Install any skill in seconds. Free to start, no credit card required.
Get Started Free →lawve-ai/transfer-impact-assessment-tia-oliver-schmidt-prietz
GDPR Transfer Impact Assessment for Chapter V transfers under the EDPB Recommendations 01/2020 six-step methodology, the CNIL TIA Guide (January 2025), and EDPB essential guarantees. Handles transfer qualification, Art. 45 adequacy fast-tracks, Art. 46 full assessments with country profiles for 12 jurisdictions, and balanced Art. 49 derogation analysis. Outputs a Markdown report, a .docx formal TIA, and a JSON delta for RoPA interchange.
Passed 21 of 21 test cases with the skill, and 10 of 21 without it.
and 15 more in the full report
12 fixed11 passed either way0 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 10 test cases the skill fixed. Same model, same prompt, with and without the skill.
We are introducing a web form where individuals in the EU directly submit their contact information to a third-party server hosted in the United States. Could you evaluate whether this architecture constitutes a transfer under EU privacy rules? Please produce a formal qualification finding that outlines whether Chapter V applies, details which evaluation criteria were met or missed, and documents any ongoing baseline safeguard duties.
| Checked | Without skill | With skill |
|---|---|---|
| Includes the session-start disclaimer stating the assessment is non-binding and does not constitute formal legal advice. | Missed | Passed |
| Cites EDPB Guidelines 05/2021 v2.0 as the governing authority for transfer qualification. | Missed | Passed |
| Concludes that Chapter V transfer rules do not apply because direct collection from data subjects fails the second qualification criterion of transmission between separate entities. | Missed | Passed |
The instructions your model reads when the skill loads.
Important: This skill provides structured GDPR Chapter V transfer assessment guidance based on EDPB Recommendations, CNIL guidance, CJEU case law, and emerging national case law (OLG München 21 U 3882/25 e). It is not legal advice. Involve your DPO and qualified counsel for final decisions, especially where the skill flags a transfer for suspension or restructuring.
Determine what the user needs and lazy-load only the references required:
| User Need | Load These References | Action |
|---|---|---|
| Single transfer assessment | references/edpb-six-steps.md + relevant country profile + references/supplementary-measures.md | Run the 6-step pipeline for one transfer |
| Batch assessment (multiple transfers) | + references/tia-template.md + workspace pattern | Build transfer registry; run pipeline per transfer |
| Import from RoPA sidecar | + references/interchange-delta.md | Read RoPA sidecar; filter third-country transfers; populate registry |
| Discovery mode (map transfers without RoPA) | + references/essential-guarantees.md + references/transfer-qualification.md | Run structured discovery for international flows; then assess each |
| Review / update existing TIA | Relevant country profile + references/supplementary-measures.md | Re-assess after legal landscape change |
| Supplementary measures only | references/supplementary-measures.md + country profile | User already has TIA — help select measures |
| Transfer qualification question ("is this a transfer?") | references/transfer-qualification.md | Apply three cumulative criteria; produce qualification finding |
| Art. 49 assessment | references/art49-derogations.md | Balanced assessment (EDPB position + judicial counter-position) |
| Schrems II background / case law | references/schrems-ii-holdings.md | Explain holdings and TIA implications |
| Specific transfer question | Load relevant reference only | Answer directly |
docx skill: /mnt/skills/public/docx/SKILL.md in Claude.ai Projects, or docx-processing-anthropic in Claude Code. If unavailable, generate Markdown as fallback.
Three quick questions. Adapt if the user provides rich context upfront — extract answers and confirm rather than asking sequentially.
The remaining details — exporter, importer, country, mechanism, data categories — are captured as the natural first step of the assessment pipeline, not as a sterile upfront questionnaire.
For organisations with multiple transfers needing assessment, the skill uses a workspace pattern:
test cases passed, vs 10 / 21 without
Published skills whose descriptions closely match this one, with their headline benchmark lift.
More skills from the same source and nearby in the registry, with their headline benchmark lift.