eu-ai-act-specialist

EU AI Act (Regulation (EU) 2024/1689) operational compliance for compliance teams. Three Article-level decisions: (1) What's the risk tier of this AI system — prohibited (Art. 5), high-risk (Art. 6 + Annex III), limited-risk (Art. 50), or minimal-risk? (2) For high-risk systems, what's the Article 43 conformity assessment route (Module A internal control vs Module H full QMS + notified body) and what goes in the Annex IV technical documentation? (3) Per organizational role (provider / deployer / importer / distributor / authorized representative), what are the active obligations and deadlines? Use during AI system intake review, when planning conformity assessment, or when scoping deployer obligations. Cites Articles + Annexes for every output. NOT executive AI strategy (see chief-ai-officer-advisor). NOT a legal substitute.

Quality

85%

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

Quality

Content

78%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-structured, actionable compliance skill with real executable scripts and appropriately split references. Main improvements are trimming the Keywords list and restated intro, and adding explicit validation checkpoints inside the multi-step workflows.

Suggestions

Trim the long Keywords list and the restated three-decisions/NOT paragraphs near the top of the body, since they duplicate the frontmatter description and consume token budget.

Add explicit validation checkpoints in Workflows 1–3 (e.g. 'verify classifier output tier before running the planner; re-run if system characteristics changed') to create clear validate→fix→retry loops.

Convert comment-only workflow steps (such as 'Cross-check with GDPR DPIA' and 'Reference ISO 42001 evidence') into concrete, executable actions or explicit decision points.

Dimension	Reasoning	Score
Conciseness	Mostly efficient and information-dense (Article/Annex mappings, role tables, real script invocations) without explaining basics Claude already knows, but the ~40-term Keywords list and the restated three-decisions/NOT-paragraphs near the top could be trimmed for token budget.	4 / 5
Actionability	Provides copy-paste-ready script commands in Quick Start and concrete Article-cited tables and an Output Standards template, but several workflow steps are comment-only hints (e.g. "Cross-check with GDPR DPIA") rather than executable instructions, leaving minor gaps.	4 / 5
Workflow Clarity	Four workflows are clearly numbered and sequenced with real commands and some implicit checkpoints ("If high-risk: run planner"; "Sign EU declaration of conformity AFTER assessment passes"), but lacks explicit validate→fix→retry feedback loops for the more involved processes.	4 / 5
Progressive Disclosure	Clear overview body with a dedicated References section linking four real, one-level-deep reference files (each with a description) plus scripts in scripts/, with the deep Article/Annex/GPAI detail appropriately split out of SKILL.md.	5 / 5
	Total	17 / 20 Passed

Description

92%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, highly specific description that clearly states what the skill does, when to use it, and how it differs from neighboring skills. Minor room to add a few plainer trigger phrasings alongside the technical compliance vocabulary.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete Article-level actions with comprehensive coverage: classifying into four named risk tiers (prohibited/high-risk/limited/minimal), selecting an Article 43 conformity route (Module A vs Module H) with Annex IV documentation, and resolving obligations per five named organizational roles.	5 / 5
Completeness	Explicitly answers both what (the three Article-level decisions, each detailed) and when ("Use during AI system intake review, when planning conformity assessment, or when scoping deployer obligations") with concrete trigger phrases.	5 / 5
Trigger Term Quality	Strong keyword coverage with synonyms ("EU AI Act" / "Regulation (EU) 2024/1689") and an explicit "Use during AI system intake review, when planning conformity assessment, or when scoping deployer obligations" clause, but the term set leans technical/jargon-heavy and omits a few plainer natural phrasings a user might say.	4 / 5
Distinctiveness Conflict Risk	Occupies a clear niche (operational EU AI Act compliance) and explicitly disambiguates from adjacent skills via "NOT executive AI strategy (see chief-ai-officer-advisor)" and "NOT a legal substitute," minimizing wrong-skill triggering.	5 / 5
	Total	19 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: alirezarezvani/claude-skills
Path: ra-qm-team/compliance-team-eu-ai-act/skills/eu-ai-act-specialist/SKILL.md
Commit: 19392f7

Reviewed: ~2 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.