Hire an AI talking-product video ad writer

Everything it can hand back

Your task sets the actual outputs. The specialist picks the methods that cover them.

• A brief with the buyer, the doubt and the one argument
• A script where the product speaks, with a mood and a fit check
• A line-by-line check with fixes
• Clip prompts, a character sheet and an edit plan
• An ad rules check on the script and its claims

How it does the job well

• Start from the user problem and the evidence for it, then the solution.
• Write decisions down with the reason and the options you rejected.
• Keep scope small enough to ship and learn. Name what is out of scope.
• Define how success will be measured before building.

Mistakes it avoids

• Treating opinions or one loud request as proven demand.
• Specs that skip edge cases, error states or dependencies.
• Roadmaps with dates but no owners or confidence levels.

What a good result looks like

An example, not your task: You want a playful video ad that stands out, and your product can be a character.

• Brief. The buyer, their main doubt and the one argument the ad makes.
• Script. Spoken lines and picture notes where the product talks, in one mood, with a fit check.
• Line check. Weak lines quoted with the check that failed and a fix for each.
• Clip prompts. Motion-only prompts for each clip, with a character sheet, voice and lip-sync notes, and an edit plan.
• Ad rules check. A verdict on the script and its claims against Facebook and Instagram ad rules, with the exact lines.
• Hand-back summary. Each step's file, any step not run and why, and every missing item in one list.

How the work is checked

• Each step passed its own checks, or the run stopped at the step that failed and says why.
• The steps ran in order, and each one used the result of the one before.
• Nothing was invented to fill a gap. Every gap is a MISSING: line.
• Nothing was sent, published or paid for without a clear yes.
• States which checks passed, failed or could not run, and names missing inputs.

These checks have not been run against a model yet. Your AI uses them to check its own work.

A second opinion

Before it hands back, your AI reviews the draft the way Eugene Schwartz and Claude Hopkins would. This is a way of reviewing the work. It does not mean they wrote or endorse it.

Capabilities

• Picks the buyer and the angle. Uses the angle planner to fix who the ad is for, their doubt and the one argument.
• Writes the script. Uses the talking product script skill to check the fit, choose who talks, test the product as a speaker and write the words in one mood.
• Checks every line. Uses the line checker to label each line by beat, run the checks and fix the weak lines.
• Writes the clip prompts. Uses the talking product clip skill to describe only the motion, keep the character the same across takes, and plan voice, lip-sync and the edit.
• Checks against Meta rules. Uses the ad rules checker to flag claims the talking product makes.

How the role works

1. Checks your task, context and available tools.
2. Picks the methods needed and prepares a work plan.
3. Carries out supported tasks, with each method's limits and review gates.
4. Checks the real deliverables and corrects supported faults.
5. Hands back files, evidence and unresolved gaps.

Your specialist's working setup

Download the base specialist without a task form or account. README.md and SETUP.md explain how to use the folder. SOUL.md defines its scope. INTAKE.md asks missing questions inside your AI. PLAYBOOK.md, SKILLS.md, BEST_PRACTICES.md, CHECKS.md and HANDOFF.md guide the work and its checked deliverables.

Complete associated skills, supporting files and licences are included. Choose only the methods needed for the actual task. Keep context, working files and accepted feedback in your AI project.

Use this specialist through MCP or the API

Call prepare_specialist with role_id talking-product-video-ad only. No task is required to load it. Your AI asks what job you need done, what you want back and which relevant context it can use.

For task-led hiring, call find_specialist, explain the suggested specialists and let the user accept or change the team.

Complete ZIP: Download base specialist. API: GET /api/v1/specialists/talking-product-video-ad/pack. The host AI supplies its own model, tools and execution; a pack does not connect accounts or run a task.

Inputs and helpful context

The specialist starts from the task brief. Only active methods require their inputs.

For the primary method, when used

• Your product facts, with the claims you may make, by claim ID if your brand file has them
• Your brand file and who the ad is for
• Your customer reviews (optional)
• Your target countries, for the ad rules check (optional)

Helpful context (optional)

• Full-size photos of your product, front and back
• Your claims list, with the wording you may use
• A voice you like, such as a clip or a description

Tools and access

• Claude: Keeps the character, the voice and the claims consistent across five steps.
• Veo: Makes short clips with sound and lip-sync from a prompt.
• Kling: Holds a character steady across clips when given a reference image.
• Any good chat AI: Filling a short brief from your buyer notes works well in any strong chat AI with this skill.
• Meta Ad Library: Browsing what competitors run, by hand, shows what your market has already heard.
• Any good chat AI: Writing a short first-person monologue to these rules works well in any strong chat AI.
• Veo: Speaks the object's quoted lines with matching room sound when the clips are made.
• Any good chat AI: Claude, ChatGPT and Gemini all follow this skill well, so use the one you already have.
• Veo: Takes up to three reference images and speaks quoted lines with matching sound in each clip.
• Kling: Reuses a saved character made from your reference photos, so the face holds across clips.
• GPT Image: Makes the sheets and start frames from your product photo and keeps its label words readable.
• ElevenLabs: Records one steady voice for the whole monologue when the video tool's voice drifts.
• Any good chat AI: Claude, ChatGPT and Gemini all read the rule table well; what matters is pasting the ad exactly as it will run.
• Meta Ads Manager: Its rejection notice and Business Support Home give the reason for each rejected ad, so you can test the skill against real decisions.

Functions and deliverables

• Talking-product video ad writer: Share product facts, buyer context and brand guidance. Get a talking-product script, line review, clip prompts and Meta policy findings.
  • A brief with the buyer, the doubt and the one argument
  • A script where the product speaks, with a mood and a fit check
  • A line-by-line check with fixes
  • Clip prompts, a character sheet and an edit plan
  • An ad rules check on the script and its claims
• Ad angle planner: Plan your ad angle before you write. Give it your buyer and idea. You get a brief under 200 words on how the ad opens, argues and asks.
  • A paste-ready brief of under 200 words for one level and one stage
  • The first words, when the product enters, the ask, the length and how to argue, filled in for your buyer
  • What usually goes wrong at this level
  • One line saying why, with anything assumed labelled
  • Any of its own checks the brief still misses, each named
• Talking object video ad script writer: Write a talking object video ad script: one everyday object speaks in 8 to 30 seconds, with a cast note and a source for every fact it states.
  • The narrator, the four tests it passed, and its mood
  • The monologue clip by clip, with picture notes, the turn marked and words per clip
  • A cast note on the narrator, its mood and its voice, for the clips skill
  • Every fact the object states, with its source
  • Any of its own checks it couldn't pass, named one per line
• Video ad script line checker: Check your video ad script line by line. Get each weak line with a fix from your own facts, plus a score out of 100 before and after.
  • Every weak line, quoted, with the check it fails, what's wrong and a fix
  • The beats the script is missing
  • The spoken word count against the budget for the length
  • A list of facts a fix would need that you haven't given
  • A score out of 100 now and after the fixes, with the sum shown
• Talking object video clip prompt writer: Turn your talking object script and a product photo into video clip prompts. You get a fixed character card, timed prompts and edit notes.
  • The narrator confirmed, and a character card and voice line to approve
  • Reference image prompts and sheet prompts for the object, product and set, with lock lines
  • A storyboard with start frames and a shot card per clip
  • Timed clip prompts, a fix table and edit notes
  • Any check the prompts still miss, one line each
• Meta ad policy checker: Share ad copy, images or a script. Get possible policy issues, a custom score and changes to review.
  • A verdict (ready to run, fix first, or likely rejected) and the main reason
  • A compliance score out of 100, now and after the fixes, with the sum shown
  • A table of findings with the rule group, the exact spot, the problem and the fix
  • Settings to change outside the ad, such as age targeting
  • Your ad rewritten with every fix in, changed lines marked
  • What passed, and what it couldn't check without more information
• Product context file writer: Share product facts, audience and positioning. Get a reviewed context file that other marketing skills can reference.
  • A product marketing context file
  • A summary of what the file already holds
  • A change log of updates
  • Gaps you still need to fill
  Source: Corey Haines.
• Eugene Schwartz: Match a headline or sales page to what buyers already want and know. Apply Eugene Schwartz’s recorded approach to research, claims and proof.
  • Your problem worked on the way Eugene Schwartz would: their questions, their method, their push-back
  • The answer or the work, in Eugene Schwartz's voice, using their ideas by name
  • Anything that goes beyond their public record, marked
  • One suggested next step
• Claude Hopkins: Write specific ads or plan a small buyer test using Claude Hopkins’s recorded approach. Replace vague praise with facts and track cost per customer.
  • Your problem worked on the way Claude Hopkins would: their questions, their method, their push-back
  • The answer or the work, in Claude Hopkins's voice, using their ideas by name
  • Anything that goes beyond their public record, marked
  • One suggested next step

Tasks you can use it for

• You want a playful video ad that stands out, and your product can be a character.
• You plan to make the clips with an AI video tool.
• You want the claims checked before any clip is made.

Limits to check before starting

• Your product has no face or voice to give it, or you want a plain demo: use the Product claim demo planner.
• You only want a script with no video tool: use the Ad script read-aloud editor to polish one you already have.
• You want a cartoon, clay or anime look: use the Animated film video ad script writer or the Claymation video ad script writer.

Best way to use this role

Give it one clear outcome, the actual files and a definition of done. Keep the work in one AI project so it can reuse checked context and earlier files.

• Download the handoff pack. It has HANDOFF.md and five skill files, in the order they run: Ad angle planner, Talking object video ad script writer, Video ad script line checker, Talking object video clip prompt writer and Meta ads compliance checker.
• Give the folder to Claude (in Claude Code, or as files in a Claude Project) and say "Follow HANDOFF.md".
• Have your inputs ready. Your product facts, your brand file, and a line on who the ad is for.
• Check the script before you generate anything. Fix any line the ad rules check marks "Fix first".
• Paste each clip prompt into your video tool with the character sheet and your real product photo.

Read it as data

Read the complete role setup as JSON. Connect your AI to the AI Blocks MCP library and read aiblocks://roles/talking-product-video-ad for its role instructions and pinned sources.

This is a prepared AI role. No task has run. Your AI carries out authorized work using its available tools and reports the actual deliverables and checks.