Hire an AI video ad script and feedback reviewer

Everything it can hand back

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

• A bridge and pacing score with a tighter script
• A pass or fail on whether it sells with the sound off, with fixes
• A playback count of how many viewers repeated your claim, and what took the rest
• Stop-ship mistakes, each with a fix, a verdict and a score out of 100

How it does the job well

• Write for one named audience and one action. Each asset has a single job.
• Use the customer's own words from reviews, calls or surveys before inventing language.
• Every claim needs proof the business can show. Leave unproven claims out or mark them.
• Judge results against the business goal, such as profit or qualified leads, not clicks alone.

Mistakes it avoids

• Generic copy that could fit any brand.
• Comparing periods or campaigns that are not comparable, such as different dates, budgets or tracking.
• Calling a test winner before there is enough data.

What a good result looks like

An example, not your task: You have a script and a shoot booked, and want one more check before it is too late.

• Step 1: Bridge and pacing. Each line marked by job, when the product enters, and a tighter version of your script.
• Step 2: Sound-off check. What a silent viewer learns, a pass or fail on claim, opening, product and brand, and fixes.
• Step 3: Playback count. Your one claim, each viewer answer scored, the playback share, what took attention, and cuts.
• Step 4: Stop-ship check. Mistakes on claims, safe zones and brand details, each with a fix, a verdict and a score.
• HAND-BACK SUMMARY. Each step's file, any step not run and why, and every MISSING line 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 Rosser Reeves and Eugene Schwartz would. This is a way of reviewing the work. It does not mean they wrote or endorse it.

Capabilities

• Check the bridge and the pacing. Marks every line by job, plots how much the viewer feels sold to, checks when the product enters, and writes a tighter script.
• Check it sells with the sound off. Lists only what is seen, writes what a silent viewer learns, and checks the claim, the first shot, the product and the brand show on screen.
• Pause. Fix it and ask ten viewers. You apply the fixes, show the script to ten people and write down what each says the ad said.
• Count what viewers heard. Fixes your one claim first, scores each answer, counts the playback and names what took attention away, with cuts.
• Run the stop-ship check. Checks safe zones, claims and brand details against platform rules, then gives each fix, a verdict and a score.

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 tighten-a-video-ad-script-before-you-film-it 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/tighten-a-video-ad-script-before-you-film-it/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 video ad script, with shots or on-screen text if you have them
• Who the ad is for and your product facts (optional)
• Your brand file (optional)
• Ten people's answers to "What did that ad say?" (you collect these halfway)

Tools and access

• Any good chat AI: Any current chat AI can read a script and plot the awareness map.
• Meta Ads Manager: Shows the retention graph of a running video, so you can see where viewers drop.
• Any good chat AI: Reading shots and flagging gaps is text work any strong chat AI does well with this skill.
• Any good chat AI: Sorting viewer answers into causes is text work any strong chat AI does well with this skill.
• A shared sheet or notepad: Keeping the ten answers verbatim in one place keeps the sort honest.
• Claude: Reads full-size images closely, so it can spell-check the words in the picture and spot the safe zones.
• Meta Ads Manager: Its safe zone guardrail marks the area the app's buttons and labels won't cover, so you see what might get hidden.

Functions and deliverables

• Video ad script and feedback reviewer: Share your video script, product facts and real viewer notes. Get clearer lines, silent-view checks, distraction findings and a pre-launch review.
  • A bridge and pacing score with a tighter script
  • A pass or fail on whether it sells with the sound off, with fixes
  • A playback count of how many viewers repeated your claim, and what took the rest
  • Stop-ship mistakes, each with a fix, a verdict and a score out of 100
• Video ad transition reviewer: Check a video ad script before you film it. Find where viewers feel sold to too soon, and get a bridge score out of 100 plus a tighter script.
  • A line-by-line map of how aware the viewer is that they are being sold to
  • Each bridge (hook to body, body to call to action) marked good or abrupt
  • A bridge score out of 100, now and after the fixes, with the sum shown
  • A tighter script, with feature-to-benefit rewrites, pacing notes and a teaching step before the product
• Sound-off commercial checker: Check if your video ad still sells with the sound off. Paste a script or storyboard. Get a pass or fail and a shot for each spoken-only line.
  • A pass or fail, and a score out of 100 with how it was worked out
  • What a silent viewer would learn, shot by shot
  • Each spoken line that has no picture
  • A replacement shot for each
• Ad distraction checker: Check your ad for distractions. Paste it with ten viewers' answers. See what stole attention from your claim and what to cut.
  • A playback count and what it means
  • What viewers remembered instead, sorted by cause
  • Each line checked for picture that does not match its words
  • A cut list in order of share stolen, and a retest plan
• Pre-launch ad checker: Share your ad, audience and approved facts. Get located issues, fixes, human checks and a custom score before launch.
  • A version-bound list of observed problems and the smallest fixes
  • The buyer argument checked against the supplied facts and proof
  • A clear list of media, destination, tracking or spec checks still needed
  • A scoped verdict and observed/eligible coverage
  • An internal editing score, with any post-fix score marked provisional
• Brand profile builder: Share your website. Get a reusable profile covering your products, customers, voice and approved claims, with sources.
  • A folder of eight plain files, from a start file for your AI to a claims list and a change log
  • A tag on every fact, and every claim marked approved, pending or banned
  • A two-sentence diagnosis of your biggest gap, and a list of what's missing and who can answer it
  • A short slice for your next step, if you name one
• Rosser Reeves: Sharpen an ad’s main claim using Rosser Reeves’s recorded approach. Choose one useful benefit, match the picture and plan an honest demonstration.
  • Your problem worked on the way Rosser Reeves would: their questions, their method, their push-back
  • The answer or the work, in Rosser Reeves's voice, using their ideas by name
  • Anything that goes beyond their public record, marked
  • One suggested next step
• 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

Tasks you can use it for

• You have a script and a shoot booked, and want one more check before it is too late.
• Your last video ad ran and people could not say what it sold.
• A creator or agency sent a script and you need to judge it.

Limits to check before starting

• You have a finished cut and only need the sound-off test: use the sound-off checker on its own.
• You have no script yet: use the Customer quote video ad writer first.
• You want a policy check on a Meta ad: use the Meta ad policy checker.

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 is a zip with HANDOFF.md and every skill file this workflow uses.
• Give the folder to your AI as files, in Claude Code or a Claude Project, and say "Follow HANDOFF.md".
• Paste your script when asked. Add your brand brain if you have one.
• At the pause, apply the fixes from steps 1 and 2. Show the script to ten people who fit your buyer.
• Ask each person only "What did that ad say?" Write down their words. Do not tell them your claim first.
• Paste the answers back. Check the stop-ship result before you book the shoot.

Read it as data

Read the complete role setup as JSON. Connect your AI to the AI Blocks MCP library and read aiblocks://roles/tighten-a-video-ad-script-before-you-film-it 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.