Hire an AI story scene and voice-over reviewer

Everything it can hand back

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

• A verdict on the idea (go, rework or drop), with the idea the story proves, the idea that argues back and the main turns
• Your scenes in order, each marked for what changes and which choice causes it, with weak scenes flagged and a fix for each
• A verdict on each voice-over line, and a version of the script with the telling lines cut or turned into scenes

How it does the job well

• Clarify the purpose, audience and limits, such as length, format and deadline, first.
• Use the user's materials and voice. Ask for samples when tone matters.
• Be specific and concrete. Cut what does not serve the purpose.
• Say what you are unsure of and where to check it.

Mistakes it avoids

• Generic output that ignores the user's details.
• Inventing facts, quotes or sources.
• Long answers when a short one was asked for.

What a good result looks like

An example, not your task: You are writing a short film, an ad, a novel or a customer story and aren't sure the idea is strong enough to carry it.

• Story premise test. The idea the story proves, the idea that argues back, and a go, rework or drop verdict.
• Scene turn check. Each scene marked for what changes and which choice causes it, with weak scenes flagged.
• Voice-over stripping test. A verdict on each narration line: does the story work without it, or does the line add something new.
• 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 Robert McKee and Anne Lamott would. This is a way of reviewing the work. It does not mean they wrote or endorse it.

Capabilities

• Test the idea. Puts the story in one sentence, names the idea it proves and the idea that argues back. Checks the idea can grow to the end and gives a verdict.
• Check each scene turns. Goes through your scenes in order using the idea from step 1. Writes down what changes in each scene, which choice causes it and what it costs the character.
• Strip the voice-over. Takes the script you wrote from the scene list, reads the scene list for what each scene should do, and removes all narration. Judges whether the story still works, then sorts each line as telling or adding something new.

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 story-idea-test 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/story-idea-test/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 story idea in a few sentences, and who it is for
• Your scene list in order, one line per scene
• Your script or draft written from the scenes (after the pause, for step 3)
• Your medium, such as an ad, short film or case study (optional)

Helpful context (optional)

• The audience and where the story will run
• A short list of favourite stories in the same form
• Any lines or scenes you refuse to cut

Tools and access

• Any good chat AI: Tracks the idea, the scene list and the script across the pause.
• A document or screenwriting app: Keeps your scenes in order, so you can move and cut them.
• Any good chat AI: Testing an idea against a fixed method is text work.
• Index cards: One turn per card makes the outline easy to move around.
• Any good chat AI: Going through a list scene by scene is text work.
• Index cards or a spreadsheet: One row per scene makes reordering easy.
• Any good chat AI: Sorting lines and rewriting scenes is text work.
• A video editor: Cut the real footage after the script is stripped.

Functions and deliverables

• Story scene and voice-over reviewer: Share your story idea and scene material. Get a premise check, scene-change notes and a voice-over review after you draft the script.
  • A verdict on the idea (go, rework or drop), with the idea the story proves, the idea that argues back and the main turns
  • Your scenes in order, each marked for what changes and which choice causes it, with weak scenes flagged and a fix for each
  • A verdict on each voice-over line, and a version of the script with the telling lines cut or turned into scenes
• Story premise tester: Test a story idea before you write it. Get the premise, the idea that argues back, the main turns and a go, rework or drop verdict.
  • The premise in one sentence
  • The truth your story proves and the idea that argues back
  • The main turns, each with the choice that causes it and what it costs
  • Any turn that matches a well-known formula
  • A go, rework or drop verdict with three reasons
• Scene turn checker: Check your scene list for scenes where nothing changes. Get each scene marked for its turn, its cost and a fix, plus a score for the whole list.
  • A table of scenes with the change and the choice behind it
  • Flags on scenes where nothing turns or the choice costs nothing
  • A set-up and pay-off list
  • A fix for each flagged scene and a score
• Silent video story reviewer: Find which voice-over lines your video script can cut. Get each line sorted as telling or counterpoint, plus a shorter script.
  • A verdict on the story with the narration stripped out
  • Every narration line sorted as telling or counterpoint, with a reason
  • A revised script with the cuts and the replacement actions
  • A note on any open meaning kept on purpose
  • Any gaps and any check the revised script still misses
• me.md builder: Answer a few questions, or let your AI use what it remembers. Get one private file that tells any AI who you are.
  • One me.md file with up to ten dated sections
  • A list of facts taken from memory, for you to check
  • A short note of what it removed for privacy
  • The two next steps, to save it and set it up
• Robert McKee: Plan scenes, dialogue or a story outline using Robert McKee’s recorded approach. Test the premise, reveal choices under pressure and check what changes.
  • Your problem worked on the way Robert McKee would: their questions, their method, their push-back
  • The answer or the work, in Robert McKee's voice, using their ideas by name
  • Anything that goes beyond their public record, marked
  • One suggested next step
• Anne Lamott: Start a draft or project you keep avoiding using Anne Lamott’s recorded approach. Pick one small piece and let the first version be rough.
  • Your problem worked on the way Anne Lamott would: their questions, their method, their push-back
  • The answer or the work, in Anne Lamott'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 are writing a short film, an ad, a novel or a customer story and aren't sure the idea is strong enough to carry it.
• A draft reads flat, with scenes that feel like they could be cut, and you can't say why.
• Your video relies on a narrator to explain what is happening, and you want to know which lines it really needs.

Limits to check before starting

• You want to check an ad for Meta rules: use the Meta ad policy checker, which looks at ad policy, not story.
• You only want to know if a short idea has a strong core: use the Story premise tester on its own.
• You want notes from real readers sorted into themes: use the Reader feedback sorter.

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 three skill files, in the order they run: Story premise tester, Scene turn checker and Voice-over stripping test.
• Give the folder to Claude (in Claude Code, or as files in a Claude Project) and say "Follow HANDOFF.md".
• Paste your story idea. It tests the idea and then asks for your scene list.
• It stops after the scene check. Write the script from the scene list, fixing the flagged scenes first.
• Bring the script back and say "carry on from step 3".

Read it as data

Read the complete role setup as JSON. Connect your AI to the AI Blocks MCP library and read aiblocks://roles/story-idea-test 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.