CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

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.

70

Quality

88%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

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

SKILL.md
Quality
Evals
Security

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 operational skill: substantive domain tables, executable script commands, and clean one-level-deep reference navigation. The main improvements are token-level — trimming the Keywords section and NOT-paragraphs — plus showing the expected JSON input shape for the three scripts.

Suggestions

Move or compress the ~40-term Keywords section (or fold the few terms not already in the description into it) — the description already carries the trigger coverage.

Add a short example of the systems.json / roles.json input shape (or point to an embedded sample's structure) so the three scripts can be invoked without guessing the format.

Consolidate the three separate "This skill is NOT..." paragraphs into one boundary block to cut redundant tokens.

DimensionReasoningScore

Conciseness

The body is dense with regulation-specific facts (tier table, Article 6(3) carve-outs, Annex IV list, role matrix) that Claude cannot be assumed to know, but the ~40-term Keywords section duplicates trigger coverage already in the description and the three NOT-paragraphs partially repeat it, adding avoidable tokens.

4 / 5

Actionability

Concrete executable commands for all three decisions ("python scripts/ai_system_risk_classifier.py path/to/systems.json") and a structured output template, but no sample input/output or the expected shape of systems.json / roles.json / system.json for the scripts.

4 / 5

Workflow Clarity

Four clearly sequenced workflows with a conditional branch ("If high-risk: run planner") and Workflow 3 built entirely of confirmation checkpoints, though no explicit error-recovery loops; sequence and checkpoints are otherwise solid.

4 / 5

Progressive Disclosure

The SKILL.md is a genuine overview: each core section points to a real one-level-deep reference file (all four referenced files exist), the scripts referenced in Quick Start exist, and a References section with per-file descriptions makes navigation easy.

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.

An exemplary description: it defines three concrete, Article-cited decisions, gives explicit use-when triggers, and fences its boundaries against adjacent skills. Only gap is that a few high-frequency user phrasings (penalties, CE marking, GPAI) live in the body keywords rather than the description itself.

DimensionReasoningScore

Specificity

The description enumerates three concrete Article-level decisions — risk-tier classification (prohibited/high-risk/limited/minimal with Article cites), the Article 43 Module A vs Module H conformity route plus Annex IV documentation, and per-role obligation scoping with deadlines — comprehensively covering the skill's stated scope.

5 / 5

Completeness

It explicitly answers both what ("Three Article-level decisions: (1)... (2)... (3)...") and when ("Use during AI system intake review, when planning conformity assessment, or when scoping deployer obligations").

5 / 5

Trigger Term Quality

Strong natural terms with synonyms ("EU AI Act (Regulation (EU) 2024/1689)", "risk tier", "high-risk", "conformity assessment", "deployer obligations"), but common user phrasings the body itself lists as keywords — "AI Act penalties", "CE marking", "GPAI" — are absent from the description itself.

4 / 5

Distinctiveness Conflict Risk

A clearly staked niche (EU AI Act operational compliance, Regulation 2024/1689) with explicit boundary disclaimers ("NOT executive AI strategy (see chief-ai-officer-advisor). NOT a legal substitute.") minimizing wrong-skill triggering.

5 / 5

Total

19

/

20

Passed

Validation

100%

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/skills/eu-ai-act-specialist/SKILL.md

Reviewed

Table of Contents

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.