iso-standards-readiness

Prepares and structurally reviews readiness evidence for ISO management-system and laboratory-competence standards - ISO 13485 medical device QMS, ISO 14971 device risk management, ISO/IEC 17025 testing and calibration laboratories, and ISO 15189 medical laboratories. Use when organizing declared scope, controlled documents, risk-management files, scope of accreditation, traceability, CAPA, external-provider controls, or bounded local evidence manifests, and when separating ISO certification from laboratory accreditation, FDA QMSR inspection, CLIA certification, MDSAP, and EU MDR/IVDR evidence boundaries. Not for legal applicability, compliance, certification, or accreditation decisions; contains no clause text.

Quality

96%

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

92%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-architected router skill: an 8-step workflow with concrete executable CLI checks, explicit fail-closed validation and feedback loops, and one-level-deep references that all resolve to real bundle files. The only weakness is mild repetition of the boundary/cannot-do statements across several sections.

Suggestions

Consolidate the 'cannot certify/accredit' boundary into one canonical statement; the current repetition across the Non-negotiable boundary list, exit-code notes, and Step 8 titling could be trimmed for token efficiency.

Add a brief error-recovery note for CLI exit code 1 (e.g., what to do when structural/evidence gaps are found) to make the feedback loop explicit rather than implied by 'preserve as blockers'.

The 'Current baseline' time-sensitive edition/version block is dense; a short pointer that this section is the dated baseline (already partially present via 'Read references/source-ledger.md') could let some detail migrate to source-ledger.md.

Dimension	Reasoning	Score
Conciseness	The body is substantive and almost entirely non-obvious domain knowledge (lane discipline, edition baselines, copyright, fail-closed CLI safety) rather than concepts Claude already knows, but the non-negotiable boundary is restated across the description, the 'cannot' list, exit-code notes, and Step 8 titling, which is trimmable repetition; this fits 'efficient with minor instances of over-explanation' better than the mostly-efficient score-3 anchor.	4 / 5
Actionability	Eight copy-paste-ready bash invocations with real script paths, template arguments, and flags (e.g. 'python3 scripts/validate_evidence_manifest.py /path/to/evidence-manifest.json --standard iso-17025 --base-dir ... --verify-files --output ...') cover each common case, matching the fully-executable score-5 anchor; placeholders are appropriate user-supplied inputs.	5 / 5
Workflow Clarity	An explicit Step 1-Step 8 sequence with validation checkpoints (fail-closed templates, HUMAN_DECISION_REQUIRED blockers, exit codes 0/1/2, --verify-files), feedback loops that preserve unresolved decisions as blockers rather than auto-resolving, and a referenced fail-closed checklist (gap-analysis-checklist.md); the destructive/batch cap does not apply because validation is present.	5 / 5
Progressive Disclosure	Explicitly declared router ('Per-standard depth lives in references/') with a References section that signals each one-level-deep file and its contents; all referenced references/, scripts/, and assets/templates/ paths were verified to exist as real bundle files, so navigation is clear and appropriately split per the score-5 anchor.	5 / 5
	Total	19 / 20 Passed

Description

100%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 dense, information-rich description that names four specific standards, lists concrete preparation/review actions, gives an explicit 'Use when' trigger clause, and adds a negative boundary. It avoids fluff despite its length because every clause adds scope or trigger specificity.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions ('Prepares and structurally reviews readiness evidence', 'organizing declared scope, controlled documents, risk-management files, ... traceability, CAPA, external-provider controls, or bounded local evidence manifests', 'separating ISO certification from laboratory accreditation') across four named standards, giving comprehensive coverage rather than the 1-2 actions of a score-3 anchor.	5 / 5
Completeness	Explicitly answers both 'what' (prepares/reviews readiness evidence for the listed ISO/IEC standards) and 'when' via a concrete 'Use when organizing ... or bounded local evidence manifests, and when separating ... evidence boundaries' trigger clause, plus a negative-scope boundary; this is the score-5 anchor.	5 / 5
Trigger Term Quality	Comprehensive natural-term coverage including the standard identifiers users actually cite (ISO 13485, ISO 14971, ISO/IEC 17025, ISO 15189) plus framework synonyms (FDA QMSR, CLIA, MDSAP, EU MDR/IVDR) and domain vocabulary (scope of accreditation, traceability, CAPA), matching the comprehensive anchor.	5 / 5
Distinctiveness Conflict Risk	Carves a clear niche (evidence-preparation for authorized human review, not decisions) with explicit lane-separation triggers and named standards, so it is unlikely to fire for a generic compliance or audit skill; minimal conflict risk per the score-5 anchor.	5 / 5
	Total	20 / 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
referenced_paths_exist	Referenced path issues: 21 deeper-than-1-level	Warning

	Total	15 / 16 Passed

Repository: K-Dense-AI/scientific-agent-skills
Path: skills/iso-standards-readiness/SKILL.md
Commit: 1e5eeff

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.