Ensure accessibility in UI components including semantic HTML, ARIA attributes, keyboard navigation, and WCAG 2.2 AA compliance.
日本語の概要は準備中です。原文の説明を表示しています。
Validate systems and processes against GDPR/CCPA privacy regulations, privacy-by-design principles, ADA/WCAG accessibility standards, data processing agreements (DPAs), and provide compliance checklists with regulatory change monitoring guidance.
インストールする前に、エージェントに与えられる指示の中身を確認できます。
Assess systems, processes, and artifacts against major regulatory frameworks:
Output is structured as PASS / CONDITIONAL / FAIL with severity-rated findings and actionable remediation tasks.
Define which regulations apply to the subject of the assessment:
## Compliance Scope
- Subject: [System / Feature / DPA / Interface being assessed]
- Jurisdictions: [EU / California / Virginia / Colorado / Other states]
- Applicable Regulations:
- [ ] GDPR (EU General Data Protection Regulation)
- [ ] CCPA/CPRA (California Consumer Privacy Act / California Privacy Rights Act)
- [ ] US State Laws (VCDPA, CPA, CTDPA, etc.)
- [ ] ADA / Section 508 (US accessibility)
- [ ] WCAG 2.1/2.2 AA (Web Content Accessibility Guidelines)
- [ ] DPA Review (vendor data processing agreement)
- Personal Data Categories Involved: [list data types]
- Assessment Date: [YYYY-MM-DD]
- Regulation Versions Referenced: [e.g., GDPR as amended 2024, CPRA effective 2023]
Execute checklist items relevant to the assessed subject:
Evaluate against Ann Cavoukian's 7 Foundational Principles:
| Principle | Assessment |
|---|---|
| 1. Proactive, not reactive | Is privacy built in from design stage, not added after? |
| 2. Privacy as default | Is the most privacy-protective setting the default? |
| 3. Privacy embedded in design | Is privacy integral to system architecture, not a bolt-on? |
| 4. Full functionality | Does privacy coexist with legitimate business objectives? |
| 5. End-to-end security | Is full lifecycle security ensured from collection to deletion? |
| 6. Visibility & transparency | Are policies and practices open and verifiable? |
| 7. Respect for user privacy | Is user-centricity maintained in all design decisions? |
Record each principle as: Implemented / Partial / Missing / Not Applicable
Evaluate against WCAG 2.1 AA (minimum standard) / WCAG 2.2 AA (current standard):
If reviewing a Data Processing Agreement:
Provide guidance on maintaining ongoing compliance:
Output one of three decisions:
{
"decision": "PASS | CONDITIONAL | FAIL",
"regulationsAssessed": ["GDPR", "CCPA", "WCAG 2.1 AA", "DPA"],
"assessmentDate": "YYYY-MM-DD",
"findings": [
{
"id": "RC-001",
"regulation": "GDPR",
"severity": "CRITICAL | HIGH | MEDIUM | LOW",
"category": "Consent Management",
"description": "Cookie consent banner missing for analytics tracking cookies",
"status": "FAIL",
"remediation": "Implement cookie consent platform with granular purpose-based opt-in",
"owner": "developer",
"deadline": "Before next deployment"
}
],
"requiredMitigations": [],
"evidencePaths": [".claude/context/reports/compliance/"],
"regulatoryLinks": [
"https://edpb.europa.eu/our-work-tools/documents/public-consultations/2023/guidelines-032023-deceptive-design-patterns_en"
],
"nextReviewDate": "YYYY-MM-DD",
"recommendedNextStep": "Assign RC-001 to developer agent; re-assess after remediation"
}
Decision Rules:
PASS: All applicable checklist items verified, no open findingsCONDITIONAL: Minor or medium findings present; allowed to proceed with documented remediation planFAIL: Critical or high findings present; must remediate before deploymentSave compliance reports to: .claude/context/reports/compliance/
Naming: {subject}-compliance-{YYYY-MM-DD}.md
| Anti-Pattern | Why It Fails | Correct Approach |
|---|---|---|
| Checking GDPR only, ignoring CCPA/state laws | Multi-jurisdiction exposure missed | Always assess all applicable jurisdictions |
| Reporting PASS when most items pass | Partial compliance is non-compliance | CONDITIONAL/FAIL for any open finding |
| Generic "implement encryption" remediation | Developer cannot act on vague guidance | Specific: "AES-256 encryption for PII fields in users table" |
| One-time audit treated as ongoing compliance | Regulations change quarterly | Establish continuous monitoring cadence |
| Treating accessibility as a nice-to-have | ADA lawsuits are an active legal risk | WCAG 2.1 AA compliance is non-negotiable for public interfaces |
| DPA with vague processing description | Regulators reject vague DPAs | Specify exact data types, processing purpose, retention periods |
Input validated against schemas/input.schema.json before execution.
Output contract defined in schemas/output.schema.json.
Pre-execution hook: hooks/pre-execute.cjs
Post-execution hook: hooks/post-execute.cjs (emits observability event)
Before starting:
cat .claude/context/memory/learnings.md
Check for:
After completing:
.claude/context/memory/issues.md.claude/context/memory/decisions.md.claude/context/memory/learnings.mdASSUME INTERRUPTION: Your context may reset. If it's not in memory, it didn't happen.
まだレビューはありません。使ってみた感想をお寄せください。
概要と使いどころ
Ensure accessibility in UI components including semantic HTML, ARIA attributes, keyboard navigation, and WCAG 2.2 AA compliance.
日本語の概要は準備中です。原文の説明を表示しています。
Use when you want to improve response quality through meta-cognitive reasoning. Applies 15+ reasoning methods to reconsider and refine initial outputs.
日本語の概要は準備中です。原文の説明を表示しています。
N-round opposing-stance debates for trade-off analysis. Assigns pro/con roles to agents, runs structured debate rounds with quality scoring, and produces a moderator synthesis with confidence-rated recommendation. Generalizable to architecture, technology, security, and design decisions.
日本語の概要は準備中です。原文の説明を表示しています。
Force adversarial code review stance that eliminates confirmation bias — reviewer must find issues or re-analyze
日本語の概要は準備中です。原文の説明を表示しています。
Creates specialized AI agents on-demand when no existing agent matches a request. Use when the Router cannot find a suitable agent for a task. Enables self-evolution by generating persistent agents.
日本語の概要は準備中です。原文の説明を表示しています。
LLM-as-judge evaluation framework with 5-dimension rubric (accuracy, groundedness, coherence, completeness, helpfulness) for scoring AI-generated content quality with weighted composite scores and evidence citations
日本語の概要は準備中です。原文の説明を表示しています。