Name: eu-ai-act-specialist
Rating: 60 (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

71%

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

Fix and improve this skill with Tessl

tessl review fix ./.gemini/skills/eu-ai-act-specialist/SKILL.md

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

Quality

Content

50%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.

The body is well-organized and operationally rich with concrete Article citations, tables, and workflows, but it is undermined by missing bundle artifacts: the three referenced scripts and four referenced reference files do not exist, breaking executable guidance and progressive disclosure. Tightening the keyword filler and adding explicit validation loops would further improve it.

Suggestions

Ship the referenced bundle files: create scripts/ai_system_risk_classifier.py, scripts/conformity_assessment_planner.py, and scripts/ai_act_obligation_tracker.py plus the four references/*.md files, or remove the dangling references.

Add explicit validate→fix→retry checkpoints to Workflows 1 and 2 (e.g., re-run the classifier and confirm the tier before planning conformity), since batch classification is a consequential operation.

Trim the large Keywords list and avoid restating the three decisions and 'NOT...' disambiguations that already appear in the frontmatter description to improve token efficiency.

Dimension	Reasoning	Score
Conciseness	Mostly operational and efficient (tables, article citations, workflows), but the long comma-separated Keywords block and re-stated three-decisions / three-'NOT' disambiguations already present in the description are padding that could be tightened.	3 / 5
Actionability	Commands and checklists are concrete in form, but the three referenced scripts (ai_system_risk_classifier.py, conformity_assessment_planner.py, ai_act_obligation_tracker.py) do not exist in the bundle, so the core executable guidance is broken rather than merely gapped.	3 / 5
Workflow Clarity	Four workflows have clear goals and numbered steps with a confirmation checklist (Workflow 3) and a gating condition (Workflow 2), but Workflows 1–2 lack explicit validate→fix→retry loops and batch classification triggers the validation cap.	3 / 5
Progressive Disclosure	Structure and signaling are good (overview with a one-level-deep References section describing four files), but none of the seven referenced scripts/reference files exist in the bundle, so the disclosure points to dead ends.	3 / 5
	Total	12 / 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, specific description that explicitly covers what (three Article-cited decisions) and when (concrete intake/planning/scoping triggers) while actively disambiguating from adjacent skills. Voice is appropriately third-person/imperative; only minor trigger-synonym gaps keep it from a clean sweep.

Dimension	Reasoning	Score
Specificity	Lists three concrete, distinct decisions (risk-tier classification, Article 43 conformity route + Annex IV docs, per-role obligation scoping) with Article citations — comprehensive coverage of concrete actions, matching the top anchor.	5 / 5
Completeness	Explicitly answers both what (three numbered decisions) 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 domain triggers ('conformity assessment', 'high-risk', 'deployer obligations', 'AI system intake review') natural for the compliance audience, but Article-number-heavy and missing common synonyms like 'CE marking' or 'AI regulation Europe'.	4 / 5
Distinctiveness Conflict Risk	Clear niche (EU AI Act operational compliance) with explicit disambiguation — 'NOT executive AI strategy (see chief-ai-officer-advisor). NOT a legal substitute' — yielding minimal conflict risk.	5 / 5
	Total	19 / 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/eu-ai-act-specialist/SKILL.md
Commit: 19392f7

Reviewed: ~3 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.