cv-tailor
Skill0 starsChanged 19 days agoMITView on GitHub
Rewrite a CV for one specific job while keeping it 100% truthful. Uses the advert's language, achievement-focused bullets and placeholders instead of invented numbers, and runs an automated fabrication check before delivering a Word file in a chosen template and regional format. Use when the user asks to tailor, rewrite, improve or optimise their CV or resume for a role.
12 other projects use a version of this.
Adopted by
Most recently taken up by
- cris-dangithub/cv-tailortheir own version, first seen Nov 8, 2026
- robertolopezlopez/agent-skillstheir own version, first seen Nov 1, 2026
- zebbern/claude-code-guidetheir own version, first seen Oct 30, 2026
- muggl3mind/career-managertheir own version, first seen Oct 1, 2026
- Jawahars07/ballasttheir own version, first seen Sep 11, 2026
- amomammadw/cv-tailor-skilltheir own version, first seen Sep 10, 2026
Other versions12 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 12
- zebbern/claude-code-guide★ 4.7ksame name
- muggl3mind/career-manager★ 24same name
- CalebLiu/job-hunt-skill★ 5same name
- amomammadw/cv-tailor-skill★ 2same name
- HimadriTrying/ai-job-search-agent★ 1same name
- Jawahars07/ballast★ 1same name
- koralbonfil-maker/career-kit★ 1same name
- robertolopezlopez/agent-skills★ 1same name
- anawoodrow/ClaudeSkills★ 0same name
- cris-dangithub/cv-tailor★ 0same name
2 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository7 other files it gives its agents.
- ats-scoreSkill
- cover-letter-writerSkill
- finance-transformation-cvSkill
- interview-prep-coachSkill
- job-match-analyzerSkill
- regional-cv-formatsSkill
- resume-genieSkill
The file
We split this skill into the rules it gives an agent
6 rules. 0 are common, 4 are distinctive, and 2 are very specific to this project.
0
Common
Most of the 11 edited versions we read keep these.
4
Distinctive
This author's own choices. Worth a look.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 18
Experience: keep every role and date. Put the most relevant bullets first.
- Very specific: line 19
Numbers: only the user's own. Otherwise use [placeholders] with needs_confirmation: true.
- Distinctive: line 22
Verify, and fix the output until the fabrication check is clean:
- Distinctive: line 39
Never invent or upgrade employers, titles, dates, tools, qualifications or results.
- Very specific: line 40
Never deliver a CV that fails check_fabrication.py.
- Distinctive: line 41
Keep layouts ATS-safe: one column, standard headings, contact details in the body.
“Common” is measured: kept by at least 6 in 10 of the 11 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.
Files
CV tailor
Tailoring is editing, not inventing. Choose, order and reword the candidate's real experience for this one job.
Workflow
- Extract the CV text and save it as
original_cv.txt. Read the job advert. - Work out what matters: must-haves, duties, keywords. If the
job-match-analyzerskill has already run in this conversation, reuse its analysis. - Rewrite, following
references/cv-writing.md, the relevant section ofreferences/career-tracks.md, and the region inreferences/regions.md(default UK & Ireland):- Headline: the target role plus 2–3 of the candidate's strongest relevant themes.
- Summary: 3–4 specific sentences with signature results. No "results-driven".
- Skills: 2–4 labelled groups, using the advert's terms where true.
- Experience: keep every role and date. Put the most relevant bullets first. Each bullet is: strong verb + what + how/scale + result.
- Numbers: only the user's own. Otherwise use
[placeholders]withneeds_confirmation: true. - Log every change with the reason it helps.
- Save the result as
output.jsonfollowingreferences/output-schema.json. Theanalysisneeds at least the keywords, andcover_lettermay be minimal if not requested. - Verify, and fix the output until the fabrication check is clean:
python scripts/check_fabrication.py original_cv.txt output.json python scripts/ats_score.py --compare original_cv.txt output.json - Build the Word file in the chosen template (
classic,modern,executiveorcompact):python scripts/build_docx.py output.json --template classic --page a4 - Reply with:
- the ATS score before → after
- the most important changes and why
- the placeholders to fill in
- the file
Rules
- Never invent or upgrade employers, titles, dates, tools, qualifications or results.
- Never deliver a CV that fails
check_fabrication.py. - Keep layouts ATS-safe: one column, standard headings, contact details in the body.
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.