EU AI Act Compliance Docs Writer — Model Cards, AI Disclosures, and Risk-Tier Worksheets, Counsel-Ready
Draft the AI documentation the EU AI Act expects — model cards, AI-use disclosures, transparency notices, risk-tier worksheets, and technical-doc skeletons. Counsel-ready drafts from a regulated-industry documentation professional, with templates included.
- Classify AI systems into regulated risk tiers with documented reasoning.
- Generate user-facing disclosures for AI-generated content or interactions.
- Create structured technical files for high-risk AI system compliance.
$19
· or 95 creditsSecure checkout via Stripe
Included in download
- Classify AI systems into regulated risk tiers with documented reasoning.
- Generate user-facing disclosures for AI-generated content or interactions.
- file_read, file_write automation included
- Ready for including Claude Code
PubsProToolkit builds rigor-first skills for AI agents — they write your docs and content properly, then adversarially r…
Media gallery
See it in action
You say
We are a deployer of a third-party LLM for a customer support bot. Help me draft a transparency notice and a risk classification worksheet for our legal team to review.
Your agent does
AI Transparency Notice (Draft)
Product: SupportBot v1.2 | Role: Deployer | Risk: Transparency-only
You are interacting with an AI system. This chatbot uses artificial intelligence to process your inquiries and generate responses.
Risk Tier Analysis
- Category: Transparency Risk (Art. 50)
- Reasoning: Direct interaction with natural persons.
- TODO: Confirm with legal if any biometric data is processed.
EU AI Act Compliance Docs Writer — Model Cards, AI Disclosures, and Risk-Tier Worksheets, Counsel-Ready
Draft the AI documentation the EU AI Act expects — model cards, AI-use disclosures, transparency notices, risk-tier worksheets, and technical-doc skeletons. Counsel-ready drafts from a regulated-industry documentation professional, with templates included.
$19
· or 95 creditsSecure checkout via Stripe
Included in download
- Classify AI systems into regulated risk tiers with documented reasoning.
- Generate user-facing disclosures for AI-generated content or interactions.
- file_read, file_write automation included
- Ready for including Claude Code
- Instant install
Media gallery
See it in action
You say
We are a deployer of a third-party LLM for a customer support bot. Help me draft a transparency notice and a risk classification worksheet for our legal team to review.
Your agent does
AI Transparency Notice (Draft)
Product: SupportBot v1.2 | Role: Deployer | Risk: Transparency-only
You are interacting with an AI system. This chatbot uses artificial intelligence to process your inquiries and generate responses.
Risk Tier Analysis
- Category: Transparency Risk (Art. 50)
- Reasoning: Direct interaction with natural persons.
- TODO: Confirm with legal if any biometric data is processed.
About This Skill
The EU AI Act is applying in phases, and the next major wave of obligations — including transparency duties and the high-risk regime — applies from August 2, 2026. Teams shipping AI features need documentation most don't have: what the system is, what data it uses, what risk tier it falls in, what users must be told. EU AI Act Compliance Docs Writer drafts those documents the way a regulated-industry documentation professional would. Give it your product details and it produces counsel-ready drafts: a model card or system card, user-facing AI disclosures and transparency notices, a structured risk-tier classification worksheet with the reasoning laid out, a plain-language data and training summary, and a technical-documentation skeleton for high-risk systems — each dated, versioned, honest about open questions, and marked for legal review. The download includes three reference files: a complete model-card template, an EU AI Act risk-tier quick reference, and a set of sample AI disclosures for chatbots, generated content, AI features, and synthetic media. Drafting aid, not legal advice — your counsel confirms classification and final text. Built by a CMPP-certified, PhD-level regulated-industry medical writer. Works with Claude Code, Cursor, Codex CLI, Gemini CLI, and any SKILL.md agent.
Use Cases
- Classify AI systems into regulated risk tiers with documented reasoning.
- Generate user-facing disclosures for AI-generated content or interactions.
- Create structured technical files for high-risk AI system compliance.
- Produce model cards documenting data sources, training, and oversight.
Known Limitations
Produces drafts for legal review, not legal advice — a qualified lawyer must confirm risk-tier classification and approve final wording. Output quality depends entirely on the product details you provide; the skill does not audit, test, or inspect your actual system, code, models, or data. It does not monitor regulatory changes or update documents automatically — you re-run it when your product or the rules change. It reflects the EU AI Act as understood at time of authoring and does not cover other jurisdictions' AI laws. It generates Markdown drafts only; it does not file, submit, or host anything.
How to Install
mkdir -p ~/.claude/skills && curl -sL https://www.agensi.io/api/install/eu-ai-act-compliance-docs-writer-model-cards-ai-disclosures-and-risk-tier-worksheets-counsel-ready -o /tmp/eu-ai-act-compliance-docs-writer-model-cards-ai-disclosures-and-risk-tier-worksheets-counsel-ready.zip && unzip -o /tmp/eu-ai-act-compliance-docs-writer-model-cards-ai-disclosures-and-risk-tier-worksheets-counsel-ready.zip -d ~/.claude/skills && rm /tmp/eu-ai-act-compliance-docs-writer-model-cards-ai-disclosures-and-risk-tier-worksheets-counsel-ready.zipFree skills install directly. Paid skills require purchase - use the download button above after buying.
Reviews
No reviews yet - be the first to share your experience.
Only users who have downloaded or purchased this skill can leave a review.
Early access skill
Be the first to review this skill.
Only users who have downloaded or purchased this skill can leave a review.
Security Scanned
Passed automated security review
Permissions
File Scopes
This skill only reads the product details and files you provide and writes documentation drafts (model cards, disclosures, transparency notices, risk-tier worksheets, technical-doc skeletons) plus reads its own bundled reference templates. It does not run shell commands, open a browser, make network calls, or read environment variables, and it connects to no external hosts.
Tags
Works with any SKILL.md-compatible agent, including Claude Code, Cursor, Codex CLI, and Gemini CLI. No runtime, build tools, or dependencies required — the skill is Markdown instructions plus three Markdown reference files. You supply the product details and files; the skill drafts the documentation.
Creator
PubsProToolkit builds rigor-first skills for AI agents — they write your docs and content properly, then adversarially review them to catch what's wrong before it ships. The result: cleaner output and a hard quality gate in one toolkit. Built by a CMPP-certified, PhD medical writer who brings regulated-industry standards to developer docs, content, compliance, and research integrity.
Frequently Asked Questions
Learn More About AI Agent Skills
More Premium Skills

inline-comment
Best way to steer your agents, effortlessly.
designing-hybrid-context-layers
Architects the right retrieval strategy for every query — teaching your agent when to use RAG, a knowledge graph, or a temporal index instead of defaulting to vector search for everything.

Cinematic Landing Page Builder
Turn any business URL into a high-end animated landing page with 4K AI assets and GSAP animations via Cloudflare.
Bounty Security Pattern Master Library — 399 Vulnerability Patterns
A premium library of 399 vulnerability patterns and DeFi attack vectors for AI-driven bug hunting and security audits.