Agent skill · AI & Agents

eu-ai-act-triage-oliver-schmidt-prietz

Fast 15-25 minute triage for preliminary EU AI Act classification and compliance assessment. This skill should be used when the user asks to "do a quick AI Act assessment", "check if the AI Act applies to us", "run a preliminary classification", "do an AI Act triage", "quick check", "preliminary assessment", "Schnellprüfung", "Ersteinschätzung", or needs a fast initial assessment before committing to full analysis.

lawve-aigithub.com/lawve-aiGitHub ↗
claude-codeNOASSERTION
Install
npx skills add lawve-ai/awesome-legal-skills --skill eu-ai-act-quick-assessment-oliver-schmidt-prietz --agent claude-code

Same command for any agent — swap --agent for codex, cursor, copilot.

Facts
Files in the skill folder: 7
SKILL.md size: 14 KB
Bundled scripts: none
Version: 2026.06.05
Declared author: Oliver Schmidt-Prietz
Path: skills/eu-ai-act-quick-assessment-oliver-schmidt-prietz/SKILL.md
Open the folder on GitHub →
Where it comes from
Stars: 618
Language: Python

Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.

From the SKILL.md

# EU AI Act Quick Assessment Fast triage tool (15-25 minutes) for preliminary AI Act classification and compliance assessment. Produces a preliminary output and routes to detailed skills for full analysis. ## Disclaimer (show at session start, do not block) > **Important:** This is a preliminary AI Act assessment based on Regulation (EU) 2024/1689, designed for rapid triage. It is not legal advice and does not replace a full assessment — validate results with a full risk-tier classification, an Art. 6 high-risk depth analysis where the high-risk branch is plausible, a role determination, an obligation mapping, a formal report, and qualified legal counsel. Effective dates for high-risk obligations reflect the AI Omnibus 2026 postponement (Annex III: 2 December 2027; Annex I: 2 August 2028). --- ## When to Search the Web **On activation — search for:** ``` EU AI Act latest enforcement updates [current year] EU AI Act Commission guidelines status [current year] ``` --- ## Quick Assessment Workflow ### Phase 1: Quick Context (Adaptive 2-Batch Flow) Gather context through a conversational 2-batch approach. Maximum 2 interaction turns — 1 if the user is detailed, 2 if gaps remain. #### B

What's inside
Steps it walks through
  1. Disclaimer (show at session start, do not block)
  2. When to Search the Web
  3. Quick Assessment Workflow
  4. Phase 1: Quick Context (Adaptive 2-Batch Flow)
  5. Phase 2: Rapid Classification (6-Step Gate Sequence)
  6. Phase 3: Preliminary Output
  7. Phase 4: Template Offer (Optional)
  8. Critical Reminders
  9. Part of the EU AI Act suite
Ships with 6 files
  • LICENSE.txt
  • README.md
  • evals.json
  • references/compliance-deadlines.md
  • references/jurisdiction-flags.md
  • references/quick-decision-tree.md
More from awesome-legal-skills
All skills →
About this skill
What does the eu-ai-act-triage-oliver-schmidt-prietz skill do?

Fast 15-25 minute triage for preliminary EU AI Act classification and compliance assessment. This skill should be used when the user asks to "do a quick AI Act assessment", "check if the AI Act applies to us", "run a preliminary classification", "do an AI Act triage", "quick check", "preliminary assessment", "Schnellprüfung", "Ersteinschätzung", or needs a fast initial assessment before committing to full analysis.

How do I install it?

Run `npx skills add lawve-ai/awesome-legal-skills --skill eu-ai-act-quick-assessment-oliver-schmidt-prietz --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.

Where does this skill come from?

From lawve-ai/awesome-legal-skills, a repository with 618 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.

Is a popular skill a good skill?

Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.

Keep going