AI Blocks › Keep your code secure
EU AI Act risk classifier
Describe your AI system. Get its risk tier under the EU AI Act and the duties that follow.
EU AI Act risk classifier is a free AI skill for the job "Keep your code secure". Give the instructions to an AI assistant that supports the required files and tools, then review its output.
Free · No account · MIT licence · Made by Alireza Rezvani · Level: advanced · Thinking: high
Made by Alireza Rezvani. See the original on GitHub; we copied it as it is, with its licence.
What it does
The risk tier of your AI system under the EU AI Act, with the duties that come with it. You learn whether it is banned, high-risk, needs a transparency notice, or is minimal. You describe the system, its purpose and who uses it. The skill checks it against the banned practices first, then the high-risk areas such as hiring, credit and education. For high-risk systems it plans the conformity route and the technical documents. It then lists duties by your role: provider, user, importer or distributor. Three Python scripts back each step. It is not legal advice, and unclear cases should go to a lawyer.
You give it
- Description of the AI system and its purpose
- Who it affects and where
- Your role in the supply chain
- Python to run the included scripts (optional)
You get
- Risk tier with the reason
- Conformity route for high-risk systems
- Documentation checklist
- Duties by role
Use it when
- You are about to launch an AI feature and need to know its risk tier.
- You are not sure if your system counts as high-risk.
- You need to know which duties fall on you as provider versus user.
- You must plan the paperwork for a high-risk system.
How to use it
- Add it to your AI once: download it and add the folder to Claude, ChatGPT or Codex as a skill.
- Ask for the job in your own words. Your AI opens the skill when it fits.