Job Hunt
Help a user find, judge, apply for and rehearse for jobs. Four modes: discover (what is out there worth looking at), assess (whether this posting is worth applying to), apply (build and pressure-test the application), interview (rehearse and debrief). Use whenever the user wants to search for roles, judge their fit for a posting, tailor or optimize their CV/resume to a job, build a resume from scratch, write a cover/motivation letter, check whether an application is strong enough, or practise an interview — e.g. "help me apply to this role", "tailor my CV to this job link", "build me a resume"
Install
npx skills add addsumtech/job-hunt --skill job-huntgit clone --depth 1 https://github.com/addsumtech/job-hunt.git /tmp/job-hunt
mkdir -p ~/.claude/skills
cp -r /tmp/job-hunt/. ~/.claude/skills/job-huntPersonal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.
From the SKILL.md
# Job Hunt — Discover · Assess · Apply · Interview You are acting as this user's **experienced career coach and recruiter**. Your job is to take them from "I want this job" to a tailored, credible application package (CV + optional motivation letter) that would plausibly clear a real recruiter screen. ## First: scope, then mode **Decide before anything else, and say which one you picked.** Use the user's requested outcome to choose the smallest sufficient workflow. **Narrow text edit:** if the user asks only to polish a supplied bullet, sentence or short passage, rewrite just that text using the stated facts and ownership. Keep confirmed numbers; do not add impact, tools, leadership or scope they did not supply. Return the requested variants in chat. An explicit text-only/no-file request needs no workspace, mode-entry command, report, PDF, research or three judges. Read a craft reference only for a real uncertainty. Stop after the edit; do not turn it into a whole CV assessment or offer unrelated modes. For a full task, choose one mode and read that mode file **in full**: | Mode | User's question | Read on entry | |---|---|---| | `discover` | What roles are worth looking at? | [modes/discover.md](modes/discover.md) | | `assess` | Is this posting worth applying to? | [modes/assess.md](modes/assess.md) | | `apply` | Build and pressure-test the application. | [modes/apply.md](modes/apply.md) |
Details
- Skill name
job-hunt- Repository
- addsumtech/job-hunt
- License
- MIT
- Repo updated
- 31 October 2026
FAQ
What does the Job Hunt skill do?
Help a user find, judge, apply for and rehearse for jobs. Four modes: discover (what is out there worth looking at), assess (whether this posting is worth applying to), apply (build and pressure-test the application), interview (rehearse and debrief). Use whenever the user wants to search for roles, judge their fit for a posting, tailor or optimize their CV/resume to a job, build a resume from scratch, write a cover/motivation letter, check whether an application is strong enough, or practise an interview — e.g. "help me apply to this role", "tailor my CV to this job link", "build me a resume"
How do I install the Job Hunt skill?
skills CLI (Claude Code, Cursor, Codex and more): npx skills add addsumtech/job-hunt --skill job-hunt. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.
Is Job Hunt popular?
It lives in addsumtech/job-hunt, which has 5 GitHub stars and 1 forks.
Related skills
Arabic Rtl Docs
5muhmoosa/claude-arabic-docs
Produce correctly-rendered right-to-left (RTL) Microsoft Office documents — Word (.docx), PowerPoint (.pptx), and Excel (.xlsx) — for Arabic, Hebrew, Persian, Urdu, and other RTL scripts. Use this skill whenever the user asks for a document in Arabic or another RTL language, or whenever the deliverable mixes RTL prose with English/Latin tokens (IBANs, URLs, emails, numbers). It must also be used whenever you produce a docx-js / openpyxl / python-pptx output that contains any RTL text, because those libraries do NOT apply section-level bidi, table direction, or heading bidi automatically — outp
Jane First Intern Copilot
5jo1-yo/janes-first-intern-copilot
A battle-tested playbook for landing a first internship or first job with no connections and no experience — concise resume rewriting, a high-volume application system, and cold emails to startup founders. Use this whenever the user mentions internships, job hunting, resumes, CVs, cover letters, cold emails or DMs to founders or recruiters, applying to companies, getting no replies to applications, or asks "how do I get experience with no experience" — even if they only ask about one small piece, like fixing a single resume bullet.
Artifact to PDF
5yheshamx/artifact-to-pdf
Convert a Claude artifact (or any URL / exported .html file) into a SINGLE continuous, pixel-accurate PDF with no page cuts — one long page sized to the whole content. Use when the user wants to export, save, download, or "turn into PDF" an artifact, HTML file, or web page, especially as one long page with no page breaks / no pagination.
Grounded
4jostelzer/grounded
Produce source-grounded scientific narrative reviews, or audit the claims and references of a supplied draft, using live literature discovery, verified bibliographic records, independent claim checking, and evidence receipts. Supports chat and journal PDF output.
Ats Resume Formatting
5msdanyg/ats-resume-skill
Use this skill whenever a resume needs to be formatted, reviewed, or debugged for upload to Workday, Greenhouse, Lever, iCIMS, or any other ATS (applicant tracking system). Trigger on requests like "format my resume for ATS," "is my resume ATS-friendly," "why is Workday leaving fields blank," "clean up my resume for online applications," or "make my resume parse-safe." Also trigger proactively any time a user is building or editing a resume that will be uploaded to a job portal, even if they don't mention "ATS" by name — most resume-formatting requests have this failure mode lurking under the
Done Means Done
5PyModel/done-means-done
Finish every part of a substantial assignment (code, research, writing, analysis or operations) against a durable ledger of the requested outcomes, executed evidence for each, every confirmed defect fixed, and a gate that alone decides done. Use for multi-part or multi-step work, exhaustive repairs, requests to finish everything, and resuming an unfinished assignment. Resume the same task; never substitute a smaller one.
Browse the most popular Claude skills, all documents & office files skills, or write your own with the skills generator.