fda-consultant-specialist
FDA regulatory consultant for medical device companies. Provides 510(k)/PMA/De Novo pathway guidance, QSR (21 CFR 820) compliance, HIPAA assessments, and device cybersecurity. Use when user mentions FDA submission, 510(k), PMA, De Novo, QSR, premarket, predicate device, substantial equivalence, HIPAA medical device, or FDA cybersecurity.
93
85%
Does it follow best practices?
Impact
99%
1.07xAverage score across 6 eval scenarios
Passed
No known issues
Quality
Discovery
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.
This is an excellent skill description that clearly defines a narrow regulatory domain with specific capabilities and comprehensive trigger terms. It follows the recommended pattern with an explicit 'Use when...' clause and uses third-person voice throughout. The description is concise yet thorough, covering both the scope of expertise and the exact scenarios that should activate this skill.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 510(k)/PMA/De Novo pathway guidance, QSR (21 CFR 820) compliance, HIPAA assessments, and device cybersecurity. These are clearly defined, domain-specific capabilities. | 3 / 3 |
Completeness | Clearly answers both 'what' (FDA regulatory consulting, pathway guidance, QSR compliance, HIPAA assessments, cybersecurity) and 'when' with an explicit 'Use when...' clause listing specific trigger terms. | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural terms users would say: 'FDA submission', '510(k)', 'PMA', 'De Novo', 'QSR', 'premarket', 'predicate device', 'substantial equivalence', 'HIPAA medical device', 'FDA cybersecurity'. These are the exact terms a medical device professional would use. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive niche focused on FDA medical device regulation. The specific regulatory terms (510(k), PMA, De Novo, QSR, 21 CFR 820) are extremely unlikely to conflict with other skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
70%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a well-organized regulatory reference skill with excellent workflow clarity and progressive disclosure. Its main weaknesses are moderate verbosity (covering broad regulatory territory that Claude partially knows) and limited actionability—it reads more as a structured knowledge base than an executable instruction set. The decision frameworks and checkpoint-based workflows are strong, but the skill would benefit from more concrete, copy-paste-ready artifacts like template sections or example outputs.
Suggestions
Add concrete output examples—e.g., a sample SE comparison table structure, a template Pre-Sub question list, or example CAPA documentation—to increase actionability beyond procedural descriptions.
Trim sections covering general knowledge Claude already has (e.g., HIPAA safeguard categories, basic CAPA concepts) and focus token budget on project-specific decision logic and non-obvious regulatory nuances like common FDA rejection reasons or specific eSTAR formatting requirements.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is generally well-structured with tables and decision trees rather than prose, but it's quite lengthy (~250 lines) and includes some information Claude likely already knows (e.g., what HIPAA safeguards are, basic CAPA concepts). The pathway comparison table with specific fees and timelines adds genuine value, but sections like HIPAA applicability and safeguards are largely general knowledge that could be trimmed. | 2 / 3 |
Actionability | The skill provides structured frameworks, decision trees, and process steps, but most guidance is procedural/conceptual rather than executable. The bash script examples at the end reference scripts that may or may not exist, and the core content is more of a reference guide than copy-paste-ready instructions. There are no concrete examples of actual submission content, SE comparison language, or template outputs. | 2 / 3 |
Workflow Clarity | Multi-step processes are clearly sequenced with explicit checkpoints throughout. The 510(k) submission workflow has phase-based organization with checkpoint gates, the Design Controls workflow includes verification steps at each stage, and the CAPA process has a clear 7-step sequence with effectiveness monitoring. These workflows include validation/verification at appropriate points. | 3 / 3 |
Progressive Disclosure | The content is well-organized with a table of contents, clear section headers, and one-level-deep references to external files (references/ and scripts/ directories) that are clearly signaled with descriptive tables. Each major section ends with a reference pointer to detailed guidance, maintaining a clean overview-to-detail structure. | 3 / 3 |
Total | 10 / 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.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
- Repository
- alirezarezvani/claude-skills
- Commit
f567c61
- 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.