drug-interaction-checker

Check for interactions between multiple medications, including severity classification and mechanism explanations.

Quality

60%

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/Evidence Insight/drug-interaction-checker/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 concrete commands and a clear output contract, but it is padded with generic boilerplate and inline reference content that hurts conciseness and progressive disclosure. Trimming the filler and pushing detail into references would raise both dimensions.

Suggestions

Remove the placeholder pointer sections ('See ## X above') and the generic boilerplate (Security Checklist, Evaluation Criteria, Lifecycle Status, Response Template) that do not add drug-interaction knowledge.

Move the full severity-criteria table and JSON output schema into the existing references and keep only a concise summary inline.

Add an explicit validation/verification step to the workflow (e.g. confirm inputs parse, re-check on failure) to introduce a real feedback loop.

Dimension	Reasoning	Score
Conciseness	The body is noticeably verbose: multiple sections are pure pointers ('See ## Features above for related details', 'See ## Prerequisites above') and generic boilerplate (Security Checklist, Evaluation Criteria, Lifecycle Status, Response Template) pads the skill without adding domain knowledge Claude lacks.	2 / 5
Actionability	Provides concrete, mostly copy-paste-ready guidance ('python scripts/main.py --drugs "Warfarin" "Aspirin" "Ibuprofen"', a module import example, a parameter table, and a JSON output schema) with only minor gaps such as no sample runtime output.	4 / 5
Workflow Clarity	A numbered workflow and a Quick Check (py_compile) exist, but the main steps lack explicit validate->fix->retry checkpoints; sequence is present yet validation is implicit.	3 / 5
Progressive Disclosure	References (interactions_db.json, severity_criteria.md, cyp450_substrates.json) are real and one level deep, but a large amount of content that belongs in those references (severity table, full output schema, security checklist) is inlined in SKILL.md.	3 / 5
	Total	12 / 20 Passed

Description

70%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 is specific and occupies a distinct niche, but it omits any explicit 'when to use' trigger guidance, which caps its completeness. Adding a 'Use when...' clause would lift the weakest dimension.

Suggestions

Append a 'Use when...' clause naming concrete triggers (e.g. 'Use when checking for drug or medication interactions, severity, or mechanism explanations').

Add the synonym 'drugs' alongside 'medications' to broaden natural trigger coverage.

Optionally mention supported input forms (drug names, generic or brand) to round out the action list.

Dimension	Reasoning	Score
Specificity	Names the domain plus several concrete actions ('Check for interactions between multiple medications, including severity classification and mechanism explanations'), but coverage stops at three actions rather than a comprehensive list.	4 / 5
Completeness	It gives a clear 'what' but no 'Use when...' clause or equivalent trigger guidance; per the rubric a missing explicit trigger caps completeness at 3.	3 / 5
Trigger Term Quality	Includes natural terms like 'interactions', 'medications', 'severity', and 'mechanism' that users would say, but misses common synonyms such as 'drugs' and any file-extension-style triggers.	4 / 5
Distinctiveness Conflict Risk	Drug-interaction checking is a clear niche with distinct triggers and minimal overlap risk with other skills.	5 / 5
	Total	16 / 20 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
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: aipoch/medical-research-skills
Path: scientific-skills/Evidence Insight/drug-interaction-checker/SKILL.md
Commit: 63c61d3

Reviewed: 6 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.