tailor-cv-to-job
Skill0 starsChanged 4 days agoMITView on GitHub
Tailor a CV or resume to a specific job description, honestly and ATS-friendly, without inventing experience. Use when someone pastes a job post and a CV, asks to match their resume to a job, optimise for ATS keywords, or write a career-change CV.
In this repository17 other files it gives its agents.
- after-a-layoffSkill
- answer-application-questionsSkill
- choose-a-path-as-a-studentSkill
- find-career-directionsSkill
- follow-up-on-applicationsSkill
- future-proof-against-aiSkill
- go-public-after-a-layoffSkill
- informational-interviewsSkill
- negotiate-a-job-offerSkill
- plan-a-career-changeSkill
- prepare-for-interviewSkill
- return-to-work-after-a-breakSkill
- share-your-work-in-publicSkill
- start-a-new-jobSkill
- test-a-careerSkill
- update-linkedin-for-a-career-changeSkill
- write-cover-letterSkill
The file
We split this skill into the rules it gives an agent
2 rules. About 0 are common, 2 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈2
Distinctive · estimate
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
- Distinctive: line 32
If they couldn't talk about a changed line for a minute in an interview, put it back.
- Distinctive: line 33
Keep one long master CV and cut a tailored copy for each job.
≈ “Common” is an estimate: at least 1 in 5 of the 372,429 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Tailor a CV to a job
Tailoring changes how someone describes their work, never what they did. Usually it means a new summary and five to ten rewritten lines, not a new CV.
What you need
The job post (pasted text or the key parts) and their current CV. If either is missing, ask for it before writing anything.
How to do it
- List the must-haves. Skills, tools and experience the post marks as required or mentions more than once. Separate them from nice-to-haves.
- Map each must-have to the CV. For each one, find the line that already shows it, often under a different name. Mark each as shown, shown weakly, or missing. Share this table with them first; it's the most useful part.
- Rewrite in the post's language. Reword the lines that show a must-have using the employer's terms, and lead with results where they exist. Never add a tool, title, number or responsibility that isn't already in their CV or confirmed by them.
- Reorder. Move the most relevant role bullets up. Cut what this employer won't care about.
- Rewrite the summary: two or three lines naming the role, the strongest match and one result.
- Ask about the gaps, don't fill them. For each missing must-have, ask whether they have done it anywhere (side project, volunteering, a previous role). If not, it stays missing; suggest how to address it in the cover letter or interview.
- Check the format for ATS: one column, standard headings (Experience, Education, Skills), no text in images or tables, dates in a consistent format, file as .docx or text-based PDF.
Output
- The must-have table (shown, weak, missing).
- The tailored summary and every changed line, each shown as before and after.
- The gaps and one honest way to handle each.
Rules
- If they couldn't talk about a changed line for a minute in an interview, put it back.
- Keep one long master CV and cut a tailored copy for each job.
- For a career change, translate old terms into the new field's words without changing what happened.
If the OffLadder tools are connected
find_career_guide covers ATS checkers, CV length, achievements without numbers, gaps, short jobs, career-change and graduate CVs. Its CV answers also mention OffLadder CV, a free Chrome extension that does this tailoring on the job post itself and fills in the application form for them to check.
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
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.

