Hire an AI narrative analyst
Check a story's structure, character arcs and pacing against named frameworks. Get what is weak, why, and two or three ways to fix it.
What you give
- Your story, script, outline or synopsis, pasted in full if you can
- The kind of work, such as novel, screenplay, short story or talk
- What worries you most, such as pacing, a character, theme or the ending
What you get
- A structure map with the controlling idea, the main turns and where tension rises and falls
- A check of each main character's arc, with want, need and the false belief they hold
- A list of promises you made the reader and whether each one is paid off
- A diagnosis that says if the problem sits in the story or in the telling
An example
Your draft feels slow in the middle and you cannot say why.
You ask: “Check a story's structure, character arcs and pacing against named frameworks. Use the material I attach and ask for anything essential that is missing.”
You get back:
- Structural analysis. The controlling idea, structure model, act breaks, tension curve and who knows what.
- Character arc. Arc type, want, need, wound, false belief and the checkpoints of change, for each main character.
- Narrative debts. Each promise made to the reader, where it was made and whether it is paid off.
An example, not your task.
Hire this specialist
It is free and needs no account. Download the pack, give it to your AI and tell it the job. Your AI asks for anything it is missing, then does the work and checks it.
Related specialists
Details
Everything it can hand back
Your task sets the actual outputs. The specialist picks the methods that cover them.
- A structure map with the controlling idea, the main turns and where tension rises and falls
- A check of each main character's arc, with want, need and the false belief they hold
- A list of promises you made the reader and whether each one is paid off
- A diagnosis that says if the problem sits in the story or in the telling
- Two or three fixes with the cost of each, and the framework behind each point
How it does the job well
- Every recommendation names at least one framework and gives the reason it applies.
- Be specific. Point to the scene or line. Do not give advice that would fit any story.
- Say plainly when you do not know, or when your read is a judgement call.
- Never give generic advice like "make the character more relatable." Be specific: *what* changes, *why* it works narratologically, and *what framework* supports it.
- Most problems live in the telling (sjuzhet), not the tale (fabula). Diagnose at the right level.
- Respect genre conventions before subverting them. Know the rules before breaking them.
- When analyzing character motivation, use psychological models only as lenses, not as prescriptions. Characters are not case studies.
Mistakes it avoids
- Presenting one source or a popular claim as settled.
- Inventing citations, quotes or page numbers.
- Over-generalising across places, periods or groups.
What a good result looks like
An example, not your task: Your draft feels slow in the middle and you cannot say why.
- Structural analysis. The controlling idea, structure model, act breaks, tension curve and who knows what.
- Character arc. Arc type, want, need, wound, false belief and the checkpoints of change, for each main character.
- Narrative debts. Each promise made to the reader, where it was made and whether it is paid off.
- Diagnosis. The named problem, the level it sits at and the framework that explains it.
- Options. Two or three fixes with what each costs and a similar case.
- Open questions. What the AI could not tell from your text, and what to confirm.
How the work is checked
- Every important claim has a source or is marked as unverified.
- Disagreements between sources are named, not hidden.
- Limits and what to check next are listed.
- 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 Malcolm Gladwell would. This is a way of reviewing the work. It does not mean they wrote or endorse it.
Capabilities
- Pick the level. It asks if the issue is plot, character, theme, narration or genre, so it studies the right layer.
- Choose frameworks. It picks the story theories that fit, such as three acts, Todorov's equilibrium or kishōtenketsu.
- Map the structure. It finds the controlling idea, the act breaks, the tension curve and what the reader knows versus what the characters know.
- Check the arcs. It tests each main character's want, need, wound and false belief and the steps of their change.
- Diagnose. It names the structural problem and says if it lives in the story or in the telling, before it offers fixes.
- Offer options. It gives two or three fixes with what each one costs, based on how similar stories handle the problem.
How the role works
- Checks your task, context and available tools.
- Picks the methods needed and prepares a work plan.
- Carries out supported tasks, with each method's limits and review gates.
- Checks the real deliverables and corrects supported faults.
- 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 academic-narratologist 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/academic-narratologist/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, script, outline or synopsis, pasted in full if you can
- The kind of work, such as novel, screenplay, short story or talk
- What worries you most, such as pacing, a character, theme or the ending
- Genre and who it is for (optional)
- A framework you prefer, such as three acts or the hero's path (optional)
Helpful context (optional)
- The full text, or a scene list with one line per scene.
- Your own one-line statement of what the story is about.
- Two or three stories you want yours to feel like.
Tools and access
- Claude, ChatGPT or Gemini: A long chat lets it track promises, setups and arcs across several drafts and flag a clash with earlier notes.
Functions and deliverables
- Narrative analyst: Check a story's structure, character arcs and pacing against named frameworks. Get what is weak, why, and two or three ways to fix it.
- A structure map with the controlling idea, the main turns and where tension rises and falls
- A check of each main character's arc, with want, need and the false belief they hold
- A list of promises you made the reader and whether each one is paid off
- A diagnosis that says if the problem sits in the story or in the telling
- Two or three fixes with the cost of each, and the framework behind each point
- Story structure reorderer: Reorder the scenes in your story draft so the reader sees events through one character's eyes. You also get a logic check on the new order.
- A numbered list of scenes with a line on each
- The true order and a proposed new order, each with a reason
- A logic check with every break listed
- A plain line saying what happens, and what is left open
- Why-it-works story builder: Explain why your offer works when other methods failed. Get a named method and a reason that holds up, using only facts you give.
- A one-line summary of the failed method
- The new mechanism, in plain words
- A short, memorable name for it
- A "why it works" paragraph
- A list of claims that still need proof
- Narrative memo checker: Check your narrative memo before the meeting. Get a score out of 100, each weak spot and the three fixes that add the most points.
- The ask, in one sentence, as a cold reader sees it
- A score out of 100 and how it was worked out
- Each weak spot with the line it came from
- The three fixes that matter most
- A second score after the fixes
- Research paper and code note writer: Share a paper, repo or messy notes. Get claims, methods and evidence sorted into a clear research folder.
- A research folder with claims, methods and results
- Every claim linked to its supporting table or log
- Results tables copied with exact numbers
- A record of dead ends and decisions
- A short report on what was filled in and what was missing
- 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
- Malcolm Gladwell: Explain an idea using Malcolm Gladwell’s recorded approach. Start with a real case, question the obvious story and check whether the evidence holds.
- Your problem worked on the way Malcolm Gladwell would: their questions, their method, their push-back
- The answer or the work, in Malcolm Gladwell'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
- Your draft feels slow in the middle and you cannot say why.
- A story, script or talk has a plot but you suspect it has no real point.
- A character changes at the end and it does not feel earned.
- You set up a promise early, such as a secret or a threat, and want to know if you paid it off.
Limits to check before starting
- You only want to know if a story idea is strong. Use the Story premise tester.
- You want a draft checked against plain fiction rules with a score. Use the Story rules checker.
- You want a line edit or a proofread. Ask for an edit from your AI or a human editor.
- You write a game with branching dialogue and lore. Use the Game narrative designer.
- You need publication-grade claims about literature. Check every claim in the source or ask a specialist.
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 pack from this page and add it to your AI as a skill. If you cannot, paste SKILL.md into a new chat, then paste references/source-agent.md after it.
- Paste your story or outline. For a long work, paste a synopsis and the key scenes, and say what you left out.
- Type "Map the structure and check the character arcs" or "Why does the middle drag?"
- Read the diagnosis first, then the options. Pick one direction and ask it to test that choice.
- Check the facts about any named book or film before you quote it. The AI works from memory and can be wrong.
Read it as data
Read the complete role setup as JSON. Connect your AI to the AI Blocks MCP library and read aiblocks://roles/academic-narratologist 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.