DhruvPrajapati4

answer-questions

Draft the free-text answers a job application asks for - "why do you want to work here", "why are you a fit for this role", "tell us about a project you are proud of", "anything else we should know" - grounded strictly in the user's real resume and the job posting, and written so they do not read as AI output. Use whenever the user is filling in an application form and needs the written portions, pastes application questions, asks "how should I answer this", wants a cover-letter box filled, or reaches that stage of apply-to-job after their resume is tailored. Also use for a recruiter's written screening questions. Do NOT use it for a cold outreach email to a company that has not asked anything (that is a different task), and do NOT use it to answer salary or work-authorization questions, which the skill deliberately hands back to the user.

Data & Documents Listed

apply-to-job

Run the entire application pipeline for a specific job from one command — extract the JD, assess fit, tailor the LaTeX resume, render the PDF, draft any free-text answers the form asks for, and prepare the submission for your confirmation. Use whenever the user gives a job URL or JD and wants the end-to-end result rather than a single step. If the user only wants to analyze a JD, check fit, or tailor without rendering, prefer the narrower skills (extract-jd / resume-fit-report / tailor-resume) instead. Orchestrates those skills in order, pauses for review before rendering, and never submits without an explicit yes.

Data & Documents Listed

extract-jd

Fetch and normalize a job posting into a structured requirements brief (role, seniority, must-haves, ATS keywords). Use whenever the user shares a job URL or pastes/links a job description and wants it analyzed, summarized, or broken down — including loose asks like "what does this job want" or dropping a link with no further instruction — and as the first step before a fit check or resume tailoring. Handles URL fetching with a clean fallback to pasted text when a site (LinkedIn, Workday, Greenhouse, Lever, Ashby) blocks scraping.

find-jobs

Find live job openings that actually match the user by querying company applicant tracking systems (Greenhouse, Lever, Ashby, Workable, Workday) directly, then filtering on location, title, stack and stated years of experience. Use whenever the user wants to discover roles rather than analyze one they already have - "find me backend jobs in Berlin", "who is hiring Rust engineers", "what is open at these companies", "find roles that fit my resume", "any openings at seed startups near me" - and as the first stage before extract-jd when the user has no specific posting yet. Also use to look up which ATS a company uses, to check whether a specific company has anything open, or to turn up companies that are not on any curated list. Do NOT use it when the user already has a job URL or pasted JD (use extract-jd), or when they want fit scoring against a known posting (use resume-fit-report).

humanize-text

Strip the tell-tale signatures of AI-generated prose so writing reads as naturally human. Removes em dashes and en dashes, converts smart quotes and other typographic Unicode to plain ASCII, and dials back robotic AI phrasing and structure. Use this as a finishing pass WHENEVER you generate, write, refine, rephrase, reword, polish, draft, or edit any prose the user will send or publish — emails, messages, docs, posts, cover letters, commit bodies, PR descriptions, blog text — even when the user only asks to "clean it up" or "make it sound natural" without naming AI. Do NOT apply it to code, code comments, config, or verbatim quotes.

Data & Documents Listed

ingest-resume

Take a user's own resume file (.tex or .docx) into the pipeline as the working master, and check it has the sections a software-engineering resume needs. Use whenever the user attaches or points to a resume file to tailor, or at the start of apply-to-job when no master resume is set yet. Preserves the user's own template and content; it polishes an existing resume, it never writes one from scratch or invents missing sections.

render-resume

Compile a LaTeX resume to PDF with latexmk (falling back to tectonic or pdflatex) and report the output path, surfacing compile errors clearly. Use whenever the user wants to build, render, compile, or generate the PDF of their resume .tex — typically right after tailoring, or to rebuild the master. Detects the available TeX engine and gives install guidance if none is present.