Name: eu-ai-act-specialist
Rating: 68 (1 reviews)
Author: alirezarezvani

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

83%

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

The canonical home for this skill is eu-ai-act-specialist in alirezarezvani/claude-skills

Quality

Content

67%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, domain-rich compliance skill with concrete commands, clear workflows, and good reference signaling. Main weaknesses are a padded keyword dump with some cross-section redundancy, and reference/script paths that point to files not included in the bundle.

Suggestions

Remove or condense the flat Keywords list (line 31) — it is padding that neither Claude nor the user needs; the natural trigger terms already live in the description.

Include the referenced bundle files (references/eu_ai_act_titles.md, references/high_risk_systems_annex_iii.md, references/gpai_obligations.md, references/cross_framework_mapping_ai_act.md, and the scripts/*.py tools) so the signaled navigation actually resolves.

Make the validation feedback loops explicit in the documentation workflows (e.g., a concrete 'if classifier returns high-risk, then run planner; verify Annex IV items 1–8 before signing the Article 47 declaration') rather than relying on implicit sequencing.

Dimension	Reasoning	Score
Conciseness	Mostly efficient domain content (tier tables, Article matrices earn their place), but the flat comma-separated Keywords dump and repeated restating of the three decisions across the intro, Core Responsibilities, and Workflows could be tightened.	3 / 5
Actionability	Provides concrete copy-paste commands ('python scripts/ai_system_risk_classifier.py path/to/systems.json') and a structured Output Standards template, but several workflow steps are comment-style placeholders rather than fully executable instructions.	4 / 5
Workflow Clarity	Four workflows are clearly sequenced with numbered steps and some checkpoints ('Sign EU declaration AFTER assessment passes', 're-run classifier if system changed'), though validation feedback loops are implicit rather than explicit validate-fix-retry cycles.	4 / 5
Progressive Disclosure	Good in-file structure with a dedicated References section giving one-line descriptions of one-level-deep reference files, but the referenced bundle files (references/.md, scripts/.py) are not present in the bundle, so navigation is incomplete.	4 / 5
	Total	15 / 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 high-quality description that concretely enumerates three distinct decisions, names the governing Articles/Annexes, gives explicit use-when triggers, and draws clear boundaries against adjacent skills. Third-person voice is maintained throughout.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions across three explicit decisions — risk-tier classification into four tiers, Article 43 Module A vs Module H conformity route selection, Annex IV documentation scoping, and per-role obligation matrices — giving comprehensive coverage.	5 / 5
Completeness	Explicitly answers both 'what' (three Article-level decisions enumerated) 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	Comprehensive natural-term coverage including synonyms and the regulation identifier: 'EU AI Act', 'Regulation (EU) 2024/1689', 'high-risk', 'conformity assessment', 'deployer obligations', plus concrete trigger contexts ('AI system intake review', 'planning conformity assessment').	5 / 5
Distinctiveness Conflict Risk	Clear niche with explicit boundary statements — 'NOT executive AI strategy (see chief-ai-officer-advisor)', 'NOT a legal substitute', 'NOT GDPR' — minimizing conflict risk with adjacent skills.	5 / 5
	Total	20 / 20 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
relative_links	Relative link issues: 4 missing	Warning
referenced_paths_exist	Referenced path issues: 17 missing	Warning

	Total	14 / 16 Passed

Repository: alirezarezvani/claude-skills
Path: .gemini/skills/skills-eu-ai-act-specialist/SKILL.md
Commit: 19392f7

Reviewed: ~4 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.