All archetypes

Skit

Format
Video
Category
Screen-Native & Entertainment
Stage
TOF
Requires
Real person

What is it

A short scene where people talk to each other instead of to the camera: a FaceTime call, a couple in the kitchen, two colleagues venting about work. The product turns up the way it would in a real conversation, as something one of them found. The viewer follows the story and stops checking whether they're being sold to.

What makes it work

  1. They talk to each other, never to the lens.

    The moment a character addresses the viewer, it's an ad again. Everything the audience needs to know has to arrive inside the conversation.

  2. Open on a native interaction.

    A FaceTime ringing, "babe, come here a sec," a text thread, a comment being read. The first two seconds should look like something personal that wasn't meant for a stranger.

  3. Give it a villain and a discovery.

    Someone has a problem, someone else already solved it. The product arrives as a find being shared, not a thing being recommended. That's the difference between a skit and a testimonial with two people in it.

  4. Keep the first five seconds cheap-looking.

    Phone camera, natural light, slightly rough audio. Polish at the top is the tell. You can get more produced later in the ad once they're in the story.

  5. One actor can play both parts.

    Change the shirt, change the room, change the lighting. Most skits are two people and you rarely need to cast two.

Reference 1

AI Edit Master Prompt

Produce a {DURATION} vertical 9:16 UGC-style "street interview" ad for {PRODUCT}.

Generate the following sequence:

The Hook (The Outfit Reveal): A {SPOKESPERSON_PERSONA} is filmed in a {LIFESTYLE_SETTING} (e.g., a suburban sidewalk) by an off-camera interviewer. The interviewer asks her about her outfit. She excitedly models the {PRODUCT} (e.g., a 3-piece activewear set) in a specific {PRODUCT_COLOR}. A static text overlay highlights a massive {DISCOUNT_PRICE} (e.g., "Discounted to $6").

The Value Proposition: The {SPOKESPERSON_PERSONA} explains she loved her {PREVIOUS_COLOR} set so much she bought another, emphasizing the incredible deal: getting all three pieces for less than the {VALUE_COMPARISON} (e.g., the price of a single pair of leggings). The off-camera voice chimes in to reinforce the value of getting all three pieces.

The Feature Breakdown: The {SPOKESPERSON_PERSONA} models and points out specific {PRODUCT_FEATURES}: the {FIT_BENEFIT} (e.g., "they snatch you"), {FEATURE_1} (e.g., thumb holes), {FEATURE_2} (e.g., padded sports bra), and {FEATURE_3} (e.g., cropped jacket). She highlights the {FEATURE_3}'s value by comparing it to a typical {COMPETITOR_PRICE}.

The Call to Action: The {SPOKESPERSON_PERSONA} delivers a final {CALL_TO_ACTION} instructing viewers to click the link below and confidently walks away. The text overlay updates to a strong {CTA_TEXT} with directional emojis (e.g., "Shop now to get it for $6 ⬇️⬇️⬇️").

Assemble: A casual, conversational "impromptu interview" style UGC edit. The interaction should feel spontaneous and unscripted, relying on the natural dialogue and the creator's enthusiastic modeling of the product to drive the pitch. Maintain a single, continuous shot or use very subtle jump cuts to preserve the authentic feel.

Text Overlay: Minimal text overlay. Use a clean, static {SUBTITLE_STYLE} font to highlight the {DISCOUNT_PRICE} at the beginning and the {CTA_TEXT} at the end. No closed captions.

Audio: The raw, conversational {INTERVIEW_AUDIO} between the creator and the off-camera person. No background music, relying on ambient outdoor sounds to maintain the authentic "street" feel.

End Card: No dedicated end card; the video concludes naturally on the final call to action as the creator walks away.

Reference 2

AI Edit Master Prompt

Produce a {DURATION} vertical 9:16 skit-style factory tour ad for {PRODUCT}.

Generate the following sequence:

The Hook (The Challenge): An off-camera {BOSS_PERSONA} issues a challenge to a sharply dressed {SPOKESPERSON_PERSONA} in a {WAREHOUSE_SETTING}, asking for a large quantity of {PRODUCT} for a very low {PRICE_POINT} (e.g., "$200"). The {SPOKESPERSON_PERSONA} confidently responds that she only needs one set to impress.

The Reveal: The {SPOKESPERSON_PERSONA} introduces the {PRODUCT} (e.g., noise-canceling shiplap slat wall panels) and announces a {DISCOUNT_OFFER}. The visual briefly cuts to a beautifully installed {PRODUCT} in a modern {INTERIOR_SETTING} to show the final result.

The Factory Tour (Feature Breakdown): The {BOSS_PERSONA} questions the quality given the low price. The {SPOKESPERSON_PERSONA} immediately leads a fast-paced tour of the {MANUFACTURING_FACILITY}. A montage of dynamic, close-up machinery shots (e.g., CNC routers cutting wood, workers assembling panels) plays while she lists the {PRODUCT_SPECS} (e.g., 8 feet by 1 foot, color options) and {CORE_BENEFITS} (e.g., reduces noise, cuts down echo, easy installation).

The Call to Action: Shots of the {PRODUCT} being neatly packaged and loaded onto a {SHIPPING_VEHICLE} are shown. The {BOSS_PERSONA} expresses amazement at the deal and asks how to get it. The {SPOKESPERSON_PERSONA} delivers a direct {CALL_TO_ACTION} (e.g., "Click the video to download the Temu app").

The Final Aesthetic: The video cuts back to the beautifully styled {INTERIOR_SETTING} showing the installed {PRODUCT}. A bright {DIRECTIONAL_GRAPHIC} (e.g., pointing emojis) and {CTA_TEXT} overlay appear on the screen.

Assemble: A fast-paced, engaging skit edit that blends a playful "boss and employee" narrative with satisfying, behind-the-scenes manufacturing B-roll. The transition from the raw warehouse to the polished living room should emphasize the product's transformative value.

Text Overlay: Clean, highly legible {SUBTITLE_STYLE} captions synced word-for-word with the audio. Use contrasting colors to highlight the {DISCOUNT_OFFER} and {CALL_TO_ACTION}.

Audio: The energetic, conversational {DIALOGUE} between the off-camera boss and the on-camera spokesperson. Blend this with satisfying, ambient {FACTORY_SOUND_EFFECTS} (e.g., machinery whirring, wood cutting) during the tour montage to enhance the industrial feel.

End Card: No dedicated end card; the video concludes smoothly on the final lifestyle shot with the CTA text overlay and directional graphics.

Reference 3

AI Edit Master Prompt

Produce a {DURATION} vertical 9:16 UGC-style skit ad for {PRODUCT}.

Generate the following sequence:

The Hook (The All-in-One Claim): Establish a quick back-and-forth dialogue between two characters played by the same creator. The {BUSINESS_OWNER_PERSONA} sits in a {CASUAL_SETTING} (e.g., a cafe table) acting skeptical. The {PRODUCT_PERSONA} sits in a {PROFESSIONAL_SETTING} (e.g., an office chair with a laptop) acting calm and confident. The {BUSINESS_OWNER_PERSONA} lists a series of {CORE_FUNCTIONS} (e.g., manage tasks, talk to team, store docs), and the {PRODUCT_PERSONA} confirms it can do it "All in one place."

The Meeting Feature: The {BUSINESS_OWNER_PERSONA} leans in, asking a specific question about {FEATURE_1} (e.g., "record meetings?"). The {PRODUCT_PERSONA} elaborates, explaining it goes further by transcribing and turning them into tasks so nothing is forgotten.

The AI Feature: The {BUSINESS_OWNER_PERSONA} challenges the {PRODUCT_PERSONA} regarding {TRENDING_TECH} (e.g., "but AI?"). The {PRODUCT_PERSONA} confidently explains their {ADVANCED_FEATURE} (e.g., a whole AI brain assistant) that connects all data and automates tasks.

The Realization: The {BUSINESS_OWNER_PERSONA} has a sudden realization, stating the {VALUE_PROPOSITION} (e.g., "so basically I don't need 5 different apps?"). The {PRODUCT_PERSONA} casually confirms.

The Punchline: The {BUSINESS_OWNER_PERSONA} acts dramatically frustrated, asking a {COMEDIC_QUESTION} about where this solution was when they were struggling in the past. The {PRODUCT_PERSONA} shrugs and delivers a simple {PUNCHLINE_ANSWER} (e.g., "Right here!!").

Assemble: A fast-paced, comedic "clone" skit edit. The pacing relies on snappy, overlapping dialogue cuts between the two personas. Ensure a clear visual distinction between the two characters through wardrobe, posture, and setting to make the back-and-forth clear and engaging.

Text Overlay: Use clean, highly legible {SUBTITLE_STYLE} captions synced word-for-word with the audio. Include static, bold character labels (e.g., "Business Owner:" and "{PRODUCT}:") at the top of the screen during each respective shot to clearly identify who is speaking.

Audio: The energetic, conversational {DIALOGUE} between the two personas. Ensure the tone of the {BUSINESS_OWNER_PERSONA} is increasingly amazed and slightly manic, while the {PRODUCT_PERSONA} remains relaxed and matter-of-fact. No background music is needed.

End Card: No dedicated end card; the video concludes abruptly on the comedic punchline to maximize engagement and loopability.

Reference 4

AI Edit Master Prompt

Produce a {DURATION} vertical 9:16 UGC-style comparison ad for {PRODUCT}.

Generate the following sequence:

The Problem (Without Product): A {USER_PERSONA} in a {WORKSPACE_SETTING} is visibly stressed during a virtual meeting. They are scrambling between typing on a laptop and writing in a notebook, appearing overwhelmed. A static header reads: "Team calls without {PRODUCT}". A cascading list of text overlays with a red "X" icon appears, highlighting {PAIN_POINTS} (e.g., "Frantically scribbling notes", "Writing follow-up emails", "Not actively listening").

The Solution (The Switch): The scene cuts. The {USER_PERSONA} returns to the same setting in a different outfit, now appearing relaxed and prepared. The header updates to: "Team calls with {PRODUCT}". A graphic overlay shows a cursor clicking to toggle on the {KEY_FEATURE} (e.g., "AI Notetaker").

The Product Demo & Benefits: A picture-in-picture graphic displays a mock virtual meeting. Alongside it, a {PRODUCT_UI_OVERLAY} shows notes, action items, and transcripts being automatically generated. The {USER_PERSONA} is now completely relaxed, making eye contact with the screen, and engaging in a {RELAXING_ACTIVITY} (e.g., sipping a beverage, petting a dog). A cascading list of text overlays with a green checkmark icon appears, highlighting {CORE_BENEFITS} (e.g., "Auto Follow-ups", "Full transcript", "Actively Participating").

The End Card: The video pauses on the smiling {USER_PERSONA}. A clean, central graphic appears displaying a {VALUE_PROPOSITION_HEADLINE} (e.g., "Never miss a thing again with") directly above the {BRAND_LOGO}. The green checkmark list remains visible on the lower half of the screen.

Assemble: A highly visual "Before and After" edit. Emphasize the stark contrast between the chaotic, fragmented energy of the first half and the calm, focused energy of the second half. Use mock UI overlays to clearly demonstrate the software's capabilities without relying on dry screen recordings.

Text Overlay: Use bold, modern {SUBTITLE_STYLE} fonts for the headers. Ensure the visual contrast between the red "X" pain points and the green checkmark benefits is immediately obvious to the viewer.

Audio: Start with a tense, fast-paced {SOUND_BED} (e.g., a ticking clock or suspenseful strings) during the "Before" segment. Abruptly cut to a smooth, relaxed {POSITIVE_SOUND_BED} (e.g., upbeat lo-fi or bossa nova) the moment the "AI Notetaker" is toggled on. Incorporate muffled, conversational {MEETING_AUDIO} in the background to establish the context.

End Card: The final frame serves as the end card, utilizing the paused lifestyle shot as a background for the brand logo, headline, and summarized benefits.

Reference 5

AI Edit Master Prompt

Produce a {DURATION} vertical 9:16 UGC-style "video call" ad for {PRODUCT}.

Generate the following sequence:

The Hook (The Desperate Call): A {CALLER_PERSONA} (e.g., a stressed parent) speaks directly to the camera in a simulated video call layout, while the {RECEIVER_PERSONA} (e.g., a friend/fellow parent) listens in a small picture-in-picture window. A bold text overlay displays a {HOOK_HEADLINE} (e.g., "THE RESULTS NO ZITS CREAM EVER GAVE HER."). The caller describes an emotional {PAIN_POINT} concerning a {LOVED_ONE} (e.g., a daughter's severe skin flare-up) and the resulting {NEGATIVE_BEHAVIOR} (e.g., refusing to leave the house, quitting sports).

The Validation & Failed Attempts: The {RECEIVER_PERSONA} empathizes, validating the caller's stress. They relate by sharing that their own {LOVED_ONE} went through the exact same thing, listing a series of ineffective {FAILED_SOLUTIONS} (e.g., standard creams, spot patches, antibiotics) to build relatable frustration.

The Solution & Mechanism: The {RECEIVER_PERSONA} introduces the {PRODUCT_NAME} and holds it up to the camera. They highlight the {KEY_INGREDIENT} (e.g., Silver Chitoderm) and provide a concise, non-jargon explanation of the {PRODUCT_MECHANISM} (e.g., kills bacteria and acts like a shield so the skin can regenerate).

The Visual Proof (The AirDrop): The {RECEIVER_PERSONA} offers to send proof. A mock {SMARTPHONE_UI_OVERLAY} (e.g., an AirDrop or text message notification) pops up on the screen, revealing a striking {BEFORE_AND_AFTER_IMAGE} of the results. The {CALLER_PERSONA} reacts with genuine shock and amazement at the visible transformation.

The Call to Action & Sign-off: The {CALLER_PERSONA} urgently asks for the {PURCHASE_LINK}, stating they will order it immediately. The {RECEIVER_PERSONA} promises to send it right over. The ad ends with a natural, friendly sign-off (e.g., "Coffee on me next time") as the caller rushes off to tend to their child.

Assemble: A raw, emotion-driven "FaceTime" style edit. Utilize a continuous picture-in-picture layout to simulate a real digital conversation. The performances should feel highly authentic, unscripted, and conversational, relying on the vulnerability of the problem to build trust before introducing the product.

Text Overlay: Use clean, easy-to-read {SUBTITLE_STYLE} captions synced word-for-word with the audio. Include realistic {UI_GRAPHICS} (e.g., End Call/Mute buttons, photo sharing pop-ups) to sell the illusion of a live video call.

Audio: The raw, slightly compressed {DIGITAL_CALL_AUDIO} of the two personas conversing. No background music is needed; the focus should remain entirely on the emotional weight of the dialogue.

End Card: No dedicated end card; the video concludes naturally with the characters wrapping up their conversation and hanging up the call.