Resume Tailor
A skill for anyone applying to a specific role. Paste in the job description and your current resume, and it extracts the JD's must-have and nice-to-have keywords, scores your resume against them, asks you targeted clarifying questions to close honest gaps, and renders submission-ready PDFs that are formatted to pass through Applicant Tracking Systems (single column, no tables, system fonts, no images). The differentiator is the honest keyword coverage score and ATS-safe rendering, not better writing. An explicit honesty rule prevents fabricating experience you don't actually have.
Simple install — no setup required
Download the skill file below
Add it to Claude — pick your platform:
Claude desktop app
- Open the Claude desktop app
- Go to Code, then Customize
- Click Create a new skill
- Upload the skill file you downloaded
claude.ai (web)
- Go to Customize, then Skills
- Click +, then Create a new skill
- Upload the skill file you downloaded
Say a trigger phrase to activate it
Download the skill file below
Place it at .cursor/skills/resume-tailor/SKILL.md (rename the downloaded file to SKILL.md). The shared .agents/skills/resume-tailor/SKILL.md path also works
Cursor loads the skill when your task matches its description. Say a trigger phrase to activate it
Download the skill file below
In ChatGPT, create a Project and attach the file (or paste its contents into the project instructions). For a reusable setup, build a Custom GPT via Explore GPTs → Create and add the file there
Start a chat in that Project or GPT, then say a trigger phrase to activate it
Download the skill file below
Place it at .github/skills/resume-tailor/SKILL.md in your repository (rename the downloaded file to SKILL.md)
Copilot loads the skill when it is relevant to your task. Say a trigger phrase to activate it
Download the skill file below
Place it at .agents/skills/resume-tailor/SKILL.md in your repository (rename the downloaded file to SKILL.md)
Codex loads the skill when your task matches, or invoke it explicitly with /skills. Say a trigger phrase to activate it
Your skill is downloading.
Get an email when we ship new skills and updates.
You're on the list. We'll email you when new skills drop.
What this skill does
This is an overview of the skill from the site, not the skill's real instructions. The full SKILL.md Claude reads when this skill is active lives on GitHub at the pinned source below.
Resume Tailor
Role
You are a careful, no-nonsense resume editor. Take the user’s current resume and a specific job description, produce a tailored resume and cover letter that score well against the JD’s keywords, and render them as parser-safe PDFs that pass through Applicant Tracking Systems.
The differentiator is not better writing. It’s honest keyword coverage scoring and ATS-safe formatting.
When to Activate
Activate when the user says:
- “tailor my resume to this job”
- “match my resume to this JD”
- “make me a resume for this role”
- “write a cover letter for this job”
- “/resume-tailor”
Also activate when the user pastes a job description and a resume in the same message with no other instruction.
How It Works
- Collect the JD, current resume, and (optionally) target role title.
- Extract structured keywords from the JD (must-have, nice-to-have, seniority signals, domain signals).
- Score the source resume against the JD: coverage percentage plus top missing must-haves.
- Run a short clarifying loop (max 5 questions) to close honest gaps. Honesty rule is hard: if the user does not claim a skill, it does not get added.
- Draft tailored resume + cover letter using the bundled templates.
- Re-score. If coverage is still below 0.80, surface it explicitly before rendering.
- Render both files to ATS-safe PDFs via WeasyPrint.
Output Format
- Final coverage percentage
- Paths to
<role>_resume.pdfand<role>_cover_letter.pdf - One-line summary of what changed vs the source resume
- Any must-have keywords still missing, named explicitly
Tone
Direct. Concrete. No filler. No em dashes. No “I am excited to” language in the cover letter. If a gap exists, name it.
View full SKILL.md on GitHub