Hire an AI expert and beginner writing editor

Everything it can hand back

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

• A brief naming both audiences, the two ways to fail and a promise to each
• A fit plan for the person who delivers it
• A draft with a plain surface and marked deeper touches
• A shorter draft with every cut listed and a put-back order
• A one-page test for one expert and one newcomer
• After the test, a ranked rewrite list that says which group each change serves

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 making a talk, article, course, product page or song for people who range from beginners to experts.

• Step 1: Two-audience brief. Both audiences described, the two ways to fail, and one promise to each.
• Step 2: Fit plan. What the deliverer does well, where the showpiece goes, and which lines to swap.
• Step 3: Layered draft. A plain surface with tagged deeper touches. This is the copy draft used by steps 4 to 6.
• Step 4: Cut draft. A shorter draft, every cut listed with a reason, and an order to put cuts back.
• Step 5: Test plan. Who to pick, what to watch, questions for each group, and pass lines.
• Step 6: Ranked rewrite list. Changes in rank order, each marked with the group it serves.

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. Steps 2 to 5 used the earlier steps' results, and step 6 used the testers' notes, not step 5's plan.
• 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 Wolfgang Amadeus Mozart and Stephen King would. This is a way of reviewing the work. It does not mean they wrote or endorse it.

Capabilities

• Names both audiences. Describes what the expert notices and what loses the newcomer, names the two ways to fail and writes one promise to each.
• Fits it to the deliverer. Lists what the speaker or performer does well, puts the showpiece where they are strongest and swaps the lines they trip on.
• Drafts in layers. Writes a plain surface a newcomer can follow in one pass, then adds a few touches only an expert would catch, each one removable.
• Cuts what crowds it. Names the main idea, scores every other idea against it, cuts what competes and lists each cut so you can put one back.
• Plans the test. Sets who to try it on, what to watch, the same questions for each group and a pass line for each, fixed before you start.
• Sorts what they said. Uses the notes your testers send back after step 5's test. Groups them by place in the draft and ranks the changes, marking which audience each serves.

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 expert-and-newcomer-writing 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/expert-and-newcomer-writing/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

• What you are making and where people will meet it
• Who the experts are and who the newcomers are, with real comments if you have them
• Who will deliver it (speak, present, read, perform), if it is not you
• Your facts, material and length limit
• Later, what an expert and a newcomer said when they tried it

Tools and access

• Any good chat AI: This is reading, sorting and writing, which any strong chat AI does well with this skill.
• Comments and reviews from both kinds of people: Real words from an expert and a beginner make the two descriptions sharper than guesses.
• A phone voice recorder: A two-minute recording of the person speaking naturally gives the plan real evidence to work from.
• A voice recorder or read-aloud tool: Hearing the surface read aloud shows whether a newcomer would follow it.
• A word counter or the AI's own count: Before and after counts show whether the cut was big enough.
• A voice recorder: With permission, a recording of their answers is easier to quote than your own notes.
• 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

• Expert and beginner writing editor: Define what experts and newcomers need, draft and trim the piece, then use real feedback from both to plan changes.
  • A brief naming both audiences, the two ways to fail and a promise to each
  • A fit plan for the person who delivers it
  • A draft with a plain surface and marked deeper touches
  • A shorter draft with every cut listed and a put-back order
  • A one-page test for one expert and one newcomer
  • After the test, a ranked rewrite list that says which group each change serves
• Two-audience brief writer: Write a brief for work that must satisfy experts and newcomers. Get two audience profiles, two failure tests and a promise to each.
  • A description of each audience: what they notice, what they need and what loses them
  • Two failure ends, each with a test you can run on a draft
  • One promise to the newcomer and one to the expert
  • The shared ground the draft can stand on
  • A list of anything missing
• Presenter fit planner: Share your brief and presenter. Get an approach that suits their strengths, with pitfalls and a standout moment.
  • A strengths and strains table for the deliverer
  • Where the showpiece goes and why
  • Which parts to keep plain, and lines to swap with the replacement
  • A rehearsal check to run, with what to mark
• Layered draft writer: Turn your mixed-audience brief into a layered draft that anyone can follow, with a few marked touches only experts will catch.
  • A full draft with a plain surface
  • A depth map listing each deeper touch and what an expert would notice
  • A feeling check if the piece carries strong emotion
  • A list of what is missing
• Long draft editor: Paste a draft that feels too full. Get the one main idea named, what competes with it cut, and every cut listed with its reason.
  • The main idea in one sentence
  • A numbered inventory of ideas, each scored
  • The cut draft, with before and after word counts
  • A cut list with the reason for each, and a parking list for ideas that belong elsewhere
• Usability test audience planner: Paste your draft. Get who to try it on, the questions to ask each, and a pass line for both.
  • Who to pick and how to keep the two groups apart
  • A setup script with nothing explained in advance
  • A watch list of what to note without asking
  • Questions for each group, and a pass line for each
  • A record sheet to fill in
• 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
• Wolfgang Amadeus Mozart: Review a performance piece using Mozart’s recorded craft ideas. Fit the performer, make the main idea clear and plan rehearsal with its audience.
  • Your problem worked on the way Wolfgang Amadeus Mozart would: their questions, their method, their push-back
  • The answer or the work, in Wolfgang Amadeus Mozart's voice, using their ideas by name
  • Anything that goes beyond their public record, marked
  • One suggested next step
• 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

Tasks you can use it for

• You are making a talk, article, course, product page or song for people who range from beginners to experts.
• Feedback pulls you both ways, with one person saying it is too basic and another saying it is too hard.
• A draft has grown past what it can carry and you cannot say what it is really about.

Limits to check before starting

• You write for one audience only: use the Creative brief reframer, or a plain editor, to sharpen the brief.
• You only need a quick edit of a finished draft: ask a plain editor or your AI to tighten it.
• You need to know what buyers want before you write: use the Customer needs finder.

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 plus one skill file for each step.
• Give the folder to Claude (in Claude Code, or as files in a Claude Project) and say "Follow HANDOFF.md".
• Say what you are making, who will see it and who will deliver it. It works step by step and saves each result.
• Run the test with one expert and one newcomer, each alone. Bring back their answers for the last step.

Read it as data

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