- Home
- Skills
- Productivity
- career driven
Works with the AI Agents you already use
career driven
Local job search engine for fact-based resume tailoring, lead ranking, and multi-board discovery.
$29
career driven
Example session with this skill installed
Tailor my Senior Software Engineer resume for the Backend role at Stripe. I have the job description saved in my clipboard.
- Read your context and instructions
- Compiled the career driven
I have initialized a new application folder for Stripe and saved the job description. I matched the requirements against your backend-eng variant and generated the tailored materials.
Application Tailoring: Stripe - Senior Software Engineer (Backend)
| Asset | Path | Status |
|---|---|---|
| Job Description | applications/2024-10-24-stripe/jd.txt | Saved |
| Tailored Resume | out/jdoe/backend-eng--stripe.pdf | Rendered (Typst) |
| ATS Resume | out/jdoe/backend-eng--stripe.docx | Generated |
| Cover Letter | out/jdoe/cover--stripe.pdf | Drafted |
| Application State | applications/2024-10-24-stripe/application.json | Status: draft |
Fact Matches & Adjustments:
- Signal: Highlighted your
distributed-systemsandgolangexperience from thecontent/bank. - Adjustment: Included the specific "High-availability API design" project as it matched the JD keywords.
- Omission: Removed the
frontend-reactsection to prioritize backend depth.
Next steps
- Review the generated PDF in the
out/directory for any final tweaks. - Submit the application manually on the Stripe careers site.
- Run
career build --target 2024-10-24-stripeto move this to theappliedstate and archive the files.
Connects securely to your tools. The creator never sees your data.
About this skill
Managing a multi-lane job search across dozens of disparate job boards and careers sites is a manual, fragmented mess. This skill localizes your entire search pipeline, providing a command-line engine to ingest your history, crawl niche job boards, rank leads by your specific criteria, and generate tailored, submission-ready PDFs.
What it does
- Local fact banking maintains a single source of truth for your professional history in
content/to prevent fact invention. - Automated job discovery crawls Greenhouse, Lever, Ashby, Workday, and other public APIs to aggregate new leads.
- Lead ranking scores job postings against your
profile.yamlkeywords, target titles, and lane signals. - Tailored document generation renders role-specific resumes and cover letters using Typst for high-quality PDFs and Word for ATS compatibility.
- Application tracking logs every sent document and interview stage in a structured local file system.
How it works
- Initialize the system by running
career initandcareer onboard ingestto transcribe existing resumes into the local fact bank. - Configure your search by defining target companies and job board watchers in
watch.yamland setting ranking signals inprofile.yaml. - Run discovery with
career discover runto fetch new postings and update yourREVIEW-QUEUE.md. - Tailor and promote leads using
career buildto generate a job-specific overlay and draft your application materials.
Frameworks & tools
The engine is a uv script requiring Python dependencies like pyyaml and python-docx. It uses typst for PDF rendering, poppler for PDF parsing, and optional playwright for HAR-based site discovery.
Why this beats prompting it yourself
Standard LLM prompting often results in "hallucinated" achievements or generic buzzwords that fail ATS screens. This skill enforces a "content-first" rule where every resume line must map back to a verified fact bank, ensuring 100% accuracy while automating the repetitive crawl-and-format loop.
Use cases
- Manage high-volume applications across multiple career "lanes" like Product Management and Engineering.
- Fix broken job board integrations by importing browser HAR files to bypass fingerprinting issues.
- Maintain a permanent, immutable record of exactly which resume version was sent to which company.
- Prepare for interviews by instantly retrieving facts and notes associated with a specific application folder.
Known limitations
Does not support one-off resume advice or OCR for image-only PDFs. Requires local installation of uv, Typst, and poppler. Cannot bypass robots.txt or site-wide bot screening.
Requires local installation of uv, Typst, and poppler. Does not submit applications or fill forms. Does not support LinkedIn or Indeed crawling. Honers robots.txt and rate limits.
How to use
- 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
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 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 1 month ago
Requires
Permissions
File Scopes
Terminal runs the bundled `career` launcher (a uv script), Typst and pdftotext. Read/write covers your resumes and everything in the data directory: content, variants, overlays, notes, application folders and crawl state. Nothing is written inside the skill folder. Network access is used only when you ask for a crawl. It reads public job-board APIs over HTTPS with an honest `career-driven/1.0` User-Agent, rate limits and robots.txt, and uploads no personal data. Environment variables are read only for the optional USAJOBS and The Muse keys and `CAREER_DRIVEN_HOME`. HAR captures are sanitized on import (cookies, auth headers, CSRF/session tokens, personal form fields and response bodies removed); the original file is never copied, and an automatic capture's raw recording is deleted. `career sources discover`, `har import` and `har capture` run only for a company you name, refuse blocked or robots-disallowed sites, and write that one board with a per-board opt-in. Installing uv, Typst, poppler or the optional Playwright/Chromium, and running `career backup`, each need your explicit yes, with a dry run offered first for backups. It never fills in or submits applications, emails recruiters or posts anything, and it never enables a careers-site source on your behalf.