agentleFS
HaroonArshad-53HaroonArshad-53/skills-for-everyone/skills/resume-builder/SKILL.md

resume-builder

Skill1 starsChanged 32 days agoMITView on GitHub

Build an ATS-friendly resume or CV from messy notes, an old resume, or a LinkedIn profile, tailored to a specific job description when one is provided, without inventing experience. Use when a user asks to make, fix, update, or tailor a resume or CV, or to match their resume to a job post.

27 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

4 rules. 0 are common, 4 are distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 18 edited versions we read keep these.

  • 4

    Distinctive

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Run the final checklist: contact details present, dates consistent, file named Firstname-Lastname-Resume.pdf, one consistent tense, no …

    line 19
  2. Distinctive:

    Never invent a job, degree, certification, date, tool, or metric.

    line 22
  3. Distinctive:

    Keep the user real voice in the summary - professional and specific, not dynamic, passionate, result-oriented individual.

    line 24
  4. Distinctive:

    Before you send - filename + 3-point final checklist

    line 31

“Common” is measured: kept by at least 6 in 10 of the 18 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Resume Builder

When to use this skill

  • Making a first resume from scattered notes
  • Tailoring a resume to a specific job description
  • A resume gets no replies and needs an honest audit

Workflow

  1. Collect the raw material: education, jobs and internships with dates, projects, skills, certifications. Ask for the target job description if one exists - tailoring beats generic.
  2. Audit honesty first: list every claim that needs proof (numbers, titles, tools). Anything the user cannot back up in an interview gets softened to the true version or removed.
  3. Structure for ATS: standard headings (Summary, Experience, Projects, Skills, Education, Certifications), no tables, no graphics, no text in headers or footers, job-title keywords from the target description used only where they are true.
  4. Rewrite bullet points as Action + Task + Result. Where no number exists, use a true scope word (team size, number of users, frequency) instead of inventing a percentage.
  5. Order for the reader: fresh graduates lead with Projects and Skills, experienced users lead with Experience. Certifications with exact names and dates as issued.
  6. Run the final checklist: contact details present, dates consistent, file named Firstname-Lastname-Resume.pdf, one consistent tense, no spelling errors, nothing the user cannot explain line by line.

Rules - never break these

  • Never invent a job, degree, certification, date, tool, or metric. This rule has no exceptions - a caught lie ends candidacies.
  • Keywords from a job description are used only where the user real experience matches. Keyword stuffing a false skill is inventing experience.
  • Keep the user real voice in the summary - professional and specific, not dynamic, passionate, result-oriented individual.
  • Two pages maximum for early-career users unless their real experience genuinely needs more.

Output format

  • The resume - clean, ATS-structured text ready to paste into a document
  • Tailoring notes - which keywords from the job post were matched, and where
  • Honesty audit - claims softened or removed and why
  • Before you send - filename + 3-point final checklist

Example

User: Make my resume from these notes and tailor it to this SOC analyst job post. Notes and job post pasted by the user.

Good output (excerpt): Bullet rewritten truthfully: before - Responsible for security monitoring. After - Monitored sign-in and endpoint alerts during internship shifts; escalated 2 confirmed phishing incidents to the senior analyst with evidence preserved. No metric invented; scope and action made it strong.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.