Hire an AI scholarship application editor

Everything it can hand back

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

• An evidence map: each rule and claim matched to a record, or marked MISSING
• A list of claims with no support, such as an award, a rank or a date
• A revised draft within the word limit, in your voice, with no new facts
• A missing documents list: what to get, which claim it backs and who can supply it
• A hand-back summary with one next step

How it does the job well

• Never invent an award, ranking, date, hardship, identity detail or personal history. A gap stays a gap.
• Keep only the identity details the check needs. Leave out ID numbers, full birth dates, addresses and the names of other people. Write "a teacher" instead of a name.
• Keep the applicant's voice. Do not add claims. Keep the original draft intact and save the revision under a new name.
• 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 have a draft essay and the scholarship asks for proof of grades, awards or service

• Evidence map. Each rule and claim matched to a record, with a status of backed, partly backed or MISSING.
• Unsupported claims. Achievements, ranks and dates with no record, and whether to cut, soften or back each one.
• Revised draft. Your draft polished inside the word limit, in your voice, with no new facts.
• Missing documents list. Each document to get, the claim it backs and who can supply it.
• Hand-back summary. Files saved, MISSING facts, checks not done and one next step.

How the work is checked

• Every claim in the revised draft is backed by a record, or is softened or cut.
• No award, rank, date or personal detail was added.
• The word count is inside the limit.
• No qualification ruling was given.
• 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 Anne Lamott and William Zinsser would. This is a way of reviewing the work. It does not mean they wrote or endorse it.

Capabilities

• Source note summariser. Matches each eligibility rule and each claim to a record you gave it, and marks gaps. It keeps only the identity details the check needs and hands on the evidence map.
• Unsupported claim spotter. Finds achievements, ranks, dates and personal claims in the draft that no record supports. It hands on the claims to cut, soften or back with a document.
• Proofreader. Polishes the real draft inside the word limit, in your voice. It adds no fact and hands back the revised draft.

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 check-scholarship-application-evidence 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/check-scholarship-application-evidence/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 application draft or essay
• The funder's eligibility rules and word limit, copied from their page
• The records that back your claims, such as transcripts, award letters and activity lists. Share only what you may share, and leave out ID numbers
• The official deadline (optional)
• Parts of the draft you want left as they are (optional)

Helpful context (optional)

• The funder's rules page, saved as a file or pasted in full.
• A teacher or advisor who can check the revised draft is true to you.

Tools and access

• Claude, ChatGPT or Gemini with file support: They read your draft and records and keep each step's result as a file. None of them can confirm your record with the school or the funder.
• Any good chat AI: Claude, ChatGPT and Gemini all handle a long source in one message. Claude takes the longest texts.

Functions and deliverables

• Scholarship application editor: Match a scholarship draft to the rules and your records. Get a polished draft, unsupported claims and missing documents.
  • An evidence map: each rule and claim matched to a record, or marked MISSING
  • A list of claims with no support, such as an award, a rank or a date
  • A revised draft within the word limit, in your voice, with no new facts
  • A missing documents list: what to get, which claim it backs and who can supply it
  • A hand-back summary with one next step
• Source note summariser: Paste an article, talk or chapter into this source note summariser. You get each claim, how well it is backed, the gaps and three quotes to keep.
  • Every claim with a quote and location, and the evidence behind each rated
  • The gaps and assumptions
  • What it adds to your question, three quotes to keep, and an 80-word summary
• 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.
• Text proofreader: Proofread your text for grammar, spelling and punctuation against a style guide. Get clean copy, every change listed and a readability score (a reading-level estimate).
  • Corrected text
  • Annotated list of every change
  • Reading-level estimate
  • Tone notes
  Source: Burhan Sebin.
• 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
• Anne Lamott: Start a draft or project you keep avoiding using Anne Lamott’s recorded approach. Pick one small piece and let the first version be rough.
  • Your problem worked on the way Anne Lamott would: their questions, their method, their push-back
  • The answer or the work, in Anne Lamott's voice, using their ideas by name
  • Anything that goes beyond their public record, marked
  • One suggested next step
• William Zinsser: Edit nonfiction using William Zinsser’s recorded approach. Find the point, order what readers need and cut words that add no meaning.
  • Your problem worked on the way William Zinsser would: their questions, their method, their push-back
  • The answer or the work, in William Zinsser'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 have a draft essay and the scholarship asks for proof of grades, awards or service
• You are not sure your draft shows that you meet each rule on the funder's page
• A teacher, parent or advisor is helping and wants to see what is backed by documents
• The deadline is close and you need to know which documents to chase first

Limits to check before starting

• You need a ruling on whether you qualify. Only the funder decides. Read their official rules or ask them.
• You are writing a grant for an organisation, not a scholarship for a person. Use the Nonprofit grant proposal writer.
• You only want a grammar pass on your text. Use the Proofreader.
• You are checking claims in an article or ad. Use the Unsupported claim spotter.

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. The site builds it as a zip with HANDOFF.md and every skill file this workflow uses. If you cannot download it, paste the steps from this page into your AI in order.
• Give the folder to Claude, ChatGPT or Gemini and say "Follow HANDOFF.md".
• Paste your draft and the funder's rules. Add your records. Remove ID numbers and anything private you do not need to share.
• Read the evidence map first. Every MISSING row is a document to find or a claim to cut.
• Read the revised draft against your own story. Change anything that is not true to you. Then check the funder's rules yourself before you submit.

Read it as data

Read the complete role setup as JSON. Connect your AI to the AI Blocks MCP library and read aiblocks://roles/check-scholarship-application-evidence 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.