iso13485-audit-prep

/cs:iso13485-audit-prep <scope> — ISO 13485 QMS audit 6-question forcing interrogation. Design controls + CAPA + post-market focused. Use before Clause 8.2.4 internal audit, MDR / FDA QSR alignment review, or product-launch DHF closure audit.

Quality

76%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

—

The risk profile of this skill

Fix and improve this skill with Tessl

tessl review fix ./compliance-os/skills/iso13485-audit-prep/SKILL.md

Quality

Content

68%Weight 40%Scale 1-5

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

A well-organized, lean audit-prep skill with concrete interrogation prompts and a copy-paste-ready output template. The main weaknesses are an under-specified Workflow section with no explicit validation checkpoints and workflow commands that reference non-bundled external scripts.

Suggestions

Tighten the Workflow section: replace the vague 'Route to ... tools' comments (steps 3-4) with concrete, executable steps or explicit routing commands, and add a validation checkpoint before the verdict is rendered (e.g., 'confirm every sampled DHF/CAPA has evidence before assigning READY/CLOSE/NOT-READY').

Make the Workflow commands verifiable by either bundling the referenced scripts (audit_schedule_optimizer.py, audit_simulator.py) under ./scripts/ or clarifying that they are external prerequisites with a fallback inline procedure when unavailable.

Trim the intro paragraph that restates the frontmatter description and de-duplicate the per-question checks against the Output Format template to reduce token redundancy.

Dimension	Reasoning	Score
Conciseness	Terse bullets that assume Claude's knowledge of ISO 13485/CAPA clauses without explaining them, but the intro restates the description and there is structural redundancy between the six questions and the Output Format, matching anchor 4 rather than 5 (every token earning its place).	4 / 5
Actionability	Concrete interrogation prompts with specific sub-checks ('DHF must include: design plan + inputs + outputs + verification + validation + transfer + changes', 'Root cause analysis depth: 5 Why minimum') plus a copy-paste-ready Output Format, but the Workflow bash commands reference scripts outside this skill's bundle that are not present, matching anchor 4 rather than 5.	4 / 5
Workflow Clarity	A coherent macro-flow (six questions -> output template -> verdict -> Top 3 Actions) exists, but the Workflow section's steps 3-4 are vague ('# Route to ... tools') and there are no explicit validation checkpoints before rendering the verdict, matching anchor 3 (steps listed but checkpoints missing or implicit).	3 / 5
Progressive Disclosure	Well-organized sections with clearly-signaled one-level references ('Reference iso13485_audit_playbook.md for the per-DHF checklist'), but no bundle files exist in this skill's own references/scripts/assets dirs and the referenced playbooks live in another team's directory, so the skill is effectively a single monolithic file, matching anchor 4 rather than 5.	4 / 5
	Total	15 / 20 Passed

Description

83%Weight 40%Scale 1-5

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 that clearly states both what the skill does and when to use it with concrete domain trigger phrases. The only meaningful weakness is minor overlap risk with the closely-related FDA QSR audit skill via the MDR/FDA alignment trigger.

Dimension	Reasoning	Score
Specificity	Names the ISO 13485 QMS domain and several concrete actions/focus areas ('6-question forcing interrogation', 'Design controls + CAPA + post-market focused'), matching anchor 4 rather than 3 (only 1-2 actions) and not 5 (not fully comprehensive across all audit areas).	4 / 5
Completeness	Explicitly answers both what ('ISO 13485 QMS audit 6-question forcing interrogation. Design controls + CAPA + post-market focused') and when ('Use before Clause 8.2.4 internal audit, MDR / FDA QSR alignment review, or product-launch DHF closure audit') with concrete trigger phrases, matching anchor 5.	5 / 5
Trigger Term Quality	Strong natural domain keywords ('ISO 13485', 'QMS audit', 'internal audit', 'MDR / FDA QSR', 'DHF closure audit', 'Clause 8.2.4') with synonyms (audit/review), matching anchor 4 (good coverage, a few terms missing) rather than 5 (which expects exhaustive coverage incl. file extensions, N/A here).	4 / 5
Distinctiveness Conflict Risk	Clear ISO 13485 niche with distinct triggers (Clause 8.2.4, DHF closure), but the 'MDR / FDA QSR alignment review' trigger creates minor overlap with the sibling fda-qsr-audit-prep skill, matching anchor 4 rather than 5.	4 / 5
	Total	17 / 20 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
relative_links	Relative link issues: 3 suspicious	Warning

	Total	15 / 16 Passed

Repository: alirezarezvani/claude-skills
Path: compliance-os/skills/iso13485-audit-prep/SKILL.md
Commit: 19392f7

Reviewed: ~10 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.