Skip to content
Content
Skill

/product-ad-video-script

Turn a product into ad angles, hooks, scenes, and CTA.

From plugin
openchatcut
91227 skills1 MCP
Install
$ npx -y skills add 0xsline/OpenChatCut --skill product-ad-video-script --agent claude-code

How it fires

How this skill gets triggered: by you, by Claude, or both.

  • Fires itselfAuto-invocation. Claude auto-loads it when your prompt matches the work.Auto-invocation is when the right skill fires by itself at the right moment, driven by a FLOW.md router and a hook, instead of you invoking it by name. It is the difference between a skill being installed and a skill actually getting used.Read the full definition →
  • You can call itInvoke it directly when you want it.
  • Slash command/product-ad-video-script

Context preview

The summary Claude sees to decide when to auto-load this skill.

Turn a product into ad angles, hooks, scenes, and CTA.

SKILL.md

product-ad-video-script.SKILL.md
name: product-ad-video-script
description: Turn a product into ad angles, hooks, scenes, and CTA.

Product Ad Video Script

Use this workflow when the user wants to turn a product, landing page, offer, screenshot, or rough idea into a short ad video plan and script.

Use this workflow to plan the ad first, then execute only the assets and edits the chosen script actually needs.

When to Use

  • The user provides a product, product page, app, feature, screenshot, or offer.
  • The user asks for ad copy, hooks, UGC script, promo video, product reel, launch video, or short-form marketing video.
  • The task needs angles, scene structure, captions, CTA, and visual treatment.

Workflow

1. Read the product context: what it is, who it is for, core benefit, proof, offer, limitations, and required claims. 2. Extract or infer the customer problem, desired outcome, objections, and strongest differentiator. 3. Pick or propose 2-4 ad angles using [references/ad-script-framework.md](references/ad-script-framework.md). 4. For the chosen angle, write a concise video structure: hook, problem, demo or proof, benefit, objection handling, CTA. 5. Map each beat to required visuals using product/page assets or user-provided media. Generate new visuals only when the script needs them. 6. Create the timeline or present the script first depending on the user's intent. 7. QA claims, readability, pacing, CTA clarity, brand fit, and whether the first seconds explain why the viewer should care.

Rules

  • Ground claims in the product page, user notes, or visible assets. Do not invent prices, guarantees, medical claims, revenue claims, or endorsements.
  • Prefer clear benefits over feature lists.
  • Keep hooks concrete and viewer-facing.
  • If required information is missing and affects truthfulness or positioning, ask or label the assumption.
  • Match the visual plan to what OpenChatCut can make now; do not prescribe external-only steps unless the user asks.
  • Do not add transitions, effects, music, or voiceover unless the selected script calls for them.

Output

For planning, show angle, target viewer, hook, script beats, visual plan, captions, CTA, and assumptions. For execution, also report what was added to the timeline.

Read more
Ships withopenchatcut

Open-source, local-first conversational AI video editor with a professional multi-track timeline, Agent Skills, MCP integration, and Remotion rendering.

Get the whole plugin

Other skills on openchatcut.