Skip to content
Back to skills

Job Hunter

ASecurity

Primary job search command center. Routes to individual skills for all job search work.

  • 24 stars
  • 0 votes
  • 1 copy
  • 11 views
  • Added September 6, 2026
ai-agentsgobash

Works with

  • terminal

Security analysis

A100/100

Pro scans all 11 files and shows the line behind each finding

Scanned September 6, 2026

npx -y skills add abdulrbasit/job-hunter --skill job-hunter --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Job Hunter?

Add the live security badge to your README. It updates with every re-scan.

Security grade badge for Job Hunter
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/abdulrbasit-job-hunter/badge)](https://www.skillsdirectory.com/skills/abdulrbasit-job-hunter)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
SKILL.md
---
name: job-hunter
description: "Primary job search command center. Routes to individual skills for all job search work."
when_to_use: "Use for all job search work: running hunts, processing candidates, tailoring, researching, and managing the pipeline."
argument-hint: "[batch|one <url>|finalize|tailor <job>|outreach <job>|interview <job>|score <job>|research <co>|stories|linkedin <cmd>|add-region|style|setup|doctor|dashboard|help]"
disable-model-invocation: true
allowed-tools: Bash Read Edit Write WebSearch WebFetch
author: "Abdul Basit (@abdulrbasit)"
category: workflow
---

Execute `.claude/skills/caveman/SKILL.md` inline before processing any command.
Execute `.claude/skills/job-hunter/_rules.md` inline before processing any command.

# Job Hunter Command Center

One entry point for all job search work. Keep output compact — no raw candidate snapshots, full logs, PDFs, or Draft/raw story-bank sections.

Arguments: `$ARGUMENTS`

## Key Paths

| What | Path |
|---|---|
| Story bank | `profile/story_bank.md` |
| Candidate queue | `outputs/state/agent_candidate_queue.json` |
| Job outputs | `outputs/jobs/<slug>/` |
| Job DB | `outputs/state/jobs.db` |
| Config | `config/job_hunter.yml` |

## Safety Rules

- Never fabricate resume facts, employers, dates, metrics, skills, or job history.
- Never submit applications, send messages, connect, follow, like, comment, or post automatically.
- Never overwrite profile/config inputs unless that mode requires it and the user requested it.
- Leave generated changes uncommitted unless the user runs `job-hunter finalize`.

## Initialization

Before any mode that reads profile files (batch, one, tailor, score, screen, interview, outreach), run:

```bash
job-hunter internal compile-profile
```

This compiles profile files into minified versions for the session. A missing config or
profile file is a silent no-op (fine for a fresh workspace). Any other failure logs one
compact warning line to `job_hunt.log` and falls back to the raw profile files — it never
raises or blocks the session.

## Routing

Normalize the first argument to lowercase. Empty argument → `help`.

**Daily workflow**
- `dashboard`, `apps`, `applications`: tell the user to open the Job Hunter app (`job-hunter dash`) and use the Applications view — there is no terminal dashboard to run inline.
- `batch`, `process`, `queue`: execute `.claude/skills/job-hunter/modes/batch.md` inline.
- `one <url>`, `url <url>`, or any pasted `http(s)://` URL: execute `.claude/skills/job-hunter/modes/one.md` inline with the URL and remaining arguments.
- `finalize`: run `job-hunter finalize` (add `--push` if the user asked to push). It validates, commits, and optionally pushes durable outputs itself — no separate skill needed. Show its output verbatim.
- `screen`: execute `.claude/skills/job-hunter/modes/screen.md` inline.

**Per-job actions** — second token is the job slug
- `tailor <job>`: execute `.claude/skills/job-hunter/modes/tailor.md` inline.
- `outreach <job>`: execute `.claude/skills/job-hunter/modes/outreach.md` inline.
- `interview <job>`: execute `.claude/skills/job-hunter/modes/interview.md` inline.
- `score <job>`: execute `.claude/skills/job-hunter/modes/score.md` inline.
- `research <job>`: execute `.claude/skills/job-hunter/modes/research.md` inline.
- `stories`: execute `.claude/skills/job-hunter/modes/stories.md` inline.

**LinkedIn sub-router** — `linkedin` (alone or with sub-argument): execute `.claude/skills/linkedin/SKILL.md` inline with remaining arguments.

**Setup sub-router** — `setup`, `init`, `onboard`, `doctor`, `health`, `check`, `add-region`, `region`, `style`: execute `.claude/skills/setup/SKILL.md` inline with remaining arguments.

Unknown mode → print the command menu and ask the user to choose a listed mode.

## Command Menu

```text
Job Hunter Command Center

── Daily Workflow ──────────────────────────────────────────────────────
/job-hunter dashboard          Open the Job Hunter app to review applications
/job-hunter batch              Process the next frozen candidate batch
/job-hunter one <url>          Process one job URL end-to-end
/job-hunter finalize           Runs `job-hunter finalize` to commit durable reviewed outputs
/job-hunter screen             Pre-screen a frozen batch against config exclusion rules

── Per-Job Actions ─────────────────────────────────────────────────────
/job-hunter tailor <job>       Tailor resume + cover letter for a job
/job-hunter outreach <job>     Draft LinkedIn connection + follow-up
/job-hunter interview <job>    Generate predicted interview questions
/job-hunter score <job>        Score one job 0-100 vs. resume and story bank
/job-hunter research <job>     Web-search a company for an imported job
/job-hunter stories            Refine raw work notes into rated STAR stories

── LinkedIn ────────────────────────────────────────────────────────────
/job-hunter linkedin ideas     Generate weekly LinkedIn post ideas
/job-hunter linkedin draft     Write one ready-to-post LinkedIn draft
/job-hunter linkedin engage    Draft comments for posts in your feed
/job-hunter linkedin network   Build a weekly connection queue

── Tools ───────────────────────────────────────────────────────────────
/job-hunter setup              One-time onboarding for a fresh workspace
/job-hunter doctor             Run the health checker and show setup status
/job-hunter add-region         Add/remove a region — dash → Settings → Guided → Regions
/job-hunter style              Change resume color/font — dash → Settings → Resume Style
```

## Output Rules

- Execute child skills inline from their `SKILL.md`; do not print a slash command as a handoff.
- Print only paths, counts, short decisions, and next actions.
- Leave generated changes uncommitted unless the user runs `job-hunter finalize`.

Files in this skill

  • SKILL.md6.2 KB
  • _rules.md1.6 KB
  • modes/batch.md5.1 KB
  • modes/interview.md2 KB
  • modes/one.md2.3 KB
  • modes/outreach.md1.9 KB
  • modes/research.md1.2 KB
  • modes/score.md1.8 KB
  • modes/screen.md2.1 KB
  • modes/stories.md871 B
  • modes/tailor.md7.1 KB

Attribution

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments

Loading comments…

Newsletter

Get the weekly list of safe new skills, and the ones we pulled.