iso-13485-certification

Prepare and structurally review ISO 13485 QMS scope, controlled documentation, and local evidence manifests. Use for ISO 13485 certification-readiness documentation or for separating related FDA QMSR, MDSAP, and EU MDR/IVDR evidence boundaries; not for legal applicability, compliance, or certification decisions.

Quality

92%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

84%

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

Highly actionable, well-structured content with executable commands and explicit validation checkpoints across an eight-step workflow. Progressive disclosure is clean — all references are one level deep and resolve to real bundle files; the only minor weakness is some verbosity in boundary and prose sections.

Suggestions

Tighten the 'Non-negotiable boundary' and per-step prose to remove repetition that assumes less competence than needed, improving token efficiency.

Consider moving the long enumerations (e.g. Step 4 review list) into a reference file referenced from SKILL.md to keep the body leaner while preserving detail.

Dimension	Reasoning	Score
Conciseness	Mostly efficient and free of obvious concept padding, but the boundary/copyright sections and the per-step prose add length that assumes less competence than needed; some enumerations could be tightened without losing clarity.	2 / 3
Actionability	Provides complete, executable CLI invocations with real flags and relative paths (e.g. 'python3 scripts/validate_scope_intake.py assets/templates/scope-intake-template.json'), and concrete field lists for each check — copy-paste ready.	3 / 3
Workflow Clarity	An eight-step sequence with explicit validation checkpoints (fail-closed templates, exit-code semantics, blocked-closure rules) and clear feedback guidance for error recovery in batch/evidence operations.	3 / 3
Progressive Disclosure	SKILL.md is a well-organized overview with one-level-deep references to verified files (references/.md, assets/templates/, scripts/*.py), each clearly signaled and listed in dedicated Templates/References sections; all referenced paths resolve to real bundle files.	3 / 3
	Total	11 / 12 Passed

Description

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.

A strong, specific description with concrete actions, natural trigger terms, and explicit what/when guidance plus a clear out-of-scope clause. It is distinguishable from neighboring skills and uses correct third-person voice.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'Prepare and structurally review ISO 13485 QMS scope, controlled documentation, and local evidence manifests' — naming specific artifact types rather than vague verbs.	3 / 3
Completeness	Explicitly answers what ('Prepare and structurally review...scope, controlled documentation, and local evidence manifests') and when ('Use for ISO 13485 certification-readiness documentation or for separating related FDA QMSR, MDSAP, and EU MDR/IVDR evidence boundaries'), with a clear negative-scope trigger.	3 / 3
Trigger Term Quality	Covers natural terms a user would say — 'ISO 13485', 'certification-readiness documentation', 'FDA QMSR', 'MDSAP', 'EU MDR/IVDR' — with good coverage of common phrasings.	3 / 3
Distinctiveness Conflict Risk	Narrow niche — ISO 13485 certification-readiness documentation with explicit 'not for legal applicability, compliance, or certification decisions' boundaries — unlikely to trigger for unrelated skills.	3 / 3
	Total	12 / 12 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
allowed_tools_field	'allowed-tools' contains unusual tool name(s)	Warning
referenced_paths_exist	Referenced path issues: 16 deeper-than-1-level	Warning

	Total	14 / 16 Passed

Repository: K-Dense-AI/scientific-agent-skills
Path: skills/iso-13485-certification/SKILL.md
Commit: 757b63b

Reviewed: about 11 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.