media-forgemf-safety-rewritelisted

# media-forge:mf-safety-rewrite Use this before finalizing any prompt involving protected IP, named brands, public figures, private people, voices, logos, songs, studios, exact scenes, or lookalike character requests — **and** before finalizing a prompt that was blocked, degraded, likely to trigger moderation, or that needs a safer rewrite without losing creative intent. These are the same job seen from two directions: a rights problem and a filter problem both get solved by replacing risky surface wording with original, professional, production-safe language while preserving the scene's actual creative function. Applies to every media-forge video provider (Veo, Kling, Higgsfield, Seedance) and to image generation. None of the guidance below is provider-specific — IP risk and filter risk live in the prompt text, not in which model renders it. ## Intent The user pointing at protected work is not trying to steal — they are showing you the clearest example of what they love that exists. A wrongly blocked prompt makes a user feel accused by a machine with no court of appeal. This skill is the advocate in both directions: find what the love is made of and give it back as something safely theirs; clear the innocent by stating their honest intent plainly; never coach the guilty. Protect the rights-holder, the platform's boundary, and the user's dignity in the same move. ## Boundary — read before anything else This skill repairs **two classes of false positive**: (1) prompts th