designed-cv-tailor
Skill0 starsChanged 41 days agoMITView on GitHub
Tailor a designed, photo-style CV (an HTML template) to one job and export a sharp, ATS-safe 2-page PDF. Use when someone shares a job link and wants their designed CV customised for it.
- Installs packages
In this repository13 other files it gives its agents.
- banner-designSkill
- brandSkill
- designSkill
- design-systemSkill
- slidesSkill
- ui-stylingSkill
- ui-ux-pro-maxSkill
- application-humanizerSkill
- application-packSkill
- creator-contract-reviewSkill
- creator-shortlistSkill
- job-scoutSkill
- linkedin-carouselSkill
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 23
Never claim an unsupported phrase.
- Distinctive: line 28
Look for words glued across line breaks (e.g.
≈ “Common” is an estimate: at least 1 in 5 of the 364,980 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
Designed CV tailor
Designed CVs (photo, sidebar, big name) impress humans but often break applicant tracking systems: text in the wrong reading order, text inside images, words glued together. This skill keeps the design and fixes the machine side. Facts never change between jobs; only emphasis, wording and order do.
Inputs
- The job link or text (fetch it from the official ATS).
cv.html: the CV as an HTML template with real text. Fonts installed locally (e.g.npm i @fontsource/<font>).facts.md: a table of roles, organisations and dates, plus education, proof points, tools and languages. This is the only source of facts.
Tailoring
- Pull 10-15 exact phrases from the job ad. Mark each as supported or not by
facts.md. - Edit
cv.html:- Kicker line under the name: mirror the job family.
- Profile (max ~65 words): years, scope, one standout proof point, one AI line if true.
- Skills: 12-13 items, job-ad terms first, only supported ones.
- Bullets: reword toward the job's language using only verified facts; 3-4 bullets for recent roles, 1 for older ones.
- Page 2 "Role fit" table: 5-6 rows mapping the job's main requirements to proof.
- Never claim an unsupported phrase. List it in the reply as a gap instead.
Build and check
- Render with headless Chromium to A4 PDF. No section may overflow its box; exactly 2 pages.
pdftotext -raw: must read in order (header, profile, skills, experience, education, page 2). Never position text absolutely; it scrambles the reading order.- Look for words glued across line breaks (e.g. "problemsolving") and rephrase.
- Render both pages to PNG and look at them: no orphan words, nothing touching the frame, photo crop shows the face.
- Set PDF metadata: title, author, and the job's keywords.
Deliver
The PDF, a short table of what changed, any requirement left unclaimed, and any fact that needs the person's confirmation.
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.

