Agent skill

Eu AI Act Report Oliver Schmidt Prietz

by lawve-ai in lawve-ai/awesome-legal-skills

Generates a formal, structured AI Act compliance assessment report suitable for legal files, audit trails, and regulatory inquiries.

AGPL-3.0Auto-check passedLegal & Compliance

Install Eu AI Act Report Oliver Schmidt Prietz

skills CLI
$ npx skills add lawve-ai/awesome-legal-skills --skill eu-ai-act-report-oliver-schmidt-prietz -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install lawve-ai/awesome-legal-skills eu-ai-act-report-oliver-schmidt-prietz --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/lawve-ai/awesome-legal-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/eu-ai-act-examination-report-generator-oliver-schmidt-prietz .claude/skills/eu-ai-act-report-oliver-schmidt-prietz && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
eu-ai-act-report-oliver-schmidt-prietz
GitHub stars
847
Token cost
~5.2k tokens
SKILL.md length
1,415 words
Files
12 (incl. references)
Skills in repo
154
Repo updated
First seen
Licence
AGPL-3.0

At a glance

Generates a formal, structured AI Act compliance assessment report suitable for legal files, audit trails, and regulatory inquiries.

  • Works in 5 steps: Input Collection (Context-First Adaptive… → 5: Input Validation → Report Generation → …
  • Asks to generate an AI Act report
  • SKILL.md covers Disclaimer (show at session…, When to Search the Web, Workflow and Critical Reminders, plus 1 more section
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Eu AI Act Report Oliver Schmidt Prietz is an agent skill from lawve-ai/awesome-legal-skills. 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.

Its SKILL.md is about 5.2k tokens, which your agent loads only when the skill is triggered. The skill folder holds 12 other files, including reference files (for example `README.md`, `evals.json` and `references/case-studies.md`).

It sits in Legal & Compliance, covering AI governance. It works with Microsoft Word. The repository describes itself as: A curated list of awesome Agent Skills for automating legal work. The licence is AGPL-3.0.

When your agent uses it

  • Asks to generate an AI Act report
  • Create a compliance assessment report
  • Document the AI Act analysis
  • Create a Prüfbericht

Example prompts

  • “generate an AI Act report”
  • “create a compliance assessment report”
  • “document the AI Act analysis”
  • “/eu-ai-act-report-oliver-schmidt-prietz”

Workflow steps

5 steps, taken from the step headings in SKILL.md.

  1. Input Collection (Context-First Adaptive Intake)
  2. 5: Input Validation
  3. Report Generation
  4. Quality Check
  5. Word Document Export (Optional)

What it can do on your machine

Read from SKILL.md and the folder at commit 045f738. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md (its code samples are markdown).

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Eu AI Act Report Oliver Schmidt Prietz loads about 5.2k tokens when it runs, and up to ~31k if it reads all its reference files. Until then it costs about 115 tokens; SKILL.md has 1,415 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~115
When it runs · the whole SKILL.md, loaded when a task matches
~5.2k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~31k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from lawve-ai/awesome-legal-skills at commit 045f738, republished under its AGPL-3.0 licence (© lawve-ai). 1,415 words, ~5,159 tokens.

Download SKILL.mdSave it as .claude/skills/eu-ai-act-report-oliver-schmidt-prietz/SKILL.md (or your agent's skills folder). This skill also uses 11 other files; get the full folder from GitHub.
name
eu-ai-act-report-oliver-schmidt-prietz
description
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.
metadata.author
Oliver Schmidt-Prietz
metadata.license
AGPL-3.0
metadata.version
2026.06.05

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's generate your AI Act compliance report."

If you've run prior AI Act skills in this conversation, I can extract the outputs. Otherwise, paste your Assessment Context block or describe your situation.

Step 2 — Coverage analysis (internal — do not show this table to the user):

Extract up to 11 fields from prior context or narrative:

#FieldSource
1System nameContext block "System:" or description
2VersionDescription or context
3Provider/vendorDescription or context
4Technology typeDescription (ML, NLP, CV, etc.)
5Deployment contextDescription or prior skill outputs
6Data types processedDescription
7Integration levelDescription (standalone, integrated, API-based)
8Organization nameContext block or description
9SectorContext block "Sector:" line
10RoleContext block "Role:" line
11Jurisdiction / Org sizeContext block lines

If an Assessment Context block is provided, auto-populate all available fields, confirm extractions, and ask only about gaps.

If no prior skill outputs are available — gather essential inputs conversationally:

"I'll need some details about the AI system and your organization. You can answer in your own words — a paragraph or bullet points covering: what the system does, who built it, how it's used, your organization's name and sector, and where you operate in the EU."

Extract fields from the response. Ask about remaining gaps in a single follow-up.

Step 3 — Report-specific fields (always asked, since they're unique to the report):

"A few report-specific details:"

  • Client/matter reference (optional)
  • Prepared by (name/role)
  • Date of assessment

Maximum 2 interaction turns for intake. If a field remains unclear, mark as [UNCLEAR — to be confirmed].


Phase 1.5: Input Validation

Before generating the report, cross-check stated inputs for consistency:

Classification Cross-Check: If stated risk tier is "minimal" or "limited" but system description mentions:

  • Recruitment, CV screening, performance evaluation → flag as potentially high-risk — Annex III Nr. 4 (Employment): recruitment, screening, evaluation, or termination
  • Credit scoring, insurance risk assessment → flag as potentially high-risk — Annex III Nr. 5 (Essential services): credit scoring, insurance, or benefit eligibility
  • Medical diagnosis, patient triage → flag as potentially high-risk — medical AI under Annex I (product safety) or Annex III Nr. 5
  • Biometric identification → flag as potentially high-risk — Annex III Nr. 1 (Biometrics): identification or categorization
  • Student assessment, admissions → flag as potentially high-risk — Annex III Nr. 3 (Education): assessment or admissions
  • Benefits eligibility → flag as potentially high-risk — Annex III Nr. 5(c) (Social benefits): eligibility evaluation → If flag: "⚠ Classification inconsistency: [concern]. Please confirm or re-do the risk-tier classification."

Role Cross-Check:

  • If "deployer" but description mentions "we developed/built/proprietary" → flag provider
  • If "deployer" but description mentions own brand, modified purpose, significant retraining → flag quasi-provider → If flag: "⚠ Role inconsistency: [concern]. Please confirm or re-do the role determination."

Completeness Cross-Check:

  • High-risk stated but no DPIA mentioned → flag "DPIA required (Art. 26(9))"
  • FRIA-triggering category but no FRIA mentioned → flag "FRIA required (Art. 27)"

Proceed to Phase 2 after validation confirmed or flags acknowledged.


Phase 2: Report Generation

Template Selection:

"Which output format would you like?"

  • (a) Full Assessment Report — comprehensive report following the standard template (default)
  • (b) Classification Record (Prüfprotokoll) — formal audit trail for the classification decision
  • (c) Compliance Register Entry — living compliance tracking document for GRC integration
  • (d) Management Briefing (Entscheidungsvorlage) — 2-page decision document for board/C-level
  • (e) Multiple — generate more than one format

For templates (b), (c), (d): Read references/output-templates.md for the template structures, quality checklists, and when-to-use guidance.

For template (a) — the full assessment report:

Read references/report-template.md for the full template structure. Read references/legal-citations-index.md for citation accuracy. Read references/interpretation-aids.md for assessment frameworks. Read references/case-studies.md for sample report excerpts (high-risk, Art. 6(3) exception, minimal risk).

Generate the report following this structure:

markdown
# AI Act Compliance Assessment Report
## [System Name] — [Date]

---

**Report Reference:** [reference number]
**Prepared by:** [name, role]
**Organization:** [organization name]
**Date:** [date]
**Status:** [Draft / Final]

---

### 1. Introduction

**1.1 Purpose of Assessment**
This report documents the assessment of [system name] under Regulation (EU) 2024/1689 (EU AI Act). The assessment determines: (a) whether the system qualifies as an AI system under Art. 3(1), (b) the applicable risk classification, (c) the organization's role in the AI value chain, and (d) the resulting legal obligations.

**1.2 Scope**
[Description of assessment scope — what is included and excluded]

**1.3 Methodology**
Assessment based on:
- EU AI Act (Regulation (EU) 2024/1689) — all articles, recitals, and annexes
- Commission Guidelines on AI System Definition (C(2025) 924 final, 6 Feb 2025)
- Commission Guidelines on Prohibited AI Practices (4 Feb 2025)
- [Other applicable Commission guidelines]
- OECD AI Framework (AI system definition alignment)
- ISO 22989:2022 (AI concepts and terminology)
- [Any additional sources consulted, including web search results]

**1.4 Limitations**
- Based on information provided by [client/organization]
- Subject to evolving regulatory interpretation
- Does not constitute legal advice
- [Any specific limitations]

---

### 2. System Description

**2.1 General Information**

| Field | Detail |
|-------|--------|
| System name | [name] |
| Version | [version] |
| Provider/vendor | [name] |
| Technology type | [ML, NLP, CV, etc.] |
| Deployment date | [date or planned] |

**2.2 Technical Description**
[Brief technical description of how the system works]

**2.3 Deployment Context**
[How and where the system is used, who uses it, who is affected]

**2.4 Data Flows**
[What data goes in, what comes out, where data is stored]

---

### 3. Preliminary Check — Scope Exclusions (Art. 2)

| # | Exclusion | Article | Applicable? | Reasoning |
|---|----------|---------|-------------|-----------|
| 1 | Military/defence/national security | Art. 2(3) | [Yes/No] | [reasoning] |
| 2 | Third-country international cooperation | Art. 2(4) | [Yes/No] | [reasoning] |
| 3 | Scientific research exclusively | Art. 2(6) | [Yes/No] | [reasoning] |
| 4 | Pre-market R&D | Art. 2(8) | [Yes/No] | [reasoning] |
| 5 | Personal/household use | Art. 2(10) | [Yes/No] | [reasoning] |
| 6 | Free and open-source | Art. 2(12) | [Yes/No] | [reasoning] |

**Result:** [AI Act applies / Exclusion under Art. 2([x]) applies]

[If open-source: include Checklist I or II analysis]

---

### 4. Scope of Application

**4.1 Material Scope — AI System Determination (Art. 3(1))**

| # | Criterion | Met? | Reasoning |
|---|-----------|------|-----------|
| 1 | Machine-based operation | [Yes/No] | [reasoning] |
| 2 | Degree of autonomy | [Level X] | [reasoning] |
| 3 | Adaptability after deployment | [Yes/No] | [reasoning] |
| 4 | Explicit or implicit goals | [Yes/No] | [reasoning] |
| 5 | Inference capability | [Yes/No] | [reasoning] |
| 6 | Output generation | [Yes/No] | [reasoning] |
| 7 | Environmental influence | [Yes/No] | [reasoning] |

**Determination:** [IS / IS NOT an AI system under Art. 3(1)]
**Confidence:** [High/Medium/Low]

**4.2 Personal Scope — Role Determination**

| Aspect | Determination |
|--------|--------------|
| Primary role | [Provider/Deployer/Importer/Distributor] |
| Legal basis | [Art. 3(x)] |
| Quasi-provider risk | [None/Low/Medium/High] |
| Art. 25 scenario | [N/A or applicable scenario] |

[Detailed reasoning for role determination]

**4.3 Territorial Scope**

| Aspect | Detail |
|--------|--------|
| Provider establishment | [EU/non-EU] |
| Deployer establishment | [EU Member State(s)] |
| AI output used in EU | [Yes/No] |
| Territorial basis | [Art. 2(1)(a)/(b)/(c)] |

---

### 5. Intended Purpose (Art. 3(12))

**Provider's documented intended purpose:**
[As stated in provider's documentation]

**Actual deployment context:**
[How the system is actually used]

**Alignment assessment:**
[Match/Deviation — if deviation, assess Art. 25(1)(c) implications]

---

### 6. Risk Classification

**6.1 Prohibited Practices Screening (Art. 5)**

| # | Category | Article | Applicable? | Reasoning |
|---|----------|---------|-------------|-----------|
| 1 | Subliminal/manipulative/deceptive | Art. 5(1)(a) | [No/Possibly/Yes] | [reasoning] |
| 2 | Exploitation of vulnerabilities | Art. 5(1)(b) | [No/Possibly/Yes] | [reasoning] |
| 3 | Social scoring | Art. 5(1)(c) | [No/Possibly/Yes] | [reasoning] |
| 4 | Criminal risk prediction (profiling) | Art. 5(1)(d) | [No/Possibly/Yes] | [reasoning] |
| 5 | Untargeted facial recognition scraping | Art. 5(1)(e) | [No/Possibly/Yes] | [reasoning] |
| 6 | Emotion recognition (workplace/education) | Art. 5(1)(f) | [No/Possibly/Yes] | [reasoning] |
| 7 | Biometric categorization (sensitive) | Art. 5(1)(g) | [No/Possibly/Yes] | [reasoning] |
| 8 | Real-time remote biometric ID (public) | Art. 5(1)(h) | [No/Possibly/Yes] | [reasoning] |

**Result:** [No prohibited practice identified / PROHIBITED — Art. 5(1)([x])]

**6.2 High-Risk Assessment**

**6.2.1 Annex I — Product Safety**
[Assessment against 18 Annex I categories]
**Result:** [Not applicable / Applicable — Annex I Nr. [X]]

**6.2.2 Annex III — Application-Based**

| # | Category | Applicable? | Sub-category | Reasoning |
|---|----------|-------------|-------------|-----------|
| 1 | Biometrics | [Yes/No] | | |
| 2 | Critical infrastructure | [Yes/No] | | |
| 3 | Education & training | [Yes/No] | | |
| 4 | Employment & workers | [Yes/No] | | |
| 5 | Essential services | [Yes/No] | | |
| 6 | Law enforcement | [Yes/No] | | |
| 7 | Migration & border | [Yes/No] | | |
| 8 | Justice & democracy | [Yes/No] | | |

**Result:** [Not applicable / Applicable — Annex III Nr. [X]]

**6.2.3 Art. 6(3) Exception Analysis**
[If Annex III triggered: analyze Art. 6(3) conditions (a)-(d)]
[Profiling re-exception check]
**Result:** [Exception applies — not high-risk / Exception does not apply — HIGH-RISK]

**6.3 GPAI / Systemic Risk Assessment**
[If applicable: GPAI model assessment, FLOP threshold, systemic risk indicators]
**Result:** [Not GPAI / GPAI standard / GPAI with systemic risk]

**6.4 Transparency Obligations (Art. 50)**

| Obligation | Article | Applicable? |
|-----------|---------|-------------|
| Interaction disclosure | Art. 50(1) | [Yes/No] |
| Synthetic content marking | Art. 50(2) | [Yes/No] |
| Emotion recognition disclosure | Art. 50(3) | [Yes/No] |
| Deep fake labeling | Art. 50(4) | [Yes/No] |

---

### 7. Applicable Obligations

[Obligation summary matrix — from a prior obligation-mapping step, or generated here based on the classification and role]

**7.1 Obligation Summary**

| Category | Count | Immediate | Short-term | Ongoing |
|----------|-------|-----------|------------|---------|
| Technical measures | [X] | [Y] | [Z] | [W] |
| Organizational measures | [X] | [Y] | [Z] | [W] |
| Management systems | [X] | — | [Y] | [Z] |
| Impact assessments | [X] | [Y] | — | — |
| **Total** | **[X]** | **[Y]** | **[Z]** | **[W]** |

**7.2 Critical Timeline Obligations**
[List obligations with nearest deadlines]

**7.3 Management Systems Required**
[List required management systems]

---

### 8. Risk Flags & Recommendations

**8.1 Identified Risks Requiring Legal Judgment**
[List any areas where the assessment cannot reach a definitive conclusion]

**8.2 Recommendations**

| # | Recommendation | Priority | Responsible |
|---|---------------|----------|-------------|
| 1 | [recommendation] | [High/Medium/Low] | [role] |
| 2 | [recommendation] | [High/Medium/Low] | [role] |

**8.3 GDPR Cross-References**
[List applicable GDPR obligations and suggested skills]

---

### 9. Conclusion

**Overall Classification:**
[System name] is classified as a **[risk tier]** AI system under the EU AI Act, with the organization acting as **[role]**.

**Compliance Readiness:**
[Assessment of current compliance status — Ready / Partially Ready / Not Ready]

**Key Actions:**
1. [Most important action]
2. [Second most important action]
3. [Third most important action]

---

**Prepared by:** [name]
**Date:** [date]
**Reviewed by:** [name, if applicable]

**Disclaimer:** This assessment is based on the information provided and current interpretation of the EU AI Act (Regulation (EU) 2024/1689) as of the assessment date. It does not constitute legal advice. The regulatory landscape is evolving — Commission guidelines, delegated acts, and harmonized standards may affect this assessment. Periodic reassessment is recommended.

Phase 3: Quality Check

After generating the report, verify:

  1. Citation completeness: Every legal determination has an article reference
  2. Reasoning documented: Each Yes/No determination includes reasoning
  3. Flags raised: All areas requiring human legal judgment are explicitly flagged
  4. GDPR cross-references: Applicable GDPR obligations are identified
  5. Follow-up actions: Clear next steps are specified
  6. Limitations stated: Any uncertainties or information gaps are documented

Suggest follow-up actions:

  • DPIA per Art. 35 GDPR if not yet completed
  • Obligation implementation tracking
  • Periodic reassessment schedule
  • Legal counsel review of flagged areas

Show full SKILL.md (607 more words)Show less
Phase 4: Word Document Export (Optional)

Note: This phase requires Claude Code (CLI) with file system access. It is not available on claude.ai or mobile.

After Phase 3 Quality Check is complete, offer the Word document export:

"Would you like me to also export this as a professionally formatted Word document (.docx)?"

If the user declines or the environment does not support file generation → skip this phase.

If yes:

Prerequisite: The docx-processing-anthropic skill must be installed at ~/.claude/skills/docx-processing-anthropic/. If the skill directory does not exist, inform the user: "Word document export requires the docx-processing skill. Install it first, then re-run this phase."

Step 1 — Confirm details:

"I'll generate a Word document. Where should I save it?"

Default: current working directory. Use the naming convention: AI-Act-[Template]-[SystemName]-[YYYY-MM-DD].docx

Step 2 — Generate the document:

Read references/docx-formatting.md for styling specifications, typography, table formatting, cover page structure, and per-template structural guidance.

Read the docx-js API reference from the docx-processing skill (~/.claude/skills/docx-processing-anthropic/references/docx-js.md) for the full library API and critical formatting rules.

Generate a JavaScript file that:

  1. Creates a cover page (own section, no header/footer) with report type, system name, metadata, and disclaimer
  2. Adds a Table of Contents (except for Management Briefing template)
  3. Converts all report sections using the heading hierarchy (H1 → HeadingLevel.HEADING_1, etc.)
  4. Renders all assessment tables with consistent styling (light gray header rows, thin gray borders)
  5. Adds headers (report title + date) and footers ("Confidential" + page numbers) on all pages except cover
  6. Includes the disclaimer as final paragraph

Run the JavaScript file to produce the .docx. Verify the file was created successfully.

Step 3 — Confirm delivery:

"Word document saved to: [file path]"


Critical Reminders

  1. This report is a documentation aid — it does not replace legal judgment on complex classification questions
  2. Flag uncertainty honestly — marking "Possibly" is better than forcing a wrong determination
  3. Include all search results — if web search revealed new guidance, cite it in the methodology section
  4. Art. 6(4) documentation requirement — providers of Annex III systems classified as non-high-risk under Art. 6(3) must document their assessment before placing on market (Art. 6(4)). This includes documenting which condition (a)-(d) is met, the harm assessment, and confirming no profiling. Include this Art. 6(4) documentation (which exception limb is met + harm assessment + no-profiling confirmation) in the report where the exception was relied on.
  5. Version control — include date and version; reassess when circumstances change
  6. Dual language terms — preserve German legal terms alongside English for EU legal context
  7. Include compliance timeline — reference references/compliance-timeline.md for applicable deadlines, quarterly action calendar, and phased compliance roadmap in Section 8 (Recommendations)
  8. Jurisdiction-specific recommendations — reference references/jurisdiction-checklists.md for per-country compliance checklists and employment law overlay when generating recommendations
  9. Enforcement context — when assessing financial exposure (especially for the Management Briefing template), use the Art. 99 penalty tiers: up to €35M / 7% of worldwide annual turnover for Art. 5 prohibited-practice violations, and €15M / 3% for other infringements, enforced via national market-surveillance authorities (and the AI Office for GPAI)

Part of the EU AI Act suite

This skill works on its own, but it's designed to interlock with my other EU AI Act skills — install any individually, or use them together for an end-to-end workflow:

  • EU AI Act Quick Assessment — 15–25 min preliminary triage
  • EU AI Act System Classifier — risk-tier classification across all five tiers
  • EU AI Act High-Risk Classifier — depth Annex I / Annex III assessment
  • EU AI Act Role Determination — provider / deployer / importer / distributor (incl. Art. 25)
  • EU AI Act Obligations Mapper — obligations by role and risk tier
  • EU AI Act Knowledge Base — Q&A over the Act + Commission guidelines

Each is available as a separate skill — install only what you need.

© lawve-ai, AGPL-3.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 11 other files (references) in skills/eu-ai-act-examination-report-generator-oliver-schmidt-prietz of lawve-ai/awesome-legal-skills.

  • SKILL.md
  • 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

Open the folder on GitHubat commit 045f738

Compare with similar skills

Eu AI Act Report Oliver Schmidt Prietz next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Eu AI Act Report Oliver Schmidt Prietz compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Eu AI Act Report Oliver Schmidt Prietz this skilllawve-ai/awesome-legal-skills847—~5.2kAutomated safety check: PassAGPL-3.0
Akf Trust Metadatasickn33/agentic-awesome-skills47k2 repos~495Automated safety check: PassMIT
Paper to Chinese Patent DrafterYuan1z0825/nature-skills47k1 repos~1.1kAutomated safety check: PassApache-2.0
Paper To Cn Patentsnipp-zha/Paper-to-patent-Skill1071 repos~959Automated safety check: PassNone
Elements-Style Complaint Generatorcat-xierluo/legal-skills721—~2.6kAutomated safety check: NotesMIT
Pii Contract Analyzegregmos/PII-Shield150—~8.9kAutomated safety check: NotesMIT

Similar skills

  • Akf Trust Metadata

    sickn33/agentic-awesome-skills

    The AI native file format. An agent skill from sickn33/agentic-awesome-skills.

    47k GitHub starsUsed in 2 repos~495 tokens
    Legal & ComplianceAuto-check passed
  • Paper to Chinese Patent Drafter

    Yuan1z0825/nature-skills

    Drafts Chinese invention patent applications and technical disclosures from research papers or inventor materials, tying each claim feature to source evidence.

    47k GitHub starsUsed in 1 repo~1.1k tokens
    Legal & ComplianceAuto-check passed
  • Paper To Cn Patent

    snipp-zha/Paper-to-patent-Skill

    Convert scientific papers, theses, technical reports, source code, figures, or research manuscripts into evidence-grounded Chinese invention patent drafts.

    107 GitHub starsUsed in 1 repo~959 tokens
    Legal & ComplianceAuto-check passed
  • Elements-Style Complaint Generator

    cat-xierluo/legal-skills

    Converts a lawyer's ordinary complaint or a described case into the Supreme People's Court's elements-style Word template, with layout checks on the result.

    721 GitHub stars~2.6k tokensUpdated yesterday
    Legal & ComplianceAuto-check: notes
  • Pii Contract Analyze

    gregmos/PII-Shield

    Universal legal document processor with PII anonymization. An agent skill from gregmos/PII-Shield.

    150 GitHub stars~8.9k tokensUpdated 3 mo ago
    Legal & ComplianceAuto-check: notes
  • Iso42001

    Sushegaad/Claude-Skills-Governance-Risk-and-Compliance

    Expert ISO 42001 AI Management System (AIMS) compliance advisor.

    946 GitHub starsUsed in 1 repo~3.7k tokens
    Legal & ComplianceAuto-check passed

More from lawve-ai/awesome-legal-skills

All 154 skills in this repo
  • Customs Trade Law Onur Kafkas

    lawve-ai/awesome-legal-skills

    U.S. An agent skill from lawve-ai/awesome-legal-skills.

    847 GitHub stars~4.1k tokensUpdated 9 days ago
    Auto-check passed
  • Eu Data Act Oliver Schmidt Prietz

    lawve-ai/awesome-legal-skills

    Practitioner skill for advising on EU Regulation 2023/2854 (Data Act).

    847 GitHub stars~3.9k tokensUpdated 9 days ago
    Auto-check passed
  • Litigation Deadline Calendar

    lawve-ai/awesome-legal-skills

    Calendar litigation and arbitration deadlines from a scheduling order.

    847 GitHub stars~4.3k tokensUpdated 9 days ago
    Auto-check passed
  • Outlook Emails Lawvable

    lawve-ai/awesome-legal-skills

    Read, search, and download emails and attachments from Microsoft Outlook via OAuth2.

    847 GitHub stars~672 tokensUpdated 9 days ago
    Auto-check passed
  • Ambiguity Report

    lawve-ai/awesome-legal-skills

    Turn an interpretive-ambiguity audit of a legal text — contract, statute, regulation, or judicial opinion — into a polished deliverable.

    847 GitHub stars~4.6k tokensUpdated 9 days ago
    Auto-check passed
  • Az Eu Website Privacy Audit

    lawve-ai/awesome-legal-skills

    Audits a website for compliance with Azerbaijan's Law on Personal Data No.

    847 GitHub stars~3.8k tokensUpdated 9 days ago
    Auto-check passed

Works with

Questions about Eu AI Act Report Oliver Schmidt Prietz

What does Eu AI Act Report Oliver Schmidt Prietz do?

Generates a formal, structured AI Act compliance assessment report suitable for legal files, audit trails, and regulatory inquiries. Eu AI Act Report Oliver Schmidt Prietz is an agent skill from lawve-ai/awesome-legal-skills. Generates a formal, structured AI Act compliance assessment report suitable for legal files, audit trails, and regulatory inquiries.

When should I use Eu AI Act Report Oliver Schmidt Prietz?

Eu AI Act Report Oliver Schmidt Prietz fits situations like: asks to generate an AI Act report; create a compliance assessment report; document the AI Act analysis; create a Prüfbericht.

How do I install Eu AI Act Report Oliver Schmidt Prietz in Claude Code?

Run `npx skills add lawve-ai/awesome-legal-skills --skill eu-ai-act-report-oliver-schmidt-prietz -a claude-code`. Or copy the skill folder (skills/eu-ai-act-examination-report-generator-oliver-schmidt-prietz in lawve-ai/awesome-legal-skills) into .claude/skills/eu-ai-act-report-oliver-schmidt-prietz in your project. Claude Code loads it when a task matches its description.

How do I install Eu AI Act Report Oliver Schmidt Prietz in Codex?

Run `npx skills add lawve-ai/awesome-legal-skills --skill eu-ai-act-report-oliver-schmidt-prietz -a codex`. Or copy the skill folder (skills/eu-ai-act-examination-report-generator-oliver-schmidt-prietz in lawve-ai/awesome-legal-skills) into .agents/skills/eu-ai-act-report-oliver-schmidt-prietz in your project. Codex loads it when a task matches its description.

Can I use Eu AI Act Report Oliver Schmidt Prietz in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add lawve-ai/awesome-legal-skills --skill eu-ai-act-report-oliver-schmidt-prietz -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/eu-ai-act-report-oliver-schmidt-prietz, .gemini/skills/eu-ai-act-report-oliver-schmidt-prietz, .github/skills/eu-ai-act-report-oliver-schmidt-prietz and .opencode/skills/eu-ai-act-report-oliver-schmidt-prietz in your project.

What does Eu AI Act Report Oliver Schmidt Prietz need to run?

SKILL.md names no scripts, command-line tools or credentials: Eu AI Act Report Oliver Schmidt Prietz is instructions for the agent only.

Does Eu AI Act Report Oliver Schmidt Prietz access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Eu AI Act Report Oliver Schmidt Prietz safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Eu AI Act Report Oliver Schmidt Prietz use?

Eu AI Act Report Oliver Schmidt Prietz is published under the AGPL-3.0 licence (from the LICENSE file in the skill folder). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Eu AI Act Report Oliver Schmidt Prietz use?

About 5.2k tokens (SKILL.md is roughly 21k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 26k tokens, read only when the agent opens those files.

What are the alternatives to Eu AI Act Report Oliver Schmidt Prietz?

Skills that share tags, products or a category with Eu AI Act Report Oliver Schmidt Prietz: Akf Trust Metadata (sickn33/agentic-awesome-skills, 47k stars), Paper to Chinese Patent Drafter (Yuan1z0825/nature-skills, 47k stars), Paper To Cn Patent (snipp-zha/Paper-to-patent-Skill, 107 stars) and Elements-Style Complaint Generator (cat-xierluo/legal-skills, 721 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Eu AI Act Report Oliver Schmidt Prietz?

lawve-ai (a GitHub organization) maintains it in lawve-ai/awesome-legal-skills, which has 847 GitHub stars. The repository holds 154 skills in this directory. The repository was last updated on October 2, 2026.

Source: lawve-ai/awesome-legal-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.