More screenshots

    Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    CV Tailor Creator

    2

    Turns one vacancy plus your real experience into a 2-page English or Russian resume (standard, bento, or boring), a print-ready PDF, an ATS check, and an honest gap report. It never invents a number.

    $20

    Secure checkout via Stripe

    Money-back guarantee

    Converts to your local currency at checkout

    Security scanned
    CV Tailor Creator

    CV Tailor Creator

    Example session with this skill installed

    Tailor my resume for this Senior Product Manager role at Acme Corp.
    Mode: bento
    Language: English

    Company: Acme Corp
    Role: Senior Product Manager
    Vacancy: https://acme.jobs/spm-123

    We need a PM who has owned a B2B SaaS lifecycle, run SQL-based product analytics, led a cross-functional squad, and improved activation and retention. Web3 experience is a plus. Apply through our careers page; the resume will be parsed by an ATS.

    • Read your context and instructions
    • Compiled the cv tailor creator
    • Generated the document

    I read the Senior Product Manager vacancy at Acme Corp and matched it to your fact bank. Six requirements are covered by a measured result. Web3 is not in the facts, so it stays a gap. Decision: go, in bento, in English. The PDF is 2 pages.

    Vacancy profile

    ItemFrom the vacancy
    LevelSenior, individual contributor
    DomainB2B SaaS
    Must-havesProduct lifecycle, SQL analytics, cross-functional leadership, activation, retention
    Nice to haveWeb3
    Language / modeEnglish, bento

    Match matrix

    RequirementFactStrength
    Own a B2B SaaS lifecycleCodeHire, candidate report and onboarding, pilot-to-subscription 25% → 41%Direct
    SQL-based analyticsSavings metrics tree and A/B reads used to change the deposit flowDirect
    Cross-functional leadership9 people on CodeHire; 20 people in 2 teams on savingsDirect
    ActivationDeposit opening 22% → 34% after the flow went from 7 steps to 3Direct
    Retention90-day churn 14% → 8% after the first-task onboardingDirect
    Web3No factNone

    ATS

    CheckResultStatus
    Parse (contacts, headings, dates, title, years)All okPASS
    Weighted keyword coverage86%PASS
    Must-have coverage100% of words that have a fact; Web3 left outPASS
    Pages2PASS

    Web3 is a miss on purpose. It is not in the fact bank, so it is not in the skills list and not hidden in the PDF.

    What changed on the page

    • Headline is Senior Product Manager. Nothing was added for Web3.
    • The five bento tiles use five different facts: pilot-to-subscription 25% → 41%, deposit opening 22% → 34%, 90-day churn 14% → 8%, payout launch 6 weeks → 5 days, and a team of 20. Each number appears once.
    • The summary uses years, B2B SaaS, and the activation result. Those numbers are not repeated on the tiles.
    • CodeHire leads. The marketplace job is shortened to two bullets because it is farther from this vacancy. It is not deleted.

    Files

    • HTML: output/2026-11-07/Acme_Alex_Smith_Resume_Senior_Product_Manager.html
    • PDF: output/2026-11-07/Acme_Alex_Smith_Resume_Senior_Product_Manager.pdf
    • Keywords: output/2026-11-07/Acme_Alex_Smith_Resume_Senior_Product_Manager_ATS_keywords.txt

    Gap, for the interview

    They may ask about Web3. The honest line is that you have not shipped it. Point at the closest fact you do have: a rules-based payout builder that cut a new payout scheme from 6 weeks to 5 days. Do not call that Web3.

    Next steps

    1. Open the PDF and read the tiles. The chart shape is an illustration; the numbers are the facts.
    2. Prepare the Web3 answer above. Do not edit the word onto the resume.
    3. If the portal is an older Workday or Taleo parser, ask for the same vacancy in standard or boring mode. Bento is the page for a person, not the safest file for a strict parser.
    4. After any hand edit to the HTML, run bash scripts/render.sh on that file and check that it is still 2 pages.

    Acme_Alex_Smith_Resume_Senior_Product_Manager.html

    PDF · document

    Generated

    Example file from a real run - the skill writes it into your workspace.

    Connects securely to your tools. The creator never sees your data.

    About this skill

    CV Tailor Creator

    An agent skill that builds a resume for one vacancy from a fact bank. The buyer keeps the facts. The skill chooses the headline, summary, order, and wording, renders a 2-page PDF, and says what the experience does not cover.

    A claim gets in only when it is written in the fact bank. No number, no claim.

    What the agent does

    1. If there is no fact bank yet, it stops tailoring and offers two paths: upload a current resume (PDF, DOCX, text, or a LinkedIn export), or answer a job-by-job questionnaire. An uploaded resume becomes the person's gold standard after a specificity check. The questionnaire builds a sample first, with [?] where a number is missing.
    2. For a ready fact bank, it maps the vacancy to the facts, writes HTML, renders a PDF, and runs an ATS check.
    3. It reports what is covered, what is a gap, and how to talk about the gap in an interview. The decision is go, iterate, or stop.

    Resume languages

    English and Russian. A Russian vacancy, a Russian company, or a request for Russian produces the Russian page. A request for both produces two files, _EN and _RU. Questions and the report follow the buyer's language. Numbers are not translated, and currency is not converted.

    Three modes

    ModeWhen
    StandardDefault. Banks, corporations, portals that parse resumes
    BentoProduct and tech companies. Five metric tiles, experience as cards
    BoringStrict ATS portals, or a plain read-test against the other modes

    What is included

    • The agent protocol (SKILL.md)
    • A questionnaire for an empty fact bank
    • A blank fact-bank template and a fictional filled example
    • Three HTML templates: standard, bento, boring
    • scripts/render.sh (HTML to PDF, page count must be 2)
    • scripts/ats_check.py (plain-text parse and keyword coverage)

    What the buyer needs

    An agent that can read files and run commands (Cursor, Claude Code, or similar), Python 3, and Google Chrome or Chromium. The skill runs locally. It is not a hosted editor and not a done-for-you writing service.

    Honesty rules

    The ATS target is weighted keyword coverage of at least 80% and must-have coverage of at least 90%. If a word is missing because the experience is missing, the skill records a gap. It does not add the word to raise the score. If the vacancy's main domain is absent from the facts, the result is stop.

    Requires source facts or an uploaded resume to start. Maximum 2-page output. Does not support non-standard fonts or hidden text stuffing. Requires headless Chrome for PDF rendering.

    How to use

    1. 1

      Connect your agent to the Agensi MCP

      Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup

    2. 2

      Sign in to Agensi

      Your agent shows a sign-in link. Sign in and click Allow.

    3. 3

      Ask for what you need

      Your agent loads this skill and uses it on your task. It always asks before any payment.

    Reviews

    No reviews yet

    Be one of the first to try it. Every listed skill goes through the trust checks below.

    Security scanned

    Checked by our 8-point scan before listing

    Fresh listing

    Recently published to Agensi

    Money-back guarantee

    Doesn't do what its page promises? You get your money back.

    Trust & safety

    Security scan

    Security scan passed 10 days ago

    Permissions

    Terminal / Shell
    Read Files
    Write Files
    Listed10 days ago
    Updatedtoday

    What's inside

    Frequently Asked Questions

    It reads the PDF the way a parser does: contacts, headings, dates, the job title, and the vacancy's words. The bar is 80% weighted coverage and 90% on must-haves. If a required word is missing because you never did that work, the skill leaves it out and writes a gap. It will not stuff keywords, hide text, or rename a fact so the score goes up.

    You get the agent skill, a questionnaire for an empty fact bank, a blank fact-bank template, a fictional filled example, three HTML templates (standard, bento, boring), a PDF render script, and an ATS check script. You run it in your own agent. A writer does not fill the resume for you.

    No. The resume is cut from the fact bank. A missing number stays blank or is marked [some questions], and the agent asks you. Unknown tools, visas, and domains go into the gap list.

    The agent does not tailor a vacancy yet. You either attach a current resume, which it turns into the gold-standard fact bank and then checks for missing numbers, or you answer the questionnaire. After the first job it shows one sample block so you can see the level of detail.

    An agent that can read and write files and run commands, such as Cursor or Claude Code. Also Python 3, and Google Chrome or Chromium for the PDF. The output is HTML plus PDF in an output/ folder.

    Yes for English and Russian, including both versions of the same vacancy. The skill does not claim other languages. Role titles on a Russian page may stay in English. Decimals, headings, and the team line follow the page language.

    New in Writing & Content