Agent skill · Security

eu-ai-act-report-oliver-schmidt-prietz

Generates a formal, structured AI Act compliance assessment report suitable for legal files, audit trails, and regulatory inquiries. This skill should be used when the user asks to "generate an AI Act report", "create a compliance assessment report", "document the AI Act analysis", "create a Prüfbericht", "export as Word document", or wants to consolidate prior AI Act skill outputs into a formal documented assessment.

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

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

Facts
Files in the skill folder: 12
SKILL.md size: 20 KB
Bundled scripts: none
Version: 2026.06.05
Declared author: Oliver Schmidt-Prietz
Path: skills/eu-ai-act-examination-report-generator-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.

Review
written from the skill's own SKILL.md · Aug 5, 2026

What it does

Generates a formal, structured AI Act compliance assessment report (Dokumentierter Pruefbericht) suitable for legal files, audit trails, and regulatory inquiries under Regulation (EU) 2024/1689.

How it works

The skill guides the user through a phased workflow:

  • Phase 1: Input Collection
    • Detect context and optionally extract up to 11 fields from prior outputs; if none, prompt for essential inputs about the AI system, organization, and context.
    • Collect report-specific fields: Client/matter reference (optional), Prepared by (name/role), Date of assessment; limit to two interaction turns for intake; unresolved fields marked as [UNCLEAR — to be confirmed].
  • Phase 1.5: Input Validation
    • Perform cross-checks for classification, role consistency, and completeness; raise flags such as Classification inconsistency, Role inconsistency, and DPIA/FRIA requirements when applicable; proceed to Phase 2 after validation.
  • Phase 2: Report Generation
    • Offer output formats: Full Assessment Report, Classification Record (Prüfprotokoll), Compliance Register Entry, Management Briefing (Entscheidungsvorlage), or multiple formats.
    • For the full assessment, follow the specified template structure, referencing supporting guidance documents and templates, and fill sections 1–9 with system description, scope, risk classifications, obligations, and recommendations.
  • Phase 3: Quality Check
    • Verify citation completeness, documented reasoning, flag any human-judgment areas, identify GDPR cross-references, and outline follow-up actions (e.g., DPIA, obligation tracking, legal review).

The skill is executed using the Claude Code tool as declared in its metadata.

From the SKILL.md

# EU AI Act Examination Report Generator Generate a formal, structured AI Act compliance assessment report (Dokumentierter Pruefbericht) suitable for legal files, audit trails, and regulatory inquiries under Regulation (EU) 2024/1689. ## Disclaimer (show at session start, do not block) > **Important:** This skill produces structured AI Act report templates based on Regulation (EU) 2024/1689. It is not legal advice. Reports should be reviewed and validated by qualified legal counsel before regulatory use. Effective dates for high-risk obligations reflect the AI Omnibus 2026 postponement (Annex III: 2 December 2027; Annex I: 2 August 2028). When report templates reference compliance deadlines, use the Omnibus-postponed values. --- ## When to Search the Web **Before report generation — search for:** ``` EU AI Act latest Commission guidance enforcement decisions [current year] EU AI Act [relevant sector] specific guidance [current year] ``` **For legal citation verification — search for:** ``` EU AI Act Regulation 2024/1689 consolidated text corrigenda [current year] ``` --- ## Workflow ### Phase 1: Input Collection (Context-First Adaptive Intake) **Step 1 — Context detection:** > "Let

What's inside
Steps it walks through
  1. Disclaimer (show at session start, do not block)
  2. When to Search the Web
  3. Workflow
  4. Phase 1: Input Collection (Context-First Adaptive Intake)
  5. Phase 1.5: Input Validation
  6. Phase 2: Report Generation
  7. Phase 3: Quality Check
  8. Phase 4: Word Document Export (Optional)
  9. Critical Reminders
  10. Part of the EU AI Act suite
Ships with 11 files
  • LICENSE.txt
  • README.md
  • evals.json
  • references/case-studies.md
  • references/compliance-timeline.md
  • references/docx-formatting.md
  • references/interpretation-aids.md
  • references/jurisdiction-checklists.md
  • references/legal-citations-index.md
  • references/output-templates.md
  • references/report-template.md
More from awesome-legal-skills
All skills →
About this skill
What does the eu-ai-act-report-oliver-schmidt-prietz skill do?

Generates a formal, structured AI Act compliance assessment report suitable for legal files, audit trails, and regulatory inquiries. This skill should be used when the user asks to "generate an AI Act report", "create a compliance assessment report", "document the AI Act analysis", "create a Prüfbericht", "export as Word document", or wants to consolidate prior AI Act skill outputs into a formal documented assessment.

How do I install it?

Run `npx skills add lawve-ai/awesome-legal-skills --skill eu-ai-act-examination-report-generator-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