Skip to content

borghei/Claude-Skills / marketing/ai-content-disclosure

ai-content-disclosure

Verified

Check AI-generated marketing content and reviews for required disclosures under the EU AI Act, FTC rules and platform AI-label policies. Use when labelling AI ads, deepfakes, chatbots, influencer posts or testimonials.

assets/content_manifest_template.json

View on GitHub
{
  "campaign": "<campaign or release name>",
  "_field_guide": {
    "type": "image | video | audio | text | chatbot | review | testimonial | endorsement",
    "channel": "youtube | tiktok | meta | facebook | instagram | threads | google_ads | website | blog | press_release | email | marketplace | linkedin | x",
    "ai_involvement": "none | assistive (standard editing: spelling, colour, crop, background clean-up) | partial (AI changed substance) | generated (AI produced the asset)",
    "realistic": "true if a person would reasonably take it for real footage, audio or photography",
    "depicts_real_people": "true if an identifiable real person appears or is voiced",
    "synthetic_performer": "true if a digitally created person appears as if a real performer",
    "virtual_influencer": "true if the endorser is an AI or CGI character",
    "public_interest": "true if the text informs the public on matters of public interest (news, policy, health, finance, elections)",
    "human_review": "true if a named person substantively reviewed it and could approve, alter or reject it",
    "editorial_responsibility": "true if a natural or legal person holds editorial responsibility for publication",
    "own_generator_offered_to_others": "true if you PROVIDE the generating AI system to others (EU provider marking duty)",
    "political": "true for social issue, electoral or political ads",
    "is_paid_ad": "true for paid placements",
    "material_connection": "none | employee | paid | free_product | discount | affiliate | family",
    "artistic_or_satirical": "true for evidently artistic, creative, satirical or fictional works",
    "regions": "EU | US | US-NY | UK | IN (audience regions; US-NY implies US)",
    "disclosures_present": "ai_label | platform_ai_toggle | ai_interaction_notice | machine_readable_marking | synthetic_performer_disclosure | material_connection | ad_disclosure"
  },
  "assets": [
    {
      "id": "<unique-id>",
      "title": "<short description>",
      "type": "video",
      "channel": "youtube",
      "ai_involvement": "generated",
      "realistic": true,
      "depicts_real_people": false,
      "synthetic_performer": false,
      "virtual_influencer": false,
      "public_interest": false,
      "human_review": false,
      "editorial_responsibility": false,
      "own_generator_offered_to_others": false,
      "political": false,
      "is_paid_ad": true,
      "material_connection": "none",
      "artistic_or_satirical": false,
      "regions": ["EU", "US"],
      "disclosures_present": []
    }
  ]
}
receiving-code-reviewobra/superpowersUse when receiving code review feedback, before implementing suggestions, especially if feedback seems unclear or technically questionable - requires technical rigor and verification, not performative agreement or blind implementationStars: 322kUpdated Claude CodeCodexVerifiedInstall
requesting-code-reviewobra/superpowersUse when completing tasks, implementing major features, or before merging to verify work meets requirementsStars: 322kUpdated Claude CodeCodexVerifiedInstall
using-git-worktreesobra/superpowersUse when starting feature work that needs isolation from current workspace or before executing implementation plans - ensures an isolated workspace exists via native tools or git worktree fallbackStars: 322kUpdated Claude CodeCodexVerifiedInstall
verification-before-completionobra/superpowersUse when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions alwaysStars: 322kUpdated Claude CodeCodexVerifiedInstall