MCP HubMCP Hub
スキル一覧に戻る

compliance-check

majiayu000
更新日 Yesterday
20 閲覧
58
9
58
GitHubで表示
メタaiapidesign

について

コンプライアンスチェックスキルは、広告やランディングページを対象に、FTC(連邦取引委員会)の開示要件やプラットフォームポリシー違反を審査します。開発者は、キャンペーン開始前、広告拒否後、またはクリエイティブ監査時に本スキルを活用すべきです。具体的には、マテリアルコネクション(物的関連性)の有無、適切な開示表示の配置、規制対象となる主張の有無などをチェックします。

クイックインストール

Claude Code

推奨
プラグインコマンド推奨
/plugin add https://github.com/majiayu000/claude-skill-registry
Git クローン代替
git clone https://github.com/majiayu000/claude-skill-registry.git ~/.claude/skills/compliance-check

このコマンドをClaude Codeにコピー&ペーストしてスキルをインストールします

ドキュメント


name: compliance-check description: Review ads and landing pages for compliance issues including FTC disclosure requirements, platform policy compliance, and restricted claims. Use before launching campaigns, when ads get rejected, or when auditing existing creative.

Compliance Check

Review creative for regulatory and platform compliance.

Process

Step 1: Check FTC Disclosure Requirements

Required Disclosures:

  • Material connections (paid/sponsored)
  • Affiliate relationships
  • Typical results (if showing testimonials)
  • Paid endorsements

Disclosure Placement:

  • Must be clear and conspicuous
  • Close to the claim
  • Same format as claim (video = video disclosure)
  • Mobile-readable size

Common FTC Issues:

  • Hidden disclosures in fine print
  • Disclosures that require scrolling
  • "Results not typical" buried at end
  • Influencer posts without #ad

Step 2: Verify Platform Policy Compliance

Facebook/Meta Policies:

  • No before/after images implying unrealistic results
  • No personal attributes targeting ("Are you overweight?")
  • No misleading claims
  • No prohibited content (weapons, adult, etc.)
  • Landing page must match ad claims

TikTok Policies:

  • Similar to Meta plus TikTok-specific rules
  • Authenticity requirements
  • No misleading information

Google/YouTube Policies:

  • Healthcare restrictions
  • Financial service requirements
  • Destination requirements

Native Ad Policies:

  • Varies by network
  • Generally stricter on health claims
  • Editorial-style requirements

Step 3: Flag Restricted Claims

Health Claims:

  • Disease treatment/cure claims
  • Drug-like claims
  • Specific medical outcomes
  • "Clinically proven" without evidence

Financial Claims:

  • Income guarantees
  • "Get rich quick" implications
  • Investment returns promises

Before/After:

  • Unrealistic transformations
  • Implied guaranteed results
  • Time-specific promises

Testimonials:

  • Atypical results presented as typical
  • Fake reviews/testimonials
  • Undisclosed paid testimonials

Step 4: Suggest Compliant Alternatives

Reframing Techniques:

  • "May help support..." vs "Cures..."
  • "Users reported..." vs "You will..."
  • "Individual results vary" disclaimer
  • Opinion-based language

Safe Phrasing:

ProblematicCompliant Alternative
"Lose 30 lbs in 30 days""Supports healthy weight management"
"Cures diabetes""Supports healthy blood sugar levels"
"Make $10K/month""Income potential varies"
"Guaranteed results""Results may vary"

Step 5: Output Compliance Report

## COMPLIANCE CHECK: [Creative/Campaign Name]

### REVIEW SUMMARY

**Overall Risk Level:** [Low / Medium / High / Critical]
**Issues Found:** [#]
**Platforms Reviewed For:** [FB, TikTok, Google, Native]

---

### FTC COMPLIANCE

**Disclosure Status:** [Compliant / Needs Work / Non-Compliant]

**Required Disclosures:**
- [ ] Affiliate relationship disclosed
- [ ] Sponsored content marked
- [ ] Typical results disclaimer present
- [ ] Material connections clear

**Issues Found:**
1. [Issue description]
   - Location: [Where in creative]
   - Severity: [Low/Medium/High]
   - Fix: [Recommended solution]

---

### PLATFORM POLICY COMPLIANCE

**Facebook/Meta:**
| Policy Area | Status | Issue | Fix |
|-------------|--------|-------|-----|
| Personal attributes | [Pass/Fail] | [Issue] | [Fix] |
| Before/after | [Pass/Fail] | [Issue] | [Fix] |
| Health claims | [Pass/Fail] | [Issue] | [Fix] |
| Landing page match | [Pass/Fail] | [Issue] | [Fix] |

**TikTok:**
| Policy Area | Status | Issue | Fix |
|-------------|--------|-------|-----|
| [Area] | [Pass/Fail] | [Issue] | [Fix] |

**[Other Platforms]:**
...

---

### CLAIM ANALYSIS

**Claims Made:**
1. "[Claim from creative]"
   - Type: [Health/Financial/Results]
   - Status: [Safe / Risky / Prohibited]
   - Evidence required: [What's needed to support]
   - Recommendation: [Keep/Modify/Remove]

2. "[Claim from creative]"
   ...

---

### FLAGGED CONTENT

**HIGH RISK (Must Fix):**
1. **Issue:** [Description]
   - Location: [Where]
   - Why it's a problem: [Explanation]
   - Compliant alternative: "[Suggested rewording]"

**MEDIUM RISK (Should Fix):**
1. **Issue:** [Description]
   ...

**LOW RISK (Consider Fixing):**
1. **Issue:** [Description]
   ...

---

### TESTIMONIALS/SOCIAL PROOF

**Testimonials Used:**
1. [Testimonial description]
   - Disclosure present: [Yes/No]
   - Typical results: [Yes/No/Unclear]
   - Recommendation: [Action needed]

---

### LANDING PAGE COMPLIANCE

**Page:** [URL]

| Element | Status | Issue |
|---------|--------|-------|
| Claims match ad | [Pass/Fail] | [Issue] |
| Disclosures present | [Pass/Fail] | [Issue] |
| Terms/Privacy linked | [Pass/Fail] | [Issue] |
| Contact info | [Pass/Fail] | [Issue] |

---

### RECOMMENDED CHANGES

**Critical (Before Launch):**
1. [ ] [Change required]
2. [ ] [Change required]

**Important (Soon):**
1. [ ] [Change recommended]

**Optional (Best Practice):**
1. [ ] [Enhancement]

---

### COMPLIANT COPY ALTERNATIVES

**Original:** "[Problematic text]"
**Compliant Version:** "[Rewritten text]"
**Why:** [Explanation of change]

---

### APPROVAL CHECKLIST

Before launching, confirm:
- [ ] All high-risk issues resolved
- [ ] Disclosures in place
- [ ] Claims substantiated or softened
- [ ] Landing page matches ad
- [ ] Platform-specific requirements met
- [ ] Legal/compliance team approved (if applicable)

---

### RISK ASSESSMENT

**If Launched As-Is:**
- Ad rejection likelihood: [Low/Medium/High]
- Account risk: [Low/Medium/High]
- Legal risk: [Low/Medium/High]
- Reputation risk: [Low/Medium/High]

Compliance Resources

FTC Guidelines:

  • Endorsement Guides
  • Health Claims guidance
  • Made in USA rules

Platform Policies:

  • Meta Advertising Policies
  • TikTok Advertising Policies
  • Google Ads Policies

Safe Practices:

  • When in doubt, soften the claim
  • Document evidence for claims
  • Use "may," "can help," "supports"
  • Always disclose relationships

Source: Affiliate Research, FTC guidelines

GitHub リポジトリ

majiayu000/claude-skill-registry
パス: skills/compliance-check

関連スキル

content-collections

メタ

This skill provides a production-tested setup for Content Collections, a TypeScript-first tool that transforms Markdown/MDX files into type-safe data collections with Zod validation. Use it when building blogs, documentation sites, or content-heavy Vite + React applications to ensure type safety and automatic content validation. It covers everything from Vite plugin configuration and MDX compilation to deployment optimization and schema validation.

スキルを見る

creating-opencode-plugins

メタ

This skill provides the structure and API specifications for creating OpenCode plugins that hook into 25+ event types like commands, files, and LSP operations. It offers implementation patterns for JavaScript/TypeScript modules that intercept and extend the AI assistant's lifecycle. Use it when you need to build event-driven plugins for monitoring, custom handling, or extending OpenCode's capabilities.

スキルを見る

evaluating-llms-harness

テスト

This Claude Skill runs the lm-evaluation-harness to benchmark LLMs across 60+ standardized academic tasks like MMLU and GSM8K. It's designed for developers to compare model quality, track training progress, or report academic results. The tool supports various backends including HuggingFace and vLLM models.

スキルを見る

sglang

メタ

SGLang is a high-performance LLM serving framework that specializes in fast, structured generation for JSON, regex, and agentic workflows using its RadixAttention prefix caching. It delivers significantly faster inference, especially for tasks with repeated prefixes, making it ideal for complex, structured outputs and multi-turn conversations. Choose SGLang over alternatives like vLLM when you need constrained decoding or are building applications with extensive prefix sharing.

スキルを見る