legitimate-interest
GDPR Legitimate Interest Assessment (LIA) — Guided assessment for Art. 6(1)(f) GDPR using the EDPB three-step test. Based on EDPB Guidelines 1/2024, EDPB Opinion 28/2024 (AI models), the OSS Case Digest on Legitimate Interest (McIntyre 2026), CNIL AI guidance (June 2025), ICO guidance, and key CJEU case law. Use when: (1) user needs to assess whether legitimate interest is appropriate, (2) user asks about Art. 6(1)(f), "Interessenabwägung", "berechtigtes Interesse", "balancing test", or "LIA", (3) user wants to document a legitimate interest assessment, (4) user mentions the three-step test, (
npx skills add lawve-ai/awesome-legal-skills --skill legitimate-interest-oliver-schmidt-prietz --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
What it does
Guides users through a comprehensive Art. 6(1)(f) GDPR assessment using the EDPB three-step test, producing a documented Legitimate Interest Assessment (LIA) suitable for accountability records.
How it works
- Provides a session initialization disclaimer and prompts to proceed.
- Informs when to search for recent developments and how to choose an assessment mode (Full LIA, Quick Check, Legal Basis Comparison, Right to Object Response).
- Performs Pre-Assessment Gate checks (G1–G4) to determine availability of Art. 6(1)(f).
- Guides through Three-Step Test:
- Step 1: Pursuit of a Legitimate Interest — outputs a clearly articulated interest, classifies as Controller/Third-party/Both, confirms lawfulness and presence, and yields a PASS/FAIL/REQUIRES REFINEMENT verdict.
- Step 2: Necessity of Processing — lists data categories, assesses less intrusive alternatives, data minimisation, proportionality, and whether third-party interests affect necessity; outputs a verdict (PASS/FAIL/REQUIRES SCOPE REDUCTION).
- Step 3: Balancing Test — core assessment to weigh controller interests against data subject interests, rights, and freedoms (full methodology and examples are referenced in the prompts).
When to use it
- Use when the user needs to assess whether legitimate interest is appropriate (Art. 6(1)(f)).
- Use to document a legitimate interest assessment for accountability records and regulatory alignment.
- Applicable when evaluating necessity, proportionality, or balancing in contexts such as direct marketing, IT security, AI training, web scraping, or cross-border data sharing.
What it can touch
- References to data categories, processing activities, controller/third-party interests, and data subject rights as part of the three-step process. The skill directs the agent to collect context and justify each step using the cited legal framework.
Caveats
- Emphasizes that the tool provides guidance based on regulatory sources and does not constitute legal advice.
- Requires up-to-date web search during activation for recent developments (EDPB, CNIL, ICO, etc.).
- Excludes use for consent assessments, contract performance, DPIA workflows, or pure ePrivacy/cookie questions (with some overlap notes).
# GDPR Legitimate Interest Assessment (LIA) Guide users through a comprehensive Art. 6(1)(f) GDPR assessment using the EDPB three-step test, producing a documented Legitimate Interest Assessment (LIA) suitable for accountability records. ## Legal Framework **Primary Sources:** - **GDPR Art. 6(1)(f)** — Legitimate interest legal basis - **EDPB Guidelines 1/2024** on processing based on Art. 6(1)(f) GDPR (adopted 8 October 2024) — the core interpretive document - **EDPB Opinion 28/2024** on AI models and processing of personal data (17 December 2024) — AI-specific LIA guidance; see [references/additional-regulatory-sources.md] §1 - **EDPB OSS Case Digest on Legitimate Interest** (March 2026, Dr. TJ McIntyre) — 62 OSS decisions + 5 EDPB binding decisions analysed; see [references/oss-enforcement-practice.md] - **CNIL Recommendations on Legitimate Interest for AI Development** (19 June 2025) + companion web scraping focus sheet — the most operationally detailed national guidance on AI + LI; see [references/additional-regulatory-sources.md] §2 - **UK ICO Legitimate Interests Guidance** (updated 23 March 2026) — includes DUA Act 2025 "Recognised Legitimate Interest" new basis; note diver
- Legal Framework
- Session Initialization
- 1. Display Disclaimer
- 2. When to Search the Web
- 3. Determine Assessment Mode
- Pre-Assessment Gate: Is Art. 6(1)(f) Even Available?
- Three-Step Test: Guided Assessment
- Information Gathering (Adaptive Conversational Flow)
- STEP 1: Pursuit of a Legitimate Interest
- STEP 2: Necessity of the Processing
- STEP 3: Balancing Test
- Contextual Modules
- Retroactive Reliance on Legitimate Interest
- Cross-Border Considerations
What does the legitimate-interest skill do?
GDPR Legitimate Interest Assessment (LIA) — Guided assessment for Art. 6(1)(f) GDPR using the EDPB three-step test. Based on EDPB Guidelines 1/2024, EDPB Opinion 28/2024 (AI models), the OSS Case Digest on Legitimate Interest (McIntyre 2026), CNIL AI guidance (June 2025), ICO guidance, and key CJEU case law. Use when: (1) user needs to assess whether legitimate interest is appropriate, (2) user asks about Art. 6(1)(f), "Interessenabwägung", "berechtigtes Interesse", "balancing test", or "LIA", (3) user wants to document a legitimate interest assessment, (4) user mentions the three-step test, (
How do I install it?
Run `npx skills add lawve-ai/awesome-legal-skills --skill legitimate-interest-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.
