Hire an AI journal paper draft writer

Everything it can hand back

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

• A packet of current sources with links, competing findings and gaps
• A manuscript draft with the source of each claim tracked
• A fair review of what is strong, what is weak and what to fix next
• The paper fitted to the journal's current limits, sections and style, with the date checked

How it does the job well

• Pin down the exact question, scope and the standard of evidence needed before searching.
• Prefer primary sources, and say how strong each source is.
• Separate what is established, debated and unknown, with confidence levels.
• Cite specifically: author, work, date or page where possible.

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: You have results and need a first manuscript fast.

• Source packet. Current papers with links, competing findings, background and the gaps in the search.
• Manuscript draft. Each section written from the sources and your results, with the source of each claim and a reference check.
• Review. What is strong, what is weak and what to fix next, written about the work and not the author.
• Journal fit. The paper fitted to the journal's current rules, with the date checked and items still to fix.
• HAND-BACK SUMMARY. Each step's file, any step not run, 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. Step 2 used step 1's packet, step 3 read step 2's draft, and step 4 used the revised paper, not the review.
• The draft has no citation or number that is not in a source or in your results.
• Nothing was invented to fill a gap. Every gap is a MISSING: line.
• 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.

Capabilities

• Gather the sources. Collects current papers, competing findings and background for your topic, keeps the link for each and notes the gaps in the search.
• Draft the manuscript. Writes each section from the sources and your results only. It tracks the source of each claim, flags gaps against reporting guidelines and checks the references.
• Review the draft. Reads the draft as a fair reviewer would. Lists what is strong, what is weak and what to fix next, with comments about the work and not the author.
• Fix the draft and pick the journal. Fix what the review found and rerun your analysis where it asks. Then name the journal or conference and bring the revised paper back.
• Fit the paper to the journal. Uses your revised paper, not the review report. Opens the official author instructions, records the date checked, then checks page limits, required sections, anonymity and citation style and fits the paper to them.

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-a-paper-review-it-and-fit-your-journals-rules 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-a-paper-review-it-and-fit-your-journals-rules/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 topic and the claims you want to support
• Your results or data tables (optional)
• Your notes on methods
• The journal or conference you aim for, after the review

Functions and deliverables

• Journal paper draft writer: Gather sources, draft from your real results and review the paper. After revision, check its format against the chosen journal's rules.
  • A packet of current sources with links, competing findings and gaps
  • A manuscript draft with the source of each claim tracked
  • A fair review of what is strong, what is weak and what to fix next
  • The paper fitted to the journal's current limits, sections and style, with the date checked
• Manuscript evidence gatherer: Name your paper topic. Get a linked research packet with relevant findings, competing evidence and a claim-to-source map.
  • Around 60 checked references
  • An evidence table by claim
  • Contradicting findings
  • Retraction flags
  • Research gaps
  Source: K-Dense.
• Scientific manuscript drafter: Give it your results and notes. Get manuscript sections with sources tracked, guideline gaps flagged and references checked.
  • Drafted manuscript sections
  • A list of missing or unverified details
  • A guideline gap report
  • A reference check
  • A trail from each claim to its source
  Source: K-Dense.
• Scholarly work reviewer: Get a fair, evidence-based review of your paper, thesis or research idea. See what is strong, what is weak and what to fix next, with no verdict.
  • Strengths and weaknesses with evidence
  • Next steps to improve the work
  • Optional rubric notes with limits stated
  • A check of an assessment process (optional)
  Source: K-Dense.
• Journal submission formatter: Name the venue, year, track and stage. Check its official guide, then fit your paper to confirmed rules.
  • The official rules with source links and date checked
  • A paper fitted to confirmed format rules
  • A page and font check on the PDF
  • Writing tips for that venue's reviewers
  Source: K-Dense.
• 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
  Source: Orchestra Research.

Tasks you can use it for

• You have results and need a first manuscript fast.
• Your draft has claims with no sources behind them.
• You are about to submit and are unsure of the journal's rules.

Limits to check before starting

• Your paper is finished and only needs copy-editing: use a person who edits, or ask your AI to fix wording alone.
• You only need the paper fitted to a journal's rules: use the Journal submission formatter on its own.
• You cannot share your data or notes with an AI tool: write the draft yourself and bring only summaries.

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".
• Give the topic, your results and your methods notes. Do not paste data you may not share.
• After the review, fix the weak parts and rerun any analysis it asks for.
• Name the journal, the year and the article type 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/draft-a-paper-review-it-and-fit-your-journals-rules 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.