mdr-745-specialist
EU MDR 2017/745 compliance specialist for medical device classification, technical documentation, clinical evidence, and post-market surveillance. Covers Annex VIII classification rules, Annex II/III technical files, Annex XIV clinical evaluation, and EUDAMED integration.
85
70%
Does it follow best practices?
Impact
96%
0.98xAverage score across 6 eval scenarios
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./ra-qm-team/mdr-745-specialist/SKILL.mdQuality
Discovery
82%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 strong, domain-specific description with excellent specificity and trigger term coverage for regulatory affairs professionals. Its main weakness is the absence of an explicit 'Use when...' clause, which would help Claude know precisely when to select this skill. Adding trigger guidance would elevate this from a good to an excellent description.
Suggestions
Add an explicit 'Use when...' clause, e.g., 'Use when the user asks about EU MDR compliance, medical device regulation, CE marking under MDR, or any Annex-specific requirements under Regulation 2017/745.'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions and domains: medical device classification, technical documentation, clinical evidence, post-market surveillance, and further specifies Annex VIII classification rules, Annex II/III technical files, Annex XIV clinical evaluation, and EUDAMED integration. | 3 / 3 |
Completeness | The 'what' is well-covered with specific regulatory areas and annexes, but there is no explicit 'Use when...' clause or equivalent trigger guidance telling Claude when to select this skill. Per the rubric, a missing 'Use when...' clause caps completeness at 2. | 2 / 3 |
Trigger Term Quality | Includes strong natural keywords users in this domain would use: 'EU MDR', '2017/745', 'medical device classification', 'technical documentation', 'clinical evidence', 'post-market surveillance', 'Annex VIII', 'Annex II/III', 'Annex XIV', 'EUDAMED'. These are precisely the terms a regulatory affairs professional would search for. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with a very clear niche: EU MDR 2017/745 compliance for medical devices. The specific regulation number, annex references, and EUDAMED mention make it extremely unlikely to conflict with other skills. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
57%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 good progressive disclosure and clear section structure. Its main weaknesses are that the workflows lack concrete feedback loops and error recovery steps, and much of the content reads as reference tables rather than actionable instructions Claude can directly execute. The classification examples are a strength, but the skill would benefit from more specific validation criteria and decision-tree logic rather than generic procedural steps.
Suggestions
Add explicit feedback loops to workflows, e.g., 'If classification is ambiguous between two rules, apply the higher classification per Article 51(7)' rather than just 'Validate with Notified Body'.
Make validation steps concrete and actionable: specify what constitutes a passing validation check and what corrective actions to take on failure for each workflow.
For the classification workflow, provide a decision-tree or if/then logic structure rather than a sequential list, since classification is inherently branching logic.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is reasonably structured but includes some information Claude would already know (e.g., what EUDAMED modules contain, basic definitions). The tables are useful reference material but some sections like 'Qualified Evaluator Requirements' and general descriptions could be tightened. Overall moderately efficient but not maximally lean. | 2 / 3 |
Actionability | The skill provides structured workflows with numbered steps and useful reference tables, but most guidance is procedural description rather than executable. The tool commands are concrete, but the core regulatory workflows are checklists of what to do without specific how-to details (e.g., 'Conduct systematic literature search' lacks methodology). Classification examples are helpful but the overall content leans toward reference material rather than actionable instructions. | 2 / 3 |
Workflow Clarity | Each major section has numbered steps with a validation checkpoint at the end, which is good. However, the validation steps are generic ('Classification confirmed with Notified Body', 'Technical file reviewed for completeness') without specifying how to validate or what to do if validation fails. There are no explicit feedback loops or error recovery paths, which is important for regulatory compliance workflows where errors can be costly. | 2 / 3 |
Progressive Disclosure | The skill has a clear table of contents, well-organized sections with appropriate depth, and references to external files (references/mdr-classification-guide.md, references/clinical-evidence-requirements.md, references/technical-documentation-templates.md) that are one level deep and clearly signaled with descriptions of their contents. The structure supports easy navigation and discovery. | 3 / 3 |
Total | 9 / 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
- alirezarezvani/claude-skills
- Commit
967fe01
- 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.