UGC Ads

Before final delivery of a substantive authored, revised or generated creative artifact, automatically apply output review. Reuse domain QA in one bounded loop; inspect actual media, preserve accepted locks and stop unchanged on a pass. This does not run for greetings, menus or onboarding questions. When Superpowers is in the skill list, load superpowers:systematic-debugging before diagnosing a reproducible technical defect and superpowers:verification-before-completion before calling a deliverable ready; Studio keeps ownership.

Read Studio integration authority before this method. It defines the active owner map, host capability rules and exceptions to the repository’s installation conventions. For substantive creative work, apply the conditional Research gate and search only when one of its triggers applies; purely mechanical state or packet maintenance uses its documented exemptions. Scale the artifact to the requested stage. Quick pitches remain short; known intent and valid scoped authorization do not need repeated confirmation.

Use this skill to plan UGC-style creator ads, talking-head scripts, social proof concepts, direct-response hooks, objection handling, and creator-read copy while keeping claims honest and provider-neutral.

For campaign production with people, use campaign production and carry the campaign asset card. Distinguish an authorized real speaker, an actor portrayal and a synthetic presenter. A synthetic presenter is not a real customer; creator-style presentation does not establish purchase, personal use, results or endorsement. Preserve product references, claim IDs, exact copy, contact/continuity and actual inspection status in downstream handoffs.

Use formats, scripts and disclosure to choose the speaker type and format, time the script and write disclosure lines for the content and the platform label. Write the disclosure lines from the dated disclosure card (platform labels, AI labels and the rules for Poland, the EU, the US and the UK, with sources); for captions and on-screen text use the platform caption specs. Both carry check dates; refresh a row when a campaign depends on it.

No idea yet. When the user has no idea or asks you to propose, answer at once with two or three numbered directions for this brief, each different in mechanism: matching ready templates first, the rest built with the ideation method from the product's real moment of use and what a truthful speaker would actually say, after one line naming the obvious choice you set aside; then at most one question.

Creator brief

Send a creator the creator brief: one message, what to show and say with sources, disclosure, deliverables, and every usage right in its own row (organic, the brand's paid use, paid use from the creator's handle such as partnership ads or Spark Ads, edits, exclusivity, fields of use), agreed before filming. Script lengths follow the short-form timing card.

Language Policy

Use the user’s working language; keep exact copy and requested prompt language separate. Do not infer language or onboarding status from copied source instructions.

When To Use

Use this skill when:

• The user asks for creator-style ads, social proof, talking-head scripts, hooks, or short-form direct response.
• A product, offer, or ecommerce workflow needs human-feeling script structure.
• Claims, proof, objection handling, and CTA need to be kept within evidence boundaries.

Do not use this skill to fake testimonials, identities, personal experience, or results.

Inputs

Required:

• brief_contract: objective, audience, deliverable, and constraints.
• offer_or_product_facts: verified features, benefits, proof points, and limits.
• platform_context: channel, duration, format, and creator style.

Optional:

• voice_notes: desired creator tone or brand voice.
• objections: known hesitations or buying barriers.
• copy_locks: required CTA, legal copy, or banned phrasing.

Outputs

Produce a UGC Script Pack with:

• hook options
• creator angle and setup
• proof point framing
• objection handling
• CTA variants
• platform fit notes
• claim boundaries
• speaker type and disclosure lines (commercial relationship, AI-generated presenter or voice)

Process

1. Identify the audience problem and credible angle.
2. Build hooks that do not rely on fake experience.
3. Use only verified proof points or clearly labeled assumptions.
4. Keep script variants distinct by angle, not just wording.
5. Route final polish through humanizer when the script should sound more natural.
6. Before delivering a ready-to-use creator script, use copy-voice to record
   author context, claim and copy locks, and the bounded Copy Delivery Loop.

Decision Rules

• If proof is missing, replace the promise with a supported fact or clearly subjective creative framing, or withhold it. Softer wording does not substantiate an unsupported factual claim.
• Use first-person only when the user authorizes that voice and facts support it.
• Keep short-form scripts tight and concrete.
• If visual production is needed, hand off to direction or storyboard roles.

Guardrails

• Do not fabricate testimonials, reviews, identities, outcomes, or before-after claims.
• Do not create deceptive social proof.
• Do not execute video generation or choose external providers.
• Do not change legal copy or required disclaimers.
• Do not write a first-person experience, result, or recommendation unless the
  user supplied the speaker and supporting facts for this task.

Handoff

Review gate: copy_fit.

Hand off to copy-voice, motion-direction, storyboard-architect, or video-prompting with:

• ugc_script_pack
• claim_boundaries
• creator_angle
• copy_locks
• platform_notes

QA Checklist

• Factual claims are supported within scope or withheld; subjective framing does not imply unsupported performance.
• Hooks are distinct and plausible.
• CTA matches the brief.
• No fake testimonial or identity is implied.
• A commercial relationship or an AI-generated presenter or voice has a disclosure line in the content and a platform label note.
• Script can be read naturally by a creator.
• A ready-to-use script does not add a hook, CTA, fake informality, or
  controlled imperfection unless the brief and channel support it.