drug-interaction-checker
Check for drug-drug interactions between multiple medications. Trigger when user asks about medication compatibility, "can I take X with Y", drug interactions, contraindications, or safety of combining pharmaceuticals.
86
Quality
81%
Does it follow best practices?
Impact
96%
1.29xAverage score across 3 eval scenarios
Passed
No known issues
Quality
Discovery
89%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is a well-crafted skill description with excellent trigger terms and completeness. The explicit 'Trigger when' clause with natural user phrases like 'can I take X with Y' makes it highly discoverable. The main weakness is limited specificity in describing the range of actions beyond basic interaction checking.
Suggestions
Expand the capability description to include additional concrete actions such as 'identify interaction severity, suggest timing adjustments, explain pharmacological mechanisms'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description names the domain (drug-drug interactions) and one action (check for interactions), but lacks multiple concrete actions like 'identify severity levels, suggest alternatives, explain mechanisms'. | 2 / 3 |
Completeness | Clearly answers both what (check for drug-drug interactions) and when (explicit 'Trigger when' clause with multiple specific scenarios including the natural phrase 'can I take X with Y'). | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural user phrases: 'can I take X with Y', 'drug interactions', 'medication compatibility', 'contraindications', 'combining pharmaceuticals' - these match how users naturally ask about this topic. | 3 / 3 |
Distinctiveness Conflict Risk | Very clear niche focused specifically on drug-drug interactions with distinct pharmaceutical terminology; unlikely to conflict with general medical or chemistry skills due to specific trigger terms like 'medication compatibility' and 'contraindications'. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
72%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
The skill provides solid actionable guidance with executable code examples and clear output formats. However, it's bloated with boilerplate sections (Risk Assessment, Security Checklist, Evaluation Criteria, Lifecycle Status) that add no instructional value and waste tokens. The core drug interaction checking content is well-structured but lacks error handling workflows.
Suggestions
Remove boilerplate sections (Risk Assessment, Security Checklist, Evaluation Criteria, Lifecycle Status) that don't provide actionable guidance for the task
Add error handling workflow: what to do when drug names aren't recognized, when no interactions are found, or when the database lacks data
Consolidate the Limitations section into a brief note rather than a separate section with obvious statements
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Contains significant boilerplate that doesn't add value (Risk Assessment table, Security Checklist, Evaluation Criteria, Lifecycle Status sections). The core functionality is reasonably documented but padded with template content Claude doesn't need. | 2 / 3 |
Actionability | Provides fully executable code examples with clear CLI usage and Python module import. The output JSON schema is concrete and copy-paste ready, and parameters are well-documented with types and defaults. | 3 / 3 |
Workflow Clarity | For a single-purpose tool, the usage is clear, but there's no validation workflow for checking results or handling errors. Missing guidance on what to do if interactions aren't found or if drug names aren't recognized. | 2 / 3 |
Progressive Disclosure | Good structure with clear sections and appropriate references to external files (interactions_db.json, severity_criteria.md, cyp450_substrates.json). Navigation is straightforward with one-level-deep references. | 3 / 3 |
Total | 10 / 12 Passed |
Validation
90%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 10 / 11 Passed | |
- Repository
- aipoch/medical-research-skills
- Commit
ca9aaa4
- 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.