toxicity-structure-alert

Analyze data with `toxicity-structure-alert` using a reproducible workflow, explicit validation, and structured outputs for review-ready interpretation.

Quality

39%

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

Fix and improve this skill with Tessl

tessl review fix ./scientific-skills/Data Analysis/toxicity-structure-alert/SKILL.md

Quality

Content

50%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.

The body is actionable with real commands, SMILES examples, and a clear output schema, but it is padded with redundant generic process sections and a generic workflow, and it underuses the reference bundle by inlining most material.

Suggestions

Consolidate the redundant process sections (Workflow, Output Requirements, Response Template, Inputs to Collect, Output Contract, Validation and Safety Rules) into one concise 'How to run' block.

Move the generic runtime/process checklist content into references/runtime_checklist.md and link to it by name instead of inlining.

Fix the 'Audit-Ready Commands' example to use a real SMILES string for --input so the validation command is consistent with the tool's actual input.

Dimension	Reasoning	Score
Conciseness	The ~300-line body carries many generic, overlapping boilerplate sections (Workflow, Output Requirements, Response Template, Inputs to Collect, Output Contract, Validation and Safety Rules) that restate the same process guidance and add little domain knowledge Claude lacks.	2 / 5
Actionability	Provides copy-paste-ready commands and real SMILES examples, a complete Python API snippet, documented parameters, and a concrete JSON output schema — minor gap being the 'Audit-Ready Commands' input that is a medical-text string rather than a SMILES.	4 / 5
Workflow Clarity	A sequence exists (Quick Check py_compile → run → review) but the Workflow section is generic boilerplate and the only validation checkpoint is a syntax compile check, with no output/result validation for the scan.	3 / 5
Progressive Disclosure	Real bundle files exist (scripts/main.py, references/runtime_checklist.md) and are referenced generically as directories, but most content is inlined in this long monolithic SKILL.md and the reference file is not linked by name.	3 / 5
	Total	12 / 20 Passed

Description

28%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.

The description names the tool but relies on generic process language instead of concrete capabilities and natural trigger phrases, and it omits any 'Use when...' guidance. It is distinguishable mainly by the tool name rather than by what it actually does.

Suggestions

Replace generic process language with concrete actions, e.g. 'Scan SMILES/SMARTS structures for known toxic structural alerts and report risk levels'.

Add an explicit trigger clause: 'Use when assessing drug molecules for toxicophores, mutagenicity/carcinogenicity alerts, or ADMET toxicity risk'.

Include natural user-facing terms (SMILES, toxicophores, structural alerts, mutagenicity) rather than only the tool name and 'data'.

Dimension	Reasoning	Score
Specificity	Names the domain (`toxicity-structure-alert`) but the actions are generic process descriptors — 'reproducible workflow, explicit validation, and structured outputs' — rather than concrete capabilities like scanning SMILES or identifying toxic alerts.	2 / 5
Completeness	Gives a vague process-oriented 'what' ('Analyze data with...') and has no 'Use when...' trigger clause, so it fails to answer 'when should Claude use it'.	2 / 5
Trigger Term Quality	Contains the tool name keyword but misses the natural phrases a user would actually say ('toxicity alerts', 'toxicophores', 'SMILES', 'mutagenicity'), relying on generic terms like 'data' and 'structured outputs'.	2 / 5
Distinctiveness Conflict Risk	The named tool `toxicity-structure-alert` is somewhat distinctive, but the surrounding 'analyze data / reproducible workflow / validation' language is generic and could overlap with other data-analysis skills.	3 / 5
	Total	9 / 20 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
relative_links	Relative link issues: 4 missing	Warning

	Total	14 / 16 Passed

Repository: aipoch/medical-research-skills
Path: scientific-skills/Data Analysis/toxicity-structure-alert/SKILL.md
Commit: f5ef65b

Reviewed: ~10 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.