ai-disclosure-policy

# AI Disclosure Policy Skill Every company now ships AI-generated content somewhere — support replies, marketing images, chatbot conversations, synthetic voices — and most have no rule for when to say so. Meanwhile transparency regulation is arriving (the EU AI Act's transparency obligations for chatbots, synthetic media, and deepfakes being the headline example, with obligations phasing in through 2026–2027), and the trust cost of an *undisclosed* AI surface being discovered is higher than the disclosure ever was. This skill produces the policy: what you label, where, in what words — with the honest line that final regulatory judgment belongs to your lawyer, and this document is what makes that conversation short. ## What This Skill Produces - A **surface inventory**: every place AI-generated content reaches users or the public, with today's disclosure state - A **disclosure matrix**: per surface — required (regulatory), expected (platform/industry norm), or chosen (trust) — with the reasoning - **Label copy** ready to ship: UI strings, footer lines, image/video marks, chatbot self-identification wording - The **review triggers**: what changes (new surface, new market, new regulation phase) forces a policy re-read, and who owns it ## Required Inputs Ask for (if not already provided): - Where AI output ships today or soon: chatbots, support, marketing content, images/video/voice, code, docs — and which are fully automated vs human-reviewed - Markets served (E...