medical-device-mdr-auditor

Audit medical device technical files against EU MDR 2017/745 regulations.

Quality

34%

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Critical

Do not install without reviewing

Optimize this skill with Tessl

npx tessl skill review --optimize ./scientific-skills/Academic Writing/medical-device-mdr-auditor/SKILL.md

Quality

Discovery

54%

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 identifies a clear, distinctive niche (EU MDR medical device auditing) with strong domain-specific trigger terms. However, it lacks a 'Use when...' clause and lists only a single action ('audit'), limiting both completeness and specificity. Adding explicit trigger guidance and enumerating specific audit activities would significantly improve it.

Suggestions

Add a 'Use when...' clause, e.g., 'Use when the user asks about MDR compliance, technical documentation review, or CE marking readiness for medical devices.'

List more specific actions beyond 'audit', such as 'Reviews essential requirements checklists, evaluates risk management documentation, checks clinical evaluation reports, and identifies gaps in technical files.'

Dimension	Reasoning	Score
Specificity	Names the domain (medical device technical files, EU MDR 2017/745) and one action (audit), but does not list multiple specific concrete actions like identifying gaps, generating compliance reports, or checking classification.	2 / 3
Completeness	The description answers 'what' (audit medical device technical files against EU MDR) but has no explicit 'Use when...' clause or equivalent trigger guidance, which per the rubric caps completeness at 2, and since the 'what' is also only a single action, this falls closer to 1.	1 / 3
Trigger Term Quality	Includes strong natural keywords a user would say: 'medical device', 'technical files', 'EU MDR', '2017/745', 'audit', and 'regulations'. These are the exact terms someone working in this domain would use.	3 / 3
Distinctiveness Conflict Risk	This is a very specific niche — EU MDR 2017/745 medical device auditing — that is highly unlikely to conflict with other skills. The regulatory reference number and domain make it clearly distinguishable.	3 / 3
	Total	9 / 12 Passed

Implementation

14%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

This skill is heavily padded with generic boilerplate sections (Risk Assessment, Security Checklist, Lifecycle Status, Evaluation Criteria, Response Template, Input Validation) that are not specific to MDR auditing and waste significant token budget. The MDR-specific content (checkpoint checklists, output format, compliance levels) is genuinely valuable but is buried within repetitive, template-driven filler. The workflow is entirely generic with no domain-specific audit sequencing or validation steps.

Suggestions

Remove all generic boilerplate sections (Risk Assessment, Security Checklist, Lifecycle Status, Evaluation Criteria, Response Template, Output Requirements, Input Validation) that don't contain MDR-specific information — these waste tokens on things Claude already knows how to do.

Replace the generic workflow with an MDR-specific audit workflow: e.g., 1) Identify device class → 2) Load class-specific checklist → 3) Scan technical file directory → 4) Map found documents to required checkpoints → 5) Validate completeness of each found document → 6) Generate compliance report with findings.

Remove the hardcoded local path (/Users/z04030865/...) from usage examples and eliminate circular section references ('See ## Prerequisites above').

Consolidate the three separate sections that repeat `python -m py_compile scripts/main.py` into a single Quick Start section, and move the detailed MDR checklists to a referenced file to improve progressive disclosure.

Dimension	Reasoning	Score
Conciseness	Extremely verbose and repetitive. Contains massive amounts of boilerplate (Risk Assessment, Security Checklist, Lifecycle Status, Evaluation Criteria, Response Template) that add no value for Claude. Multiple sections reference each other circularly ('See ## Prerequisites above', 'See ## Usage above'). The same information (e.g., running py_compile, the script path) is repeated in multiple sections. Hardcoded local paths (/Users/z04030865/...) are included. Much content explains things Claude already knows.	1 / 3
Actionability	The MDR checkpoint checklists (CER, PMS, PMCF) are genuinely useful and specific. The parameter table and output JSON example are concrete and actionable. However, the actual script commands use hardcoded local paths, there's no executable code showing how the audit logic works, and the 'Example run plan' is generic boilerplate rather than domain-specific guidance.	2 / 3
Workflow Clarity	The workflow section is entirely generic ('Confirm the user objective', 'Validate that the request matches the documented scope') with no MDR-specific steps. There are no validation checkpoints for the audit process itself. The 'Example run plan' is also generic boilerplate. For a regulatory audit involving destructive decisions (compliance/non-compliance), the lack of verification steps and domain-specific sequencing is a significant gap.	1 / 3
Progressive Disclosure	The document is a monolithic wall of text with 20+ sections, many of which are boilerplate that could be removed entirely. Sections reference each other circularly. The single reference to 'references/audit-reference.md' is buried at the bottom. No bundle files are provided to verify the reference. Content that should be in separate files (e.g., the full MDR checklist, the response template) is inline.	1 / 3
	Total	5 / 12 Passed

Validation

90%

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 — 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: 73f6514

Reviewed: about 15 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.