Works with the AI Agents you already use
Claude Code
Cursor
Codex CLI
Muse
Dots+21 moreClaude CodeCursorCodex CLIMuseDots
Manus
Grok
Grok Bot+18 agentsEU AI Act Compliance Docs Writer Skill
Drafts evidence-linked EU AI Act compliance documentation and obligation maps for AI systems.
$38.99
EU AI Act Compliance Docs Writer Skill
Example session with this skill installed
I need a compliance draft for a CV screening tool used by HR in Germany. It uses a custom LLM to rank candidates based on job descriptions. We are the provider.
- Read your context and instructions
- Compiled the eu ai act
I have analyzed the system profile for your CV screening tool. Based on its intended purpose in employment and recruitment, this system likely falls under the High-Risk category (Annex III) of the EU AI Act.
AI Act Compliance Draft: CV Screening System
| Section | Detail / Status | Source / Article Reference |
|---|---|---|
| System Purpose | Automated ranking of job candidates via LLM analysis of CVs and job descriptions. | Annex III, Point 4(a) |
| Provider Role | Internal development and deployment under own brand (Provider). | Article 3(3) |
| Risk Class | High-Risk (Employment, workers management). | Annex III, 4(a) |
| Applicability Date | Annex III obligations scheduled for 2 December 2027. | Official EU AI Act Timetable |
| Human Oversight | [PENDING] Define specific roles for HR staff to override rankings. | Article 14 |
| Transparency | Notice required for candidates regarding automated processing. | Article 50 / GDPR Art. 13 |
Draft Transparency Notice (High-Risk)
Notice to Candidates: This application process utilizes an AI system to assist in evaluating candidate qualifications. The system ranks profiles based on [Insert Specific Criteria]. Final hiring decisions are made by human recruiters who review the system's output. You have the right to [Link to Procedure] to request human intervention or contest the ranking.
Evidence & Risk Register
- Risk 1: Algorithmic bias in ranking criteria. Control: Bi-annual bias audits and diverse training sets.
- Risk 2: Lack of human oversight. Control: Compulsory recruiter sign-off on all top-ranked candidates.
Documentation Status: Technical documentation outline generated; Data governance notes pending data source confirmation.
Next steps
- Confirm if the system is already placed on the market or in use to determine transition rule eligibility.
- Complete the human oversight procedure by defining the "stop button" or override protocols for HR managers.
- Review the unresolved questions list with your legal department to validate the Annex III classification.
Connects securely to your tools. The creator never sees your data.
About this skill
Navigating the EU AI Act's phased implementation is a moving target for engineering teams. This skill drafts evidence-linked compliance documentation by mapping your system's architecture and purpose directly to official legislative requirements. It eliminates the guesswork of identifying relevant articles and applicability dates, providing a structured foundation for legal review.
What it does
- System profiling generates a detailed map of intended purpose, user roles, and deployment contexts.
- Obligation mapping identifies specific AI Act provisions based on your system's risk classification.
- Draft generation produces transparency notices, risk registers, and human-oversight procedures.
- Source tracing links every material claim to official EU sources, URLs, and specific provisions.
- Evidence tracking categorizes facts as supplied, pending, or not applicable to maintain a clear audit trail.
How it works
- Intake facts regarding the system's purpose, deployment context, and provider roles.
- Contextual analysis to distinguish between confirmed facts and assumptions requiring legal review.
- Drafting phase creates jurisdiction-specific documents and technical outlines.
- Validation checks for inconsistent dates, placeholder completion, and source link accuracy.
Frameworks & tools
This skill utilizes official European Union legislative databases, Commission guidance, and the specific Annexes of the EU AI Act. It is designed for developers, product managers, and compliance officers working within regulated AI environments.
Why this beats prompting it yourself
Generic prompts often hallucinate legal dates or fail to distinguish between voluntary codes of practice and mandatory requirements. This skill enforces a rigorous mapping process that requires evidence for every claim and adheres to the complex, phased implementation timeline of the Act.
Use cases
- Draft transparency notices for general-purpose AI systems.
- Create technical documentation outlines for high-risk AI systems.
- Build a risk register mapped to specific Article 50 or Annex III obligations.
- Generate review checklists for legal counsel to accelerate conformity assessments.
Known limitations
Does not provide legal advice or official certification. Users must verify the official timetable for specific transition rules as timelines may shift via new Commission guidance.
Output is a draft for review only. Does not replace legal counsel or conformity assessments. User must provide factual system inputs to avoid unknowns.
How to use
- 1
Connect your agent to the Agensi MCP
Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup
- 2
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 3
Ask for what you need
Your agent loads this skill and uses it on your task. It always asks before any payment.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill goes through the trust checks below.
Security scanned
Checked by our 8-point scan before listing
Fresh listing
Recently published to Agensi
Money-back guarantee
Doesn't do what its page promises? You get your money back.
Trust & safety
Security scan
Security scan passed 24 days ago