AI-agent skill · Claude Code · Codex · Cursor · Gemini CLI
EU AI Act Readiness Kit lets your AI coding agent check an AI product against the EU AI Act. It scans the code for AI use, works out the risk category with the articles behind it, lists every obligation that applies with its date and the days left, and drafts the paperwork: the Annex IV technical documentation, the Article 6(3) record, transparency notices and an AI literacy plan. Built on the law as amended by the 2026 Digital Omnibus (Regulation (EU) 2026/1744).
In May 2026 the Commission published draft guidelines with hundreds of practical examples of AI systems that should or should not count as high-risk. I collected 312 of them from the official AI Act Service Desk and split them by area. I built the skill on four areas only. Then I froze it and gave the other 166 examples (education, essential services and credit, migration, justice and elections, and cross-cutting cases) to a fresh AI agent that had never seen them or their answers. It followed the skill once.
| Case | Point | Example (Commission, paraphrased) | Commission | Skill |
|---|---|---|---|---|
| edu28 | 3(d) | Plagiarism checker compares submitted homework against existing content. | not high-risk | high-risk |
| edu30 | 3(d) | AI helps a human proctor confirm or deny already suspected cheating by analysing the flagged student's data; the proctor decides. | not high-risk | high-risk |
| ess27 | 5(b) | Margin credit assessment for leveraged trading. | not high-risk | high-risk |
| ess45 | 5(d) | Manages network traffic for emergency calls. | not high-risk | high-risk |
| hor01 | 5(b) | Credit score for a sole trader's business using only business data. | not high-risk | high-risk |
| Blind test area | Correct |
|---|---|
| education | 29/31 |
| essential-services | 47/49 |
| horizontal | 12/13 |
| justice-democracy | 27/27 |
| migration | 46/46 |
| Development area | Correct |
|---|---|
| biometrics | 40/41 |
| critical-infrastructure | 25/25 |
| employment | 32/32 |
| law-enforcement | 47/48 |
Honest notes: the examples are short paraphrases of the Commission's draft guidelines, which are not final and not binding. In 16 of the 97 correct "not high-risk" answers, the skill gave a different reason than the Commission ("outside the use case" versus "Article 6(3) exemption"). That matters because the exemption must be documented and registered. This test covers the high-risk decision only; prohibited practices, transparency duties, GPAI rules and dates are covered by 44 automated tests.
A separate fresh agent installed the frozen skill and ran it end to end on six real GitHub projects, with nobody to answer its questions. I wrote down my expected answer for each project before it ran.
| Project | What it is | Expected | Skill's result | Match |
|---|---|---|---|---|
| sliday/resume-job-matcher | An employer screens and ranks resumes to decide who to interview | High-risk, Annex III 4(a) | High-risk, 4(a) (profiling, no exemption) + transparency | ✅ match |
| max-fitzpatrick/Credit-scoring-model | Predicts a consumer's probability of default | High-risk, Annex III 5(b) | High-risk, 5(b) | ✅ match |
| srbhr/Resume-Matcher | A job seeker tailors their own resume with an LLM | Not high-risk (candidate's own tool); transparency | Transparency (Art 50(2)), not high-risk | ✅ match |
| mckaywrigley/chatbot-ui | Chat interface for LLMs | Transparency (Art 50(1), 50(2)) | Transparency (Art 50(1), 50(2)) | ✅ match |
| kmhmubin/Face-Recognition-Attendance-System | Webcam face recognition marks students' attendance | Borderline: must weigh 'remote' identification (1(a)) vs people stepping up to the camera | High-risk 1(a) on the stricter reading, with the 'remote' question and the way to narrow it explained | ✅ match (borderline, reasoned) |
| lllyasviel/Fooocus | Image generator (SDXL) with face swap and inpainting | Transparency (Art 50(2)); mention the 2 Dec 2026 bans | v1.0.0 said 'PROHIBITED'. The law (Art 5(1a)) bans such generators only without adequate safeguards, which the agent found are off by default. v1.0.1 now says: prohibited from 2 Dec 2026 unless safeguards are added, plus Art 50 duties | ⚠️ partial: right issue, too strong a verdict; fixed in v1.0.1 |
Every command worked the first time on all six projects; the scan took 0.1 to 3.9 seconds. 5 of 6 matched the expected answer and 1 was partly right. The buyer agent also found real problems, all fixed in v1.0.1: 'unsure' answers were not always treated strictly, the borderline note was not printed, re-running overwrote an edited documentation draft, the pre-fill counted weak evidence, and some scanner signals were noise. The Annex IV drafts started with 3 to 10 of 26 items pre-filled from the code; after the agent completed them, 12 to 21 of 26 had content and the rest needs the team.
2 Feb 2025 Prohibited practices banned; AI literacy duty.
2 Aug 2025 General-purpose AI model rules.
2 Aug 2026 Transparency duties: tell people they talk to AI, mark AI-generated content, label deepfakes.
2 Dec 2026 New bans on AI that makes non-consensual intimate imagery or child sexual abuse material; generators already on the market must mark outputs.
2 Dec 2027 High-risk rules for Annex III use cases (hiring, education, credit, insurance, biometrics...).
2 Aug 2028 High-risk rules for AI in regulated products (medical devices, toys, lifts...).
European start-ups and agencies that build AI products and want to know where they stand before customers, investors or authorities ask.
One Python script, standard library only (Python 3.10+). Nothing leaves your machine.
When a deciding fact is unknown, it asks and assumes the stricter reading. In the blind test every error was a false alarm, never a miss.
It does not cover GDPR, copyright, product liability or sector law, and it cannot replace a lawyer. The law version is printed on every report.
Made by Muhammad Shahmeer · Data Science MSc, University of Naples Federico II · © 2026, all rights reserved. Not legal advice. Not affiliated with the European Commission. Examples paraphrased from the Commission's draft guidelines (AI Act Service Desk).