Medical device risk management specialist implementing ISO 14971 throughout product lifecycle. Provides risk analysis, risk evaluation, risk control, and post-production information analysis. Use when user mentions risk management, ISO 14971, risk analysis, FMEA, fault tree analysis, hazard identification, risk control, risk matrix, benefit-risk analysis, residual risk, risk acceptability, or post-market risk.
91
85%
Does it follow best practices?
Impact
94%
1.09xAverage 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 a strong skill description that clearly defines its domain (medical device risk management per ISO 14971), lists specific capabilities, and provides comprehensive trigger terms via an explicit 'Use when...' clause. The description is concise yet thorough, covering both the what and when effectively with highly distinctive terminology that minimizes conflict risk.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: risk analysis, risk evaluation, risk control, post-production information analysis, and references specific methodologies like FMEA and fault tree analysis. Also specifies the standard (ISO 14971) and scope (product lifecycle). | 3 / 3 |
Completeness | Clearly answers both 'what' (risk analysis, evaluation, control, post-production information analysis per ISO 14971) and 'when' with an explicit 'Use when...' clause listing numerous trigger terms. | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural terms users would say: 'risk management', 'ISO 14971', 'FMEA', 'fault tree analysis', 'hazard identification', 'risk control', 'risk matrix', 'benefit-risk analysis', 'residual risk', 'risk acceptability', 'post-market risk'. These are all terms a user working in medical device risk management would naturally use. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive niche combining medical devices, ISO 14971, and specific risk management methodologies. The domain-specific terminology (FMEA, fault tree analysis, hazard identification, residual risk) makes it very unlikely to conflict with general risk or document 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-structured risk management skill with excellent workflow clarity and progressive disclosure. Its main weaknesses are moderate verbosity—many tables and decision frameworks overlap in content—and a lack of fully concrete, worked-through examples that would make the guidance immediately actionable rather than template-oriented. Trimming redundant tables and adding one complete end-to-end hazard example would significantly improve it.
Suggestions
Add one complete worked example showing a specific hazard traced through the entire process (identification → analysis → evaluation → control → residual risk), filling in the templates with realistic data.
Consolidate redundant risk acceptability information—the same accept/ALARP/unacceptable actions appear in at least three separate tables/trees; merge into a single authoritative reference.
Include a concrete usage example for risk_matrix_calculator.py with sample input and expected output rather than just referencing --help.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is extensive and well-structured but includes significant redundancy across sections (e.g., risk acceptability actions repeated in multiple tables and decision trees). Several tables restate information Claude would already know about ISO 14971 concepts. The document could be substantially trimmed while preserving all actionable guidance. | 2 / 3 |
Actionability | The skill provides structured workflows, templates, and decision trees which are useful, but most content is procedural guidance rather than executable artifacts. The Risk Control Option Analysis template is a good fill-in-the-blank format, but there are no complete worked examples showing a real hazard analyzed end-to-end. The script reference exists but lacks concrete usage examples beyond --help. | 2 / 3 |
Workflow Clarity | Each major workflow (planning, analysis, evaluation, control, post-production) has clearly numbered sequential steps with explicit validation checkpoints at the end. Decision trees provide clear branching logic for risk evaluation and control selection. The risk control workflow includes feedback loops for new hazards introduced and residual risk re-evaluation. | 3 / 3 |
Progressive Disclosure | The document provides a clear table of contents, well-organized sections with appropriate depth, and references to external files (risk-analysis-methods.md, risk-assessment-templates.md, iso14971-implementation-guide.md) for detailed content. References are one level deep and clearly signaled. Related skills are linked at the end. | 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.
f567c61
Table of Contents
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.