Hire an AI manuscript revision planner

Everything it can hand back

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

• A page-by-page list of mistakes, out-of-character acts and big holes, with a score out of 100
• What the story is about and the scenes to add, sharpen or cut
• The draft cut to 90% of its length, with a log, plain wording and a dialogue score
• A question sheet for your readers and, later, a ranked rewrite list from their notes

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 have a finished first draft of a story, memoir or book that has rested for a few weeks.

• Step 1 cold re-read. Pages to change, out-of-character acts, big holes and a score out of 100.
• Step 2 what it is about. What recurs, three readings, the best supported, and scenes to add, sharpen or cut.
• Step 3 the cut. The draft at 90% of its length, with a log of every cut.
• Step 4 plain wording. Timid words swapped for plain ones, each change with its reason.
• Step 5 the talk. Failing lines of dialogue, fixes that keep each voice, and a score out of 100.
• Step 6 reader questions. Your ideal reader, a question sheet and a short note to send with the draft.

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.
• Every problem names a page or scene, and the score sums re-add.
• 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 Stephen King and William Zinsser would. This is a way of reviewing the work. It does not mean they wrote or endorse it.

Capabilities

• Re-read it cold. Reads the whole draft in one pass and marks every page that needs a change, with a score out of 100.
• Find what it is about. Counts what recurs, writes three readings and picks the best supported, with the scenes to add or cut.
• Cut ten percent. Cuts the draft to 90% of its length in passes and logs every cut.
• Clean up timid wording. Swaps adverbs, passive verbs and dressed-up words for plain ones, and said for fancy tags.
• Check how the talk sounds. Tests every line of dialogue by ear, fixes the worst and gives a score out of 100.
• Plan what to ask your readers. Names your ideal reader and writes a one-page question sheet to send with the draft.
• Sort what readers said. Uses the notes your readers send back after step 6's question sheet. Groups them, marks agreed problems, washes and fact catches, and ranks the rewrite list.

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 draft-revision 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/draft-revision/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 finished draft, rested for about six weeks if you can
• Facts the story must keep, such as ages, dates or names (optional)
• Who you are writing for (optional at first, needed for step 6)
• Your readers' notes, when they come back

Helpful context (optional)

• A one-line summary of each act, for a long draft
• The facts the story must keep
• A list of readers and what each is good at spotting

Tools and access

• Any good chat AI: Keeps all seven steps in one thread, so each builds on the last.
• A shared document: Readers can comment on the draft itself, so notes are tied to the place.
• Any good chat AI: Reading a long draft and listing problems is text work any strong chat AI does well.
• A pencil and a printout: Read once on paper in one sitting, mark pages, then compare with the report.
• Any good chat AI: Finding patterns across a draft is text work that a strong chat AI does well.
• A friend who reads: Ask them what the story was about in one sentence, before you show the report.
• Any good chat AI: Counting, cutting in passes and logging are text work for any strong chat AI. Ask it to show its counts.
• A word processor: Check the word count there. A chat AI's count is an estimate.
• Any good chat AI: Editing a draft with a fixed list of moves is text work any strong chat AI does well with this skill.
• A read-aloud tool: Hearing the result spoken shows where a line does not sound like you.
• Any good chat AI: Testing lines against four rules is text work any strong chat AI does well.
• Your own voice: Read each failing line aloud. Your ear is the final check.
• Any good chat AI: Writing a short question sheet is simple text work.
• A shared document: Let readers comment on the draft itself so notes are tied to the place.
• Any good chat AI: Sorting and counting notes is text work any strong chat AI does well.
• A shared document: Comments in the draft are easier to tie to places than a loose email.

Functions and deliverables

• Manuscript revision planner: Review a rested draft, target a 10% cut and improve wording and dialogue. Collect real reader feedback for the next rewrite.
  • A page-by-page list of mistakes, out-of-character acts and big holes, with a score out of 100
  • What the story is about and the scenes to add, sharpen or cut
  • The draft cut to 90% of its length, with a log, plain wording and a dialogue score
  • A question sheet for your readers and, later, a ranked rewrite list from their notes
• Fresh draft reviewer: Paste a rested draft. Get every page that needs a change, the big holes, and a score.
  • A list of pages that need a change, with the reason
  • Out-of-character acts and big holes, named
  • The flailing passages at the start
  • A list of things that recur, and a score out of 100 with the sum
• Story theme and scene reviewer: Share a finished story draft. Find recurring details, compare possible themes and plan scene changes that make the strongest reading clearer.
  • A count of what recurs, by page
  • Three readings of what it is about, with evidence
  • The best-supported reading as a tension
  • Scenes to add or sharpen, and scenes that pull another way
• Draft shortening editor: Paste a long draft and cut 10 percent of its words. You get the shorter draft, a log of every cut and a check that the story still works.
  • The draft at 90% of its length or less
  • A log of every cut by pass, with word counts
  • A list of planted details it kept
  • A story and voice check
• Plain English editor: Paste a draft and get it back in plain English, with every cut explained and a read-aloud check. Edit stiff emails, reports and pages.
  • The edited text in plain words
  • A list of every cut or swap, with its reason
  • The point of the piece in one sentence
  • Questions where a fact was missing
• Dialogue editor: Share a scene with speaker notes. Review natural speech, distinct voices, hidden explanation and dialogue tags, then get fixes and a checklist score.
  • A table of every line with four marks
  • The lines nobody would say, rewritten
  • A check that each speaker sounds different
  • A score out of 100 with the sum
• Reader feedback question writer: Share your draft. Identify the right test reader and get questions that uncover where they struggle.
  • Your ideal reader, named in a line
  • Five to eight questions for every reader
  • One question for each part you doubt
  • A short message to send with the draft and the rules for readers
• Reader feedback sorter: Sort feedback from several readers into what to fix, what to leave alone and a ranked rewrite list for your next draft.
  • All the notes in one list by place in the draft
  • A count of how many readers raised each point
  • Agreed problems, washes and fact catches, kept apart
  • A ranked rewrite list and questions to ask readers who were vague
• 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
• Stephen King: Plan or revise fiction using Stephen King’s recorded craft advice. Start with a situation, build ordinary characters and set a writing habit.
  • Your problem worked on the way Stephen King would: their questions, their method, their push-back
  • The answer or the work, in Stephen King's voice, using their ideas by name
  • Anything that goes beyond their public record, marked
  • One suggested next step
• William Zinsser: Edit nonfiction using William Zinsser’s recorded approach. Find the point, order what readers need and cut words that add no meaning.
  • Your problem worked on the way William Zinsser would: their questions, their method, their push-back
  • The answer or the work, in William Zinsser'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 finished first draft of a story, memoir or book that has rested for a few weeks.
• Your draft feels long and you do not know what to cut.
• You have readers' notes that disagree.
• You are about to send a draft to beta readers and want it as clean as you can make it first.

Limits to check before starting

• You have not written a first draft yet: use Story draft and writing habit planner.
• You want to fix one scene so readers need the next one: use Suspense scene writer and editor.
• You want a piece that experts admire and newcomers enjoy: use Expert and beginner writing editor.
• Your piece is an ad, a web page or an email: use Sales copy editor.
• The draft is only a day old. It runs, but the cold read is thinner and the report says so.

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".
• Paste your draft. For a long book, give one act at a time and a one-line summary of the rest. Say how long the draft has rested.
• It works step by step and saves each result. It pauses after the reader questions. Send the draft and the question sheet to four to eight readers, including your ideal reader.
• Come back with their notes and run the last step. Read the ranked list, then decide what to change.

Read it as data

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