This is taking longer than expected.

Try againBrowse the library
AI Blocks

All AI specialists

Hire an AI newsletter draft and subject editor

Turn your notes into one newsletter issue. Get plain copy, honest subject options and review gaps before sending.

What you give

  • This week's notes, the moment you noticed and the one reader it is for
  • Your brand brain, for the voice check (advised)
  • Opens, clicks and replies from past issues (optional)

What you get

  • The issue, ready to paste, with the subject line chosen and alternatives
  • A readiness score out of 100 with the ship or fix call
  • The main cuts, so you learn the pattern
  • A plan of the next 12 issues, each with a reader and a worry

An example

You send a weekly newsletter and the writing eats the day before it goes out.

You ask: “Turn your notes into one newsletter issue. Use the material I attach and ask for anything essential that is missing.”

You get back:

  • The issue. The newsletter ready to paste, with the chosen subject line and the other options under it.
  • Who it is for. The one reader and their worry in a single line.
  • Score. A score out of 100, what it measured, and the ship or fix call.

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.

Download the specialist

Related specialists

Skills and workflows for this job: Write emails that get read

Details

Everything it can hand back

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

  • The issue, ready to paste, with the subject line chosen and alternatives
  • A readiness score out of 100 with the ship or fix call
  • The main cuts, so you learn the pattern
  • A plan of the next 12 issues, each with a reader and a worry
  • Reader replies worth turning into future issues

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

  • Writing for "the audience". Pick the one person.
  • Burying the worry under a list of updates.
  • A subject line the issue does not deliver.
  • Adding an offer the writer did not ask for.
  • Generic copy that could fit any brand.
  • Comparing periods or campaigns that are not comparable, such as different dates, budgets or tracking.

What a good result looks like

An example, not your task: You send a weekly newsletter and the writing eats the day before it goes out.

  • The issue. The newsletter ready to paste, with the chosen subject line and the other options under it.
  • Who it is for. The one reader and their worry in a single line.
  • Score. A score out of 100, what it measured, and the ship or fix call.
  • What changed. The main cuts from the editor and the voice check, with the reason for each.
  • Topics left. How many planned issues remain and which topic is next.
  • Replies to read. Reader replies that could shape a future issue.

How the work is checked

  • The issue is for one named reader and opens with a moment, not a topic.
  • Every fact, number and claim comes from the notes or the brand brain.
  • The chosen subject line is true to what the issue says.
  • The score passed, or the loop stopped at three with the gaps 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 Ann Handley and George Orwell would. This is a way of reviewing the work. It does not mean they wrote or endorse it.

Capabilities

  • Check the topic plan. Keeps 12 issues ahead, each with one reader and one worry, and refills the list when it runs low.
  • Draft the issue. Writes from your notes for the named reader, opening with the moment you noticed and ending with a question.
  • Edit it plain. Cuts clutter, explains each cut, and removes any sentence that could appear in anyone else's newsletter.
  • Check the voice. Ranks off-voice lines against your brand brain and fixes them, leaving claims alone unless the brain backs them.
  • Write the subject lines. Three to five angles, the first naming the worry in the reader's words, all true to the issue.
  • Score it and loop. Scores the issue out of 100. A fix call sends it back to the editor, up to three times.
  • Log and hand back. Ticks the topic, records the score and stops. You send.

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 weekly-newsletter-keeper 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/weekly-newsletter-keeper/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

  • This week's notes, the moment you noticed and the one reader it is for
  • Your brand brain, for the voice check (advised)
  • Opens, clicks and replies from past issues (optional)
  • Reader replies from last week (optional)
  • Your topic plan, once it exists

Helpful context (optional)

  • Reader replies from last week, pasted as written
  • Opens and clicks per issue from your email tool

Tools and access

  • Claude Code: It can keep the topics and issues files between weeks and run every Thursday.
  • Any good chat AI: Paste the agent and your notes. Keep the topic plan in a note yourself.
  • 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: Claude, ChatGPT and Gemini all handle a one-message prompt like this well.

Functions and deliverables

  • Newsletter draft and subject editor: Turn your notes into one newsletter issue. Get plain copy, honest subject options and review gaps before sending.
    • The issue, ready to paste, with the subject line chosen and alternatives
    • A readiness score out of 100 with the ship or fix call
    • The main cuts, so you learn the pattern
    • A plan of the next 12 issues, each with a reader and a worry
    • Reader replies worth turning into future issues
  • Content topic planner: Describe your business. Get topic clusters, a content calendar and the pieces to write first.
    • Pillars and topic clusters
    • Keyword ideas by customer stage
    • Content calendar
    • First pieces to write, ranked
    Source: Corey Haines.
  • Marketing content drafter: Write a first draft of a blog post, social post, newsletter, landing page or press release. Marketing content drafter gives headline options too.
    • A full draft
    • Headline options
    • Platform-fitted formatting
    • Notes on voice used
    Source: Anthropic.
  • 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
  • Draft brand voice checker: Share a draft and voice guide. Get ranked findings and before-and-after edits for top issues.
    • Issues ranked High, Medium or Low
    • The reason each line was flagged
    • A before and after fix for the top issues
    • A separate list of legal and compliance flags
    • A short overall verdict
    Source: Anthropic.
  • Subject line writer: Write email subject lines that get opens and stay honest. Give it your email and audience. You get options in several angles, matched to your list.
    • Several subject lines, each in a different angle.
    • A short note on why each line might work.
    • A check that flags clickbait, creepy personalization and false urgency.
    • One suggested line to test first.
    Source: sickn33.
  • Email draft readiness checker: Share an email draft. Get counts, edits, three subject lines, a score out of100 and a send-or-fix verdict.
    • Counts for lead, length and subject
    • The draft marked with cuts and rewrites
    • A score out of 100, a verdict and three fixes
  • 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
  • Ann Handley: Write or revise an email, page or newsletter using Ann Handley’s public approach. Start with the reader’s concern and cut generic lines.
    • Your problem worked on the way Ann Handley would: their questions, their method, their push-back
    • The answer or the work, in Ann Handley's voice, using their ideas by name
    • Anything that goes beyond their public record, marked
    • One suggested next step
  • George Orwell: Rewrite a memo, report or announcement in plain words using George Orwell’s recorded approach. Cut padding and reveal what vague labels hide.
    • Your problem worked on the way George Orwell would: their questions, their method, their push-back
    • The answer or the work, in George Orwell'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 send a weekly newsletter and the writing eats the day before it goes out.
  • Your issues have started to sound generic and replies have dried up.
  • You have good notes every week and no time to shape them.

Limits to check before starting

  • You send one-off campaigns or have no regular send: use the Marketing content drafter to write the email.
  • You only want subject lines for an issue you already wrote: use the Subject line writer.
  • You want it to send or schedule the issue: it never does, so use your email tool and send it yourself.

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.

  • Start a chat with the agent. In Claude Code, add it as a skill or save it in .claude/agents, then ask it to write this week's issue.
  • Paste your notes for the week and name the one reader it is for. Attach your brand brain if you have one.
  • On the first run, approve the 12-issue topic plan. It saves it.
  • Read the issue. Change anything that is not you, then paste it into your email tool and send it yourself.
  • Next week, paste the replies and the open and click numbers. The plan learns from them.

Read it as data

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