agentleFS
samsam007bsamsam007b/claude-code-standards-kit/skills/compliance-check/SKILL.md

compliance-check

Skill2 starsChanged 8 months agoMITView on GitHub

Check EU regulatory compliance (European Accessibility Act, GDPR, EU AI Act) across the project — produces a compliance report with required actions

9 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

3 rules. 0 are common, 1 is distinctive, and 2 are very specific to this project.

  • 0

    Common

    Most of the 7 edited versions we read keep these.

  • 1

    Distinctive

    This author's own choices. Worth a look.

  • 2

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    If empty or "all", check all three.

    line 35
  2. Very specific:

    Read contracts/CONTRACT-EU-AI-ACT.md for criteria.

    line 41
  3. Very specific:

    Run agents/AGENT-ACCESSIBILITY-AUDIT.md with focus on:

    line 58

“Common” is measured: kept by at least 6 in 10 of the 7 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

/compliance-check — EU Regulatory Compliance Check

Usage: /compliance-check [regulation]

Checks the project against EU regulatory requirements and produces a compliance report with required actions.

Supported regulations:

  • eu-ai-act — EU AI Act (Regulation 2024/1689)
  • accessibility / eaa — European Accessibility Act (enforceable June 28, 2025)
  • gdpr — General Data Protection Regulation
  • all — Full EU compliance sweep (default)

Step 1 — Determine Scope

Parse $ARGUMENTS to determine which regulation(s) to check. If empty or "all", check all three.


Step 2 — EU AI Act Check (if applicable)

Read contracts/CONTRACT-EU-AI-ACT.md for criteria.

Check:

  1. AI system risk classification — Is the system high-risk per Annex III? (recruitment, credit, law enforcement, education, critical infrastructure)
  2. Transparency obligations — Are AI-generated outputs clearly labeled?
  3. Human oversight mechanisms — Is there a human override capability?
  4. Technical documentation — Is the model/system documented?
  5. Prohibited practices — No social scoring, no subliminal manipulation, no real-time biometric surveillance in public spaces

For each criterion: PASS / FAIL / N/A

Observable truth: EU AI Act compliance report with no FAIL on prohibited practices.


Step 3 — Accessibility Check (if applicable)

Run agents/AGENT-ACCESSIBILITY-AUDIT.md with focus on:

  • WCAG 2.1 AA minimum (European Accessibility Act threshold)
  • EN 301 549 standard
  • Keyboard navigation, screen reader compatibility
  • Color contrast ≥ 4.5:1 (normal text), ≥ 3:1 (large text)

Legal threshold: Score ≥ 80/100 (EAA enforceable June 28, 2025)

Observable truth: Accessibility audit score ≥ 80/100.


Step 4 — GDPR Check (if applicable)

Check:

  1. Data minimization — Are only necessary data fields collected?
  2. Consent mechanisms — Is consent obtained before data processing?
  3. Right to deletion — Is there a data deletion mechanism?
  4. Privacy policy — Does a privacy policy exist and reference GDPR?
  5. Data processing records — Are data flows documented?

For each criterion: PASS / FAIL / N/A

Observable truth: GDPR compliance report with no FAIL on mandatory items.


Step 5 — Compliance Summary

Output a compliance matrix:

╔══════════════════════════════════════════╗
║     EU COMPLIANCE REPORT                 ║
╚══════════════════════════════════════════╝

Date: [current date]
Regulations checked: [list]

┌──────────────────┬────────┬──────────────┐
│ Regulation       │ Status │ Actions      │
├──────────────────┼────────┼──────────────┤
│ EU AI Act        │ [✓/✗]  │ [count] req. │
│ Accessibility    │ [✓/✗]  │ [count] req. │
│ GDPR             │ [✓/✗]  │ [count] req. │
└──────────────────┴────────┴──────────────┘

REQUIRED ACTIONS:
[Numbered list of mandatory fixes]

RECOMMENDED ACTIONS:
[Numbered list of improvements]

Observable truth: Compliance matrix generated. No blocking violations unaddressed.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.