('ADMET-AI predictions, CTD toxicogenomics, PubChemTox experimental data, GHS/IARC hazard classification', 'dose-response evaluation', 'acute (LD50) vs chronic toxicity assessment').

3 / 3

Completeness

Clearly answers both what (the assessment and integrated data sources) and when ('Use for chemical hazard identification, occupational/consumer-product toxicity, dose-response evaluation, and acute (LD50) vs chronic toxicity assessment').

3 / 3

Trigger Term Quality

Includes natural terms users would actually say — 'toxic', 'ADMET', 'dose-response', 'LD50', 'occupational/consumer-product toxicity', 'chemical hazard identification'.

3 / 3

Distinctiveness Conflict Risk

Occupies a clear chemical-safety/toxicology niche with distinct triggers and a differentiating clause ('Distinguishes drug toxicity from environmental chemical toxicity'), unlikely to conflict; third-person voice is used.

3 / 3

Total

12

/

12

Passed

Validation

100%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
mims-harvard/ToolUniverse
Reviewed

Table of Contents

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.