Hire an AI research report and claim-source checker

Everything it can hand back

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

• A research outline with sub-questions and the evidence that would answer each
• A shortlist of sources with a note on each
• A report with a citation on every claim
• A check of every claim against its source, with fixes applied

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: A decision rests on a factual question and you want an answer you can defend.

• Step 1: Outline. Each sub-question, the evidence that would answer it, and what counts as a source for your reader.
• Step 2: Sources. A shortlist of sources per sub-question, with what each shows, how strong it is, and a link.
• Step 3: Report. An answer to each sub-question with a citation on every claim, plus where sources disagree and what is unknown.
• Step 4: Claim check. Each claim read against its source, marked supported or not, and kept, softened or cut.
• HAND-BACK SUMMARY. Each step's file, any step not run, and every MISSING line in one list.

How the work is checked

• Each sub-question says what evidence would answer it.
• Every source on the shortlist has a note on what it shows and how strong it is.
• The claim check covered the claims you most wanted to be true.
• The report says what is not known.
• 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

• Outline the question. Breaks the question into sub-questions and says what evidence would answer each.
• Find the sources. Searches scholarly and public databases per sub-question and shortlists sources with a note on each.
• Write the cited report. Writes the report with a citation on every claim, answering each sub-question in turn.
• Check every claim. Reads every claim against its source, flags what is not supported and fixes, softens or cuts it.

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 research-a-question-and-write-a-cited-report 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/research-a-question-and-write-a-cited-report/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 question, in your words
• What the answer is for and who will read it
• Sources you already have or trust (optional)
• Sources or kinds of sources to avoid (optional)

Helpful context (optional)

• Sources you already trust
• Your citation format
• Past reports on the topic

Tools and access

• Any good chat AI: Every step is a plan or a piece of writing.
• A reference manager: Holds the shortlisted sources and formats the citations.
• Scholarly databases: The search step works best with access to full texts.
• Any good chat AI: Plans in one message. Use a research mode afterwards to run the plan.

Functions and deliverables

• Research report and claim-source checker: Share your question, scope and source needs. Get an outline, source shortlist, cited report and a check of claims against sources.
  • A research outline with sub-questions and the evidence that would answer each
  • A shortlist of sources with a note on each
  • A report with a citation on every claim
  • A check of every claim against its source, with fixes applied
• Research question outliner: Turn a big research question into a clear plan. Get sub-questions, source types, search phrases and a test for when your research is done.
  • A sharper question
  • Ordered sub-questions with source types and search phrases
  • A test for when you are done
  • The likely trap
• Scholarly database searcher: Search PubMed, arXiv, OpenAlex and 15 more free sources for papers, citations and open full text. Every query is shown so you can repeat it.
  • A list of matching papers and preprints
  • Open access links where they exist
  • Citation data
  • The queries used, so you can repeat them
  Source: K-Dense.
• Cited research report writer: Ask a research question. Get a cited report with source quotes, claim checks and a run folder.
  • A cited report
  • Source list with checked quotes
  • A run folder with the audit trail
  • Claims that failed checks removed or flagged
  Source: ZhongHanLoo.
• Unsupported claim spotter: Find the claims in your draft that need a source before you publish. Each one is ranked by risk, with the kind of source to look for.
  • A summary of how many claims need support
  • A table of claims ranked by risk
  • The kind of source that would settle each
  • Internal conflicts in your draft
  Source: Pro Skill Packs.
• 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

• A decision rests on a factual question and you want an answer you can defend.
• You write for people who check sources.
• Your last report had a claim that turned out to be unsupported.

Limits to check before starting

• You want an opinion piece or a question with no evidence to cite: ask your AI for a plain summary instead.
• You only want a source search for one sub-question: use the Community evidence researcher.
• You already have a draft and only need its claims checked: ask your AI to check each claim against its source, without the full workflow.

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 question and what the answer is for. It outlines the research and searches for sources.
• Read the shortlist. Add sources you trust or strike ones you do not.
• Read the report and the claim check. Publish or file the corrected version.

Read it as data

Read the complete role setup as JSON. Connect your AI to the AI Blocks MCP library and read aiblocks://roles/research-a-question-and-write-a-cited-report 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.