ai-act-knowledge

EU AI Act Knowledge Engine — authoritative regulatory Q&A grounded in 70 official EU source documents (including the 2026 Commission draft guidelines on Art.

Skill by Oliver Schmidt-Prietz

IndexedNOASSERTION★ 895

Write a review

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/lawve-ai-ai-act-knowledge

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

About

EU AI Act Knowledge Engine — authoritative regulatory Q&A grounded in 70 official EU source documents (including the 2026 Commission draft guidelines on Art. 6 high-risk classification — general principles, Annex I, Annex III). Answers any question about the AI Act with article-level citations from the full regulation text, Commission guidelines, EDPB/EDPS opinions, codes of practice, harmonised standards, FRIA guides, incident templates, and sector-specific guidance. This skill should be used when the user asks about the "EU AI Act", "AI Act regulation", "Regulation 2024/1689", "KI-Verordnung", asks to "explain an AI Act article", "what does Article X say", "AI Act requirements", "AI Act penalties", "AI Act timeline", "GPAI obligations", "high-risk AI", "prohibited AI practices", "AI Act and GDPR", "fundamental rights impact assessment", "AI Act standards", "AI Act national implementation", "AI literacy", "serious incident reporting", "Digital Omnibus", "AI regulatory sandbox", or any question about EU artificial intelligence regulation. Also triggers on German terms: "KI-Gesetz", "KI-Verordnung", "Hochrisiko-KI", "KI-Kompetenz", "Grundrechte-Folgenabschaetzung", "GPAI-Verhaltenskodex". For assessment workflows that produce a classification decision rather than a knowledge answer, offer to run a structured risk-tier classification in-session.

Use cases: writing, legal

Reviews

Write a review

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools: No tools found
Secrets: None asked for
Install scripts: None found

Network hosts it talks to 1

codeload.github.com · found in install command

Files it touches

~/.claude/skills/ai-act-knowledge

What's inside

Skill name: ai-act-knowledge
Description: EU AI Act Knowledge Engine — authoritative regulatory Q&A grounded in 70 official EU source documents (including the 2026 Commission draft guidelines on Art. 6 high-risk classification — general principles, Annex I, Annex III). Answers any question about the AI Act with article-level citations from the full regulation text, Commission guidelines, EDPB/EDPS opinions, codes of practice, harmonised standards, FRIA guides, incident templates, and sector-specific guidance. This skill should be used when the user asks about the "EU AI Act", "AI Act regulation", "Regulation 2024/1689", "KI-Verordnung", asks to "explain an AI Act article", "what does Article X say", "AI Act requirements", "AI Act penalties", "AI Act timeline", "GPAI obligations", "high-risk AI", "prohibited AI practices", "AI Act and GDPR", "fundamental rights impact assessment", "AI Act standards", "AI Act national implementation", "AI literacy", "serious incident reporting", "Digital Omnibus", "AI regulatory sandbox", or any question about EU artificial intelligence regulation. Also triggers on German terms: "KI-Gesetz", "KI-Verordnung", "Hochrisiko-KI", "KI-Kompetenz", "Grundrechte-Folgenabschaetzung", "GPAI-Verhaltenskodex". For assessment workflows that produce a classification decision rather than a knowledge answer, offer to run a structured risk-tier classification in-session.
License: NOASSERTION
Metadata: author: Oliver Schmidt-Prietz · license: AGPL-3.0 · version: 2026.06.21
Instructions: 190 lines in SKILL.md · view on GitHub

Agent Skills spec issues

name: "ai-act-knowledge" does not match folder "eu-ai-act-knowledge-base-oliver-schmidt-prietz"
description: longer than 1024 characters
files: referenced but missing: templates/draft-guidance-art73-high-risk.md, templates/serious-incident-template-gpai.md

Files (88)

LICENSE.txt
README.md
SKILL.md
evals.json
README.md · references/codes-of-practice/
gpai-code-detailed.md · references/codes-of-practice/
gpai-code-ec-overview.md · references/codes-of-practice/
gpai-code-final.md · references/codes-of-practice/
transparency-code-draft-1.md · references/codes-of-practice/
transparency-code-draft-2.md · references/codes-of-practice/
transparency-code-overview.md · references/codes-of-practice/
art-6-classification-annex-i-2026.md · references/commission-guidelines/
art-6-classification-annex-iii-2026.md · references/commission-guidelines/
art-6-classification-general-principles-2026.md · references/commission-guidelines/
README.md · references/compliance-guides/
ai-literacy-repository.md · references/compliance-guides/
copyright-tdm-consultation.md · references/compliance-guides/
modifying-ai-classification.md · references/compliance-guides/
small-businesses-guide.md · references/compliance-guides/
whistleblowing-ai-act.md · references/compliance-guides/
README.md · references/core/
annex-iii-high-risk.md · references/core/
decision-trees.md · references/core/
high-level-summary.md · references/core/
regulation-preamble-recitals.md · references/core/
regulation-title-I-general.md · references/core/
regulation-title-II-prohibited.md · references/core/
regulation-title-III-high-risk.md · references/core/
regulation-title-IV-transparency.md · references/core/
regulation-title-V-gpai.md · references/core/
regulation-title-VI-X-governance.md · references/core/
regulation-title-XI-XIII-final.md · references/core/
README.md · references/cybersecurity/
enisa-advisory-opinion.md · references/cybersecurity/
enisa-ai-cybersecurity.md · references/cybersecurity/
enisa-cybersecurity-standardisation.md · references/cybersecurity/
README.md · references/fria/
article-27-fria.md · references/fria/
ecnl-fria-guide.md · references/fria/
fria-guide-danish-institute.md · references/fria/
README.md · references/governance/
ai-office-faq.md · references/governance/
ai-pact.md · references/governance/
ec-qa-navigating-ai-act.md · references/governance/
governance-enforcement.md · references/governance/
implementation-next-steps.md · references/governance/
implementation-timeline.md · references/governance/
whistleblower-tool.md · references/governance/
README.md · references/guidelines/
ai-system-definition.md · references/guidelines/
digital-omnibus.md · references/guidelines/
ec-regulatory-framework.md · references/guidelines/
gpai-obligations-scope.md · references/guidelines/
guidelines-roadmap.md · references/guidelines/
prohibited-practices-full.md · references/guidelines/
prohibited-practices-web.md · references/guidelines/
README.md · references/impact-assessments/
healthcare-study-2026.md · references/impact-assessments/
impact-assessment-original.md · references/impact-assessments/
supporting-study.md · references/impact-assessments/
…and 28 more

The license isn't open source, so the instructions aren't shown here. Read SKILL.md on GitHub

Signals

Stars: 895
Forks: 119
Open issues: 7
Last commit (this folder): Jul 30, 2026 (3 months ago)

From GitHub (fetched Oct 24, 2026).

Details

Version: 2026.06.21
License: NOASSERTION
Repository: github.com/lawve-ai/awesome-legal-skills
Website: lawve.ai
First seen: Oct 24, 2026
Last checked: Oct 24, 2026
Source: GitHub github-graphql

More from Oliver Schmidt-Prietz

Cite this page

ai-act-knowledge skill. Agent Mart. https://agentmart.dev/skills/lawve-ai-ai-act-knowledge (last updated 2026-10-24)