CtrlK
BlogDocsLog inGet started
Tessl Logo

iso-13485-certification

Comprehensive toolkit for preparing ISO 13485 certification documentation for medical device Quality Management Systems. Use when users need help with ISO 13485 QMS documentation, including (1) conducting gap analysis of existing documentation, (2) creating Quality Manuals, (3) developing required procedures and work instructions, (4) preparing Medical Device Files, (5) understanding ISO 13485 requirements, or (6) identifying missing documentation for medical device certification. Also use when users mention medical device regulations, QMS certification, FDA QMSR, EU MDR, or need help with quality system documentation.

76

1.45x
Quality

67%

Does it follow best practices?

Impact

93%

1.45x

Average score across 3 eval scenarios

SecuritybySnyk

Passed

No known issues

Optimize this skill with Tessl

npx tessl skill review --optimize ./scientific-skills/iso-13485-certification/SKILL.md
SKILL.md
Quality
Evals
Security

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 its scope, lists specific concrete actions, and provides comprehensive trigger guidance. It uses proper third-person voice, includes both a primary 'Use when' clause with enumerated scenarios and a secondary 'Also use when' clause for related terms. The highly specialized domain (ISO 13485 medical device QMS) makes it distinctly identifiable among other skills.

DimensionReasoningScore

Specificity

Lists multiple specific concrete actions: conducting gap analysis, creating Quality Manuals, developing procedures and work instructions, preparing Medical Device Files, understanding ISO 13485 requirements, and identifying missing documentation.

3 / 3

Completeness

Clearly answers both 'what' (comprehensive toolkit for preparing ISO 13485 certification documentation with six enumerated capabilities) and 'when' (explicit 'Use when' clause with detailed trigger scenarios, plus an 'Also use when' clause covering related regulatory terms).

3 / 3

Trigger Term Quality

Excellent coverage of natural terms users would say: 'ISO 13485', 'QMS documentation', 'gap analysis', 'Quality Manuals', 'Medical Device Files', 'medical device regulations', 'QMS certification', 'FDA QMSR', 'EU MDR', 'quality system documentation', and 'medical device certification'.

3 / 3

Distinctiveness Conflict Risk

Highly distinctive niche focused specifically on ISO 13485 medical device QMS documentation. The specific regulatory standards (ISO 13485, FDA QMSR, EU MDR) and domain-specific terminology make it very unlikely to conflict with other skills.

3 / 3

Total

12

/

12

Passed

Implementation

35%

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

This skill is comprehensive in coverage but severely undermined by verbosity—it reads more like a training manual than a concise skill file for Claude. Much of the content explains general knowledge (document writing best practices, what ISO clauses cover) rather than providing Claude-specific actionable instructions. The structure is logical but the content-to-signal ratio is low, with common scenarios largely restating the core workflow.

Suggestions

Reduce content by 60%+: Remove explanations of concepts Claude already knows (what an MDF is, general writing advice, what each ISO clause covers at a high level) and instead point to the reference files that already contain this information.

Consolidate the 5 common scenarios into the core workflow—they repeat the same steps with minor variations. A brief 'adapt approach based on user context' note would suffice.

Move the 31 procedures list, regulatory requirements, and document retention sections entirely to reference files (they appear to already exist in references/) and just link to them.

Add concrete output examples: show what a gap analysis report looks like, what a customized procedure section looks like after placeholder replacement, rather than describing the process abstractly.

DimensionReasoningScore

Conciseness

Extremely verbose at ~500+ lines. Extensively explains concepts Claude already knows (what an MDF is, what a Quality Manual is, general document writing best practices like 'clear, simple language' and 'avoid jargon'). The common scenarios section largely repeats the core workflow with minor variations. Much content could be condensed by 60-70% without losing actionable value.

1 / 3

Actionability

Provides some concrete guidance like the gap_analyzer.py command and references to specific template files, but most content is procedural description rather than executable instructions. The 'create documentation' sections are largely generic advice (replace placeholders, customize to organization) rather than specific, copy-paste-ready examples. No actual code examples beyond a single bash command.

2 / 3

Workflow Clarity

Multi-step workflows are clearly sequenced with numbered steps and phases, and there are some validation checklists (e.g., Quality Manual validation checklist, pre-audit checklist). However, validation steps are mostly presented as static checklists rather than explicit feedback loops with error recovery. The gap analysis workflow mentions running a script but doesn't address what to do if the script fails or produces unexpected results.

2 / 3

Progressive Disclosure

References to external files (references/, assets/templates/, scripts/) are well-signaled and appear to be one level deep. However, the SKILL.md itself is monolithic with enormous amounts of inline content that should be in separate files (e.g., the 31 procedures list, common scenarios, best practices, regulatory requirements, document retention). The Resources section at the end properly lists references, but the body duplicates much of what those references presumably contain.

2 / 3

Total

7

/

12

Passed

Validation

81%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation9 / 11 Passed

Validation for skill structure

CriteriaDescriptionResult

skill_md_line_count

SKILL.md is long (679 lines); consider splitting into references/ and linking

Warning

metadata_version

'metadata.version' is missing

Warning

Total

9

/

11

Passed

Repository
K-Dense-AI/claude-scientific-skills
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.