Hire an AI research paper peer-review drafter

Everything it can hand back

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

• A claim check: every claim against the results, with the ones that overreach flagged
• A methods and writing review
• A drafted peer review with summary, major and minor points and a recommendation
• The review rewritten to be specific and kind

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: An editor has sent you a manuscript and a deadline.

• Step 1: Claim check. Each claim from the abstract and discussion set against the results, with claims that go further than the data flagged.
• Step 2: Methods and writing review. Design, analysis, novelty, missing literature and writing, with anything outside your judgement marked.
• Step 3: Draft review. A summary, major points, minor points and a recommendation, each tied to a page or figure.
• Step 4: Final review. Every comment rewritten to be specific and kind, so the authors know what to change.
• Hand-back summary. Each step's file, any step not run and why, 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, and each one used the result of the one before.
• 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.

Capabilities

• Check the claims. Reads every claim against the paper's own results and flags the ones that go further than the data.
• Review methods and writing. Reviews design, analysis, novelty, missing literature and writing, leaving out what you said you cannot judge.
• Draft the review. Drafts the review with a summary, major and minor points and a recommendation, each tied to a page or figure.
• Make it specific and kind. Rewrites each comment so the author knows exactly what to change, in a tone you would use to a colleague.

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 review-a-paper-and-write-a-fair-peer-review 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/review-a-paper-and-write-a-fair-peer-review/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

• The manuscript, including figures and tables as text
• The journal's review form or criteria, if there is one (optional)
• Your field and what you can and cannot judge

Helpful context (optional)

• The trial registration, if there is one
• The reporting guideline for this study type
• Your past reviews for the same journal

Tools and access

• Any good chat AI: Every step is a plan or a piece of writing.
• The journal's reviewer system: Where the final review and the confidential note go.

Functions and deliverables

• Research paper peer-review drafter: Share the manuscript, review rules and your expertise limits. Get claim checks, methods findings and a specific, source-linked peer-review draft.
  • A claim check: every claim against the results, with the ones that overreach flagged
  • A methods and writing review
  • A drafted peer review with summary, major and minor points and a recommendation
  • The review rewritten to be specific and kind
• Study and claim evidence reviewer: Share a study or claim. Get a review of its design, bias, statistics and limits.
  • A list of biases and confounders
  • Notes on weak or misused statistics
  • An evidence-strength grade
  • A plain-language verdict
  • Questions to ask the authors
  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.
• Manuscript peer review drafter: Share a paper or proposal. Get a fair, evidence-based review with claim checks, method critique and revision steps.
  • A claim-by-claim check
  • A critique of methods and statistics
  • Strengths and weaknesses
  • Ranked revision requests
  • A confidentiality checklist
  Source: K-Dense.
• Code review comment editor: Turn code review comments into direct feedback with clear locations, concrete problems, and suggested fixes.
  • Rewritten comments with line number, label, problem and fix
  • Severity labels for each
  • A shorter review that is easier to act on
  Source: sickn33.
• 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

• An editor has sent you a manuscript and a deadline.
• You want to catch the claim that overreaches, which is the one that gets quoted.
• Your past reviews were called harsh or vague.

Limits to check before starting

• You have a conflict of interest with the paper or its authors: tell the editor and decline the review.
• You are checking your own manuscript before you send it: use the Unsupported claim spotter instead.
• The journal bans putting manuscripts into AI tools: check its confidentiality rules first, or review by hand.

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 the manuscript and the journal's criteria. It checks the claims and reviews the methods.
• Read the draft review. Remove any point you cannot stand behind and add what you saw yourself.
• Read the kind version once more and submit it.

Read it as data

Read the complete role setup as JSON. Connect your AI to the AI Blocks MCP library and read aiblocks://roles/review-a-paper-and-write-a-fair-peer-review 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.