This is taking longer than expected.

Try againBrowse the library
AI Blocks

All AI specialists

Hire an AI resume parsing checker

Check your resume for what hiring software may miss. Get a score out of 100, layout and keyword gaps and bullet fixes. Paste your resume.

What you give

  • Your resume. Paste the text, or attach the PDF or Word file
  • The job post you are applying to (optional, but keywords are checked against it)
  • The job title you are aiming for (optional)

What you get

  • A score out of 100 with its four-part split and a grade from A to D
  • Layout checks marked Pass, Warn, Fail or Not checked, each with a fix
  • Keywords found, keywords missing that you can add if true, and keywords not to claim yet
  • A table of weak bullets with rewrites that use only your facts

An example

You apply to many jobs and hear nothing back.

You ask: “Check your resume for what hiring software may miss. Use the material I attach and ask for anything essential that is missing.”

You get back:

  • Score card. Your score out of 100, the four-part split, a grade and the main finding for each part.
  • Layout checks. Text layer, characters, reading order, headings, contact details and tables, each marked Pass, Warn, Fail or Not checked.
  • Keyword gap list. Terms found, terms missing that you can add if true, and terms not to claim without proof.

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: Prepare job applications

Details

Everything it can hand back

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

  • A score out of 100 with its four-part split and a grade from A to D.
  • Layout checks marked Pass, Warn, Fail or Not checked, each with a fix.
  • Keywords found, keywords missing that you can add if true, and keywords not to claim yet.
  • A table of weak bullets with rewrites that use only your facts.
  • A short prompt you can paste into another AI to rewrite the weak bullets.

How it does the job well

  • Never invent a metric, tool, employer, title, date, degree or result. If a result would help but was not given, ask for it or mark a gap.
  • Never suggest hidden text or keyword stuffing, and never promise an interview, offer or that a system will pass the resume.
  • The score is a guide from fixed rules, not what a real hiring system will give. Say this once at the end.
  • This is not legal advice or a bias audit. If the user is building or buying hiring software, say a bias audit needs an independent expert.
  • Read the existing code, its conventions and its tests before changing anything. Match the project's patterns.
  • Make the smallest change that fully solves the request. Keep unrelated refactors out.
  • Reproduce a bug before fixing it, and add a test that fails without the fix.

Mistakes it avoids

  • Claiming code works without running it or its tests.
  • Inventing APIs, package versions or settings instead of checking the installed ones.
  • Changing behaviour outside the request, such as reformatting whole files or renaming public interfaces.

What a good result looks like

An example, not your task: You apply to many jobs and hear nothing back.

  • Score card. Your score out of 100, the four-part split, a grade and the main finding for each part.
  • Layout checks. Text layer, characters, reading order, headings, contact details and tables, each marked Pass, Warn, Fail or Not checked.
  • Keyword gap list. Terms found, terms missing that you can add if true, and terms not to claim without proof.
  • Bullet fixes. Each weak bullet, what is missing from it and a rewrite built only from your facts.
  • Hand-off prompt. A paste-ready prompt for another AI to rewrite your weak bullets without inventing results.

How the work is checked

  • The changed files build, and the relevant tests and linters pass. The commands and results are shown.
  • Each change is explained in one line with its reason, and risky areas are named.
  • Any check that could not run is reported as NOT_RUN with what it needs.
  • 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 text. It confirms your file holds real text, not a picture, and looks for broken characters that make words unsearchable.
  • Check the layout. It looks for a single reading order, standard headings, no tables or floating text boxes, and clean contact details.
  • Map the keywords. It lists the skills and tools in the job post, marks which your resume has, and marks the rest as gaps you must verify.
  • Score each bullet. Each bullet scores on action and scope, a measured result and the method used. Duty wording and vanity numbers lose points.
  • Add up the score. It combines the four parts, shows every deduction and writes a hand-off prompt for the rewrite.

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 engineering-ats-validator-architect 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/engineering-ats-validator-architect/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 resume. Paste the text, or attach the PDF or Word file.
  • The job post you are applying to (optional, but keywords are checked against it).
  • Your level, such as junior, mid, senior or executive, or your years of experience.
  • The job title you are aiming for (optional).

Helpful context (optional)

  • The full job post, not a summary, so keywords are exact.
  • Real numbers behind your work, such as sales, time saved or users.
  • The Word version of your resume as well as the PDF.

Tools and access

  • Claude, ChatGPT or Gemini with file upload: They can open your PDF, so layout and font checks run instead of saying Not checked.

Functions and deliverables

  • Resume parsing checker: Check your resume for what hiring software may miss. Get a score out of 100, layout and keyword gaps and bullet fixes. Paste your resume.
    • A score out of 100 with its four-part split and a grade from A to D.
    • Layout checks marked Pass, Warn, Fail or Not checked, each with a fix.
    • Keywords found, keywords missing that you can add if true, and keywords not to claim yet.
    • A table of weak bullets with rewrites that use only your facts.
    • A short prompt you can paste into another AI to rewrite the weak bullets.
    Source: Michael Sitarzewski and Agency Agents contributors.
  • Resume and job application builder: Share real experience and a job post. It maps evidence to role needs and drafts a tailored resume and letter without adding unsupported claims.
    • A master profile that stores every role, bullet, metric and skill you have
    • A tailored resume, single column and easy for tracking systems to read
    • A PDF or Word file with text you can select, if your AI can run Python
    • A labeled estimate of keyword coverage
    • A truthfulness check against your source
    • A cover letter or LinkedIn advice, when you ask
    Source: João Vitor Amaral.
  • Resume layout editor: Fix your resume layout so hiring software and recruiters can read it. Get a formatting review with clear fixes for fonts, spacing and sections.
    • A list of specific layout fixes.
    • Recommended type, spacing and section order.
    • A final readability and file-format checklist.
    Source: Daniel (San) Ávila.
  • Product manager resume reviewer: Check your product manager resume against ten rules. Get fixes from your own bullets and a draft tailored to the job you want.
    • Feedback on ten best practices
    • Rewritten bullets using your own work
    • Keyword gaps against the posting
    • A tailored resume version
    Source: Pawel Huryn.
  • AI project context organiser: Share your project and next task. Get a short rules file, a focused file list and a clear handoff for later sessions.
    • A ready rules file for your project
    • A list of which files to load for each task
    • Rules for when to reset or trim the session
    • A checklist for spotting drifting answers
    Source: Addy Osmani.

Tasks you can use it for

  • You apply to many jobs and hear nothing back.
  • You use a two-column or designer resume template and worry it will not read properly.
  • You want to know which words in the job post your resume lacks, and which you can truthfully add.
  • Your bullets say "Responsible for" and you want them to show results.

Limits to check before starting

  • You want the whole resume rewritten for one job. Use the Resume editor.
  • You want a cover letter as well. Use the Resume and job application builder.
  • You want the look of your resume fixed, such as fonts and spacing. Use the Resume layout editor.
  • You are building or buying hiring software and need a bias audit. This check is not a legal or independent audit.

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.

  • Add the pack to your AI as a skill. In a plain chat, paste SKILL.md first.
  • Paste your resume text and the job post. Say your level.
  • For layout and font checks, attach the PDF and use an AI that can open files. Without it those checks say Not checked.
  • Say "Run the ATS check." Your AI asks once for anything missing.
  • Fix layout failures first. Then add missing keywords you can honestly claim. Then rewrite the weak bullets.
  • Run it again on the new version to see the score move. Save the final file as Firstname_Lastname_Resume_Year.pdf.

Read it as data

Read the complete role setup as JSON. Connect your AI to the AI Blocks MCP library and read aiblocks://roles/engineering-ats-validator-architect 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.