medical-device-mdr-auditor

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

Quality

46%

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Critical

Do not install without reviewing

Fix and improve this skill with Tessl

tessl review fix ./scientific-skills/Academic Writing/medical-device-mdr-auditor/SKILL.md

Quality

Content

35%

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

The skill has a genuinely useful regulatory core (MDR check points, parameters, output JSON, exit codes) with real bundle files, but it is buried under large amounts of generic templated boilerplate and duplicated/contradictory sections that hurt token efficiency. Trimming the boilerplate and consolidating the duplicated usage blocks would substantially improve it.

Suggestions

Remove the generic templated sections ('Key Features', 'Implementation Details', 'Risk Assessment', 'Security Checklist', 'Evaluation Criteria', 'Lifecycle Status') that restate the same ideas; keep only the MDR-specific content.

Consolidate the two contradictory usage blocks ('Example Usage' vs 'Usage') into one with portable relative paths instead of the /Users/z04030865/... absolute path.

Move the detailed MDR check-point lists and output-format spec into references/ and keep SKILL.md as a lean overview with explicit validation steps (validate inputs -> run audit -> check exit code -> report).

Dimension	Reasoning	Score
Conciseness	The body is heavily padded with templated, generic sections ('Key Features', 'Dependencies', 'Implementation Details', 'Risk Assessment', 'Security Checklist', 'Evaluation Criteria', 'Lifecycle Status') that restate the same points and add little Claude-specific knowledge, plus contradictory duplicated 'Usage'/'Example Usage' blocks.	1 / 3
Actionability	It provides concrete executable commands (py_compile, --help, --input/--class invocations) and a real output JSON example, but the core audit logic lives in main.py rather than the body, and one usage block uses a non-portable absolute path (/Users/z04030865/...) reducing copy-paste readiness.	2 / 3
Workflow Clarity	A numbered Workflow and a fallback path exist, but validation checkpoints are implicit (relying on py_compile/exit codes) and the 'Audit-Ready Commands' duplicate rather than add validation steps; for a batch/destructive-style audit operation the rubric would expect explicit validate->fix->retry loops, capping this at 2.	2 / 3
Progressive Disclosure	A real one-level reference (references/audit-reference.md) exists and is linked once, but the body is otherwise a monolithic wall of inline content that could be split (check points, compliance levels, output format) into references; structure is present but not well separated.	2 / 3
	Total	7 / 12 Passed

Description

57%

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 clearly distinct within the medical-device regulatory niche, but it lacks an explicit 'Use when...' trigger clause and lists only a single action, which caps both completeness and specificity. Adding trigger phrases and a couple more concrete actions would lift it to full marks.

Suggestions

Add an explicit trigger clause, e.g. 'Use when auditing medical device technical files for EU MDR 2017/745 compliance, CE marking documentation, or regulatory submissions.'

List more concrete actions (e.g. 'check required documents, classify findings by severity, generate a compliance report') instead of just 'Audit'.

Include natural user terms like 'compliance', 'CE marking', and 'regulatory audit' for better trigger coverage.

Dimension	Reasoning	Score
Specificity	It names the domain ('medical device technical files', 'EU MDR 2017/745') and a concrete action ('Audit'), but lists only one action rather than multiple specific concrete actions like 'check documents, classify findings, generate reports'.	2 / 3
Completeness	It answers 'what' (audit medical device technical files against EU MDR) but has no explicit 'Use when...' trigger clause, so the 'when' is only implied and per guideline is capped at 2.	2 / 3
Trigger Term Quality	It includes relevant domain keywords ('medical device', 'technical files', 'EU MDR 2017/745'), but misses common natural variations a user would say such as 'compliance', 'CE marking', or 'regulatory audit'.	2 / 3
Distinctiveness Conflict Risk	The EU MDR 2017/745 medical-device niche is clearly specific with distinct regulatory triggers, making it unlikely to fire for the wrong skill.	3 / 3
	Total	9 / 12 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
Commit: 7cc5680

Reviewed: 3 days 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.