Hire an AI competitor research video script writer

Everything it can hand back

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

• A study board of up to 27 ads, three per type, each with what to study
• A map of where your category crowds, its clichés, and the gaps your proof can fill
• An original video script, with the one idea it borrows and a five-line distance check
• The script polished to read aloud, an ad rules check, and one list of what's missing

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

• Skipping a check step to save time.
• Copying any competitor's words, people, footage, music or logos.
• Publishing, posting or spending money without the person's clear yes.
• 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've saved competitor ads you admire and want to know why they work.

• Study board. Saved ads filed into nine types, three per type, with brand, library ID, start date and what to study.
• Category map. Which types are crowded, repeated claims word for word, and gaps your proof can fill.
• Script. The one idea borrowed, a beat-by-beat script, and a five-line distance check.
• Read-aloud fixes. Lines reworded so they sound natural when spoken, with no change to claims or facts.
• Ad rules check. A verdict, exact lines that could get the ad rejected, and settings to choose at launch.
• 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.
• No competitor ad is called a winner, and run time is given in days.
• All five distance lines say yes, and every claim in the script is in the brand's facts.
• No draft script exists if no real ad was studied.
• 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 Al Ries would. This is a way of reviewing the work. It does not mean they wrote or endorse it.

Capabilities

• Sorts the ads. Uses the study board skill to file each ad under one of nine types and keep three per type from at least two brands, long-running ones first. The run is only as good as the ads you collect by hand. No step fills a gap from your notes.
• Maps the category. Uses the competitor gaps skill to count which types the category crowds, list repeated claims word for word, and check them against what buyers say.
• Writes your own script. Uses the one-idea script skill to pick an idea your facts can back, write a new script from your reviews, and run a five-line distance check.
• Fixes how it sounds. Uses the read-aloud skill to fix lines nobody would say out loud, without changing any claim or fact.
• Checks the ad rules. Uses the Facebook and Instagram ad rules skill to flag anything that could get the ad rejected and list what to set at launch.

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 competitor-ad-to-script 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/competitor-ad-to-script/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

• The ads you saved, each with its library ID, the brand, its start date, its words and a screenshot
• Your brand file, or your website so one can be built
• Your customer reviews, copied as written
• Your product facts and the claims you may and may not make
• Your current ad's words and offer, for the rules check to compare against
• The competitors that matter to you (optional)

Helpful context (optional)

• A screenshot of each ad's whole library card, so the start date and versions are on file
• Ads from three to six competitors, so the map shows the category and not one brand's habits
• Twenty or more of your own reviews, so the gaps rest on what your buyers say
• A list of claims and offer styles you never want borrowed, so the distance check looks for them

Tools and access

• Meta Ad Library: The public place to find competitor ads with their library ID and start date, browsed by hand.
• Claude: Holds dozens of ad cards, your reviews and your claims rules in one long run.
• Google Sheets: Keeps the board by library ID and counts types per brand, so the map is easy to check.
• Meta Ad Library: The public source for every active ad, with its library ID and start date, browsed by hand.
• Google Sheets: Keeps the board and its library IDs, so reruns only add new ads.
• Any good chat AI: Filing ads from screenshots works in any strong chat AI that reads images.
• Meta Ad Library: The public source for competitor ads, with library IDs and start dates, browsed by hand.
• Claude: Holds dozens of ad cards and your claims rules in one long chat.
• Google Sheets: Counts types per advertiser, so crowded and open cells are easy to check.
• Meta Ad Library: The free public place to see a real ad and note its ID and start date, browsed by hand.
• Any good chat AI: The job is careful reading and writing from your facts, which any strong chat AI handles.
• Any good chat AI: Finding lines that trip and fixing only the sound works well in any strong chat AI.
• Your phone's voice recorder: One recorded read shows where the presenter stumbles, which is the best evidence for what to fix.
• 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

• Competitor research video script writer: Study saved competitor ads and find useful gaps. Write an original video script, then check the spoken lines and ad rules.
  • A study board of up to 27 ads, three per type, each with what to study
  • A map of where your category crowds, its clichés, and the gaps your proof can fill
  • An original video script, with the one idea it borrows and a five-line distance check
  • The script polished to read aloud, an ad rules check, and one list of what's missing
• Competitor ad swipe file builder: Build a competitor ad swipe file from Meta Ad Library ads. Get them sorted into 9 types, with three examples each and what to study.
  • A board table with type, advertiser, library ID, start date, tier and what to study
  • A one-line pattern note for each buyer question
  • A list of thin types and ads it couldn't look at
  • Any of its own checks the board still misses, each one named
• Competitor ad opportunity finder: Share competitor ads. Find messages and formats they overlook, with briefs for ads you could test.
  • A short summary and the top three gaps
  • A map of the category by ad type, crowded, thin or open
  • A card for every ad studied, and the claims everyone repeats
  • Briefs for each gap, with the proof each rests on and what to avoid
  • A score out of 100 for how many of its own checks the study passes, with each miss named
• Competitor-inspired video script writer: Turn a competitor ad you admire into a new video script. It borrows one idea, writes from your own facts, and checks nothing else is copied.
  • The one idea borrowed, in a sentence, with the fact it rests on and where it acts
  • A new script with the belief it changes, every line sourced, opening variants and a test plan
  • A five-line distance check and a list of anything missing
  • A list of any of the nine checks still missed, or none
• Ad script read-aloud editor: Fix the lines in your ad script that trip when read aloud. Paste it in and get each fix, the rule it broke, and any line still failing.
  • Each failing phrase, where it is and the rule it breaks
  • The full fixed text for each one
  • Flags for any claim or number that looks wrong, left as written
  • Any line a presenter still couldn't say cleanly after the fixes
• 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
• 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
• Al Ries: Clarify what a brand should stand for using Al Ries’s recorded approach. Examine its category, focus, name and launch story.
  • Your problem worked on the way Al Ries would: their questions, their method, their push-back
  • The answer or the work, in Al Ries'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've saved competitor ads you admire and want to know why they work.
• Your ads feel stuck and you want ideas from outside your own account.
• You want to borrow what works without copying anyone's words, people or footage.

Limits to check before starting

• You have no competitor ads you can open in the public Ad Library: start with the Fact-based ad copy writer, or collect a few ads by hand first.
• You want a single image ad, not a video script: use the Reference layout image ad maker.
• You only want to check an ad you already wrote: 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's a zip with HANDOFF.md and every skill file this workflow uses.
• Give the folder to Claude (in Claude Code, or as files in a Claude Project) and say "Follow HANDOFF.md".
• Have your inputs ready. Save the ads by hand from Meta's public Ad Library, with each one's library ID, start date, words and a screenshot. Add your brand file, reviews and product facts.
• It works step by step and saves each result. If it can't see any real ads, it stops after step 1 and tells you exactly what to collect.
• Read the distance check under the script. If any line says no, ask for a rewrite before you go further.

Read it as data

Read the complete role setup as JSON. Connect your AI to the AI Blocks MCP library and read aiblocks://roles/competitor-ad-to-script 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.