Skip to content
Back to search

job-seeker

Automate your job search with your favorite coding agent. Skills, guides, and scripts that any agent (Devin, Claude, Cursor, opencode) consumes to search, apply, and track jobs on your behalf.

Safety scan

A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.

Checked today

Check it deeper on your machine

It has changed since its scan on 11 Nov 2026.

As a Claude Code plugin, install it and then ask Claude Code:

/plugin marketplace add keithmackay/mackayi/plugin install scanskillsafety@mackayiDo a deep scan of https://github.com/galiprandi/job-seeker with scanskillsafety

Or from a terminal, clone it and run it:

git clone https://github.com/keithmackay/scanskillsafety-skill ~/.claude/skills/scanskillsafetynode ~/.claude/skills/scanskillsafety/cli.cjs --deep 'https://github.com/galiprandi/job-seeker'

It checks the exact commit: every file, its packages against OSV (api.osv.dev), how it compares with this page's scan (findsafeskills.com receives the repository's address), and, if you agree, Claude reading every file with your own Claude subscription. It never runs the code.

Badge for your README
findsafeskills safety rating

Markdown

[![findsafeskills safety rating](/api/listings/galiprandi--job-seeker/badge.svg)](/listings/galiprandi--job-seeker)

HTML

<a href="/listings/galiprandi--job-seeker"><img src="/api/listings/galiprandi--job-seeker/badge.svg" alt="findsafeskills safety rating" /></a>

Install

i

Install instructions from the README

As written by the repo's author. findsafeskills has not verified these steps.

git clone https://github.com/<your-username>/job-seeker.git
cd job-seeker
npm install

Create `.env` with your connection string:

DATABASE_URL=postgresql://user:pass@ep-xxx.neon.tech/dbname?sslmode=require

Open your coding agent in the repo and say: "run the onboarding skill"

After onboarding, try:

- "profile" - set up your professional profile - "strategy" - configure your search aggressiveness - "apply to 5 jobs" - search and apply - "news" - check for updates from recruiters

What was scanned

The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.

README.md · README · 239 lines

View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)

This file has changed since it was scanned, so this is not exactly the text that was scanned, and no line is marked. The findings are listed with the safety scan above.

  1. # Job Seeker
  2. > Let your AI coding agent apply to jobs for you.
  3. [![CI](https://github.com/<your-username>/job-seeker/actions/workflows/ci.yml/badge.svg)](https://github.com/<your-username>/job-seeker/actions/workflows/ci.yml)
  4. [![Docs](https://img.shields.io/badge/docs-vitepress-646cff.svg)](https://<your-username>.github.io/job-seeker/)
  5. [![License: MIT](https://img.shields.io/badge/license-MIT-blue.svg)](LICENSE)
  6. [![Stars](https://img.shields.io/github/stars/<your-username>/job-seeker?style=social)](https://github.com/<your-username>/job-seeker)
  7. **If this helps you find your next role, [give it a star](https://github.com/<your-username>/job-seeker).** It helps other devs discover it.
  8. ## First time here? No coding experience needed
  9. If you use an AI coding agent like **[Claude Code](https://claude.com/product/claude-code)**, **[Codex](https://openai.com/codex)**, or **[Antigravity](https://antigravity.google/)** (download one if you don't have it yet, all have free options) and aren't sure how to get started, copy and paste this prompt into your agent:
  10. ```text
  11. Clone the repository https://github.com/<your-username>/job-seeker, run npm install, then read AGENTS.md and .agents/skills/onboarding/SKILL.md and run the onboarding flow. Walk me through each step and ask for anything you need (LinkedIn/Gmail logins, a Neon Postgres connection string, etc.).
  12. ```
  13. The agent will clone the repo, install dependencies, and start onboarding, which sets up your browser, database, and profile. You'll only be asked to log into LinkedIn and Gmail manually and to provide a Postgres connection string (Neon's free tier works).
  14. Job Seeker is a set of **markdown skills** that any coding agent (Devin, Claude, Cursor, opencode) consumes to automate the entire job search:
  15. - Searches LinkedIn with your Must-have filters
  16. - Fills Easy Apply forms from your Postgres DB
  17. - Tracks every application in a kanban pipeline
  18. - Drafts recruiter replies in your writing style
  19. - Runs a daily routine while you review and approve
  20. Your data stays in your own DB. The repo is candidate-agnostic: clone it, run onboarding, and go.
  21. **Full documentation: [https://<your-username>.github.io/job-seeker/](https://<your-username>.github.io/job-seeker/)**
  22. ## Demo
  23. https://github.com/<your-username>/job-seeker/releases/download/v0.1.0/demo-terminal.webm
  24. **Pipeline kanban** (`node scripts/pipeline.js`):
  25. <img src="assets/pipeline-demo.png" width="640" alt="Pipeline Kanban" />
  26. The CLI prints a terminal kanban grouped by pipeline stage (discovered → hired), with match indicators (★ Must, ◆ Strong, ○ Nice), interview dates, and a closed summary. Use `--closed` to include rejected/withdrawn/skipped columns, `--funnel` for a bar chart, `--move <id> <stage>` to move cards, and `--card <id>` for full card detail with linked messages.
  27. **Local dashboard** (`node scripts/dashboard.js --open`):
  28. <img src="assets/dashboard-light.png" width="720" alt="Dashboard" />
  29. The dashboard visualizes your pipeline with a VitePress-inspired design, including KPI cards, a funnel chart, a kanban board, target-company groups, and recent messages. It also supports light and dark themes. The agent opens it at the end of each round so you can visually review the pipeline. It auto-refreshes every 30 seconds.
  30. ## Why Job Seeker?
  31. The average job seeker spends **5-8 hours per week** scrolling job boards, filling repetitive forms, and tracking applications in spreadsheets. Job Seeker automates the boring part:
  32. - **Search** your agent reads your profile and searches LinkedIn with your Must-have filters
  33. - **Apply** Easy Apply forms filled automatically with your data from the DB (no guessing, no inventing)
  34. - **Track** every application, message, and interview in a Postgres pipeline with a kanban view
  35. - **Reply** recruiter messages drafted in your style, reviewed by you before sending
  36. - **Remember** your preferences are detected automatically and stored for future sessions
  37. You stay in control. The agent does the grunt work.
  38. ## How it works
  39. ```
  40. You: "apply to 5 jobs"
  41. -> Agent loads your profile from DB
  42. -> Searches LinkedIn with your Must-have filters
  43. -> Applies via Easy Apply (form data from DB)
  44. -> Registers every application
  45. -> Shows you a summary
  46. ```
  47. 1. Clone the repo
  48. 2. Tell your agent: "run the onboarding skill"
  49. 3. The agent opens a browser, asks you to log into Gmail and LinkedIn, creates your DB, and profiles your CV
  50. 4. You say: "apply to 5 jobs" and the agent searches, filters, applies and records everything
  51. Your profile, preferences, writing style and history live in Postgres (Neon). Your browser session persists in a dedicated profile. Nothing sensitive is committed to the repo. The repo is **candidate-agnostic**: clone it, run onboarding, and everything you need is stored in your DB. No file in the repo contains personal data.
  52. ## Flows
  53. | Flow | Trigger | What it does |
  54. |---|---|---|
  55. | `onboarding` | `onboarding` | Bootstrap: browser with dedicated profile, Gmail + LinkedIn login, Neon DB, user data |
  56. | `profile` | `profile` | Profiling: CV + questionnaire (30 preferences with weights) + voice/style + platform selection |
  57. | `strategy` | `strategy` | Configure job search aggressiveness level. All flows respect it |
  58. | `radar` | `radar` | Passive sourcing: register on job boards, configure alerts, Gmail filter to Job Alerts folder |
  59. | `targets` | `targets` | Active direct sourcing: register and create standout profiles on target companies' career sites, then apply to matching positions |
  60. | `news` | `news` | Review updates in Gmail, LinkedIn and platforms. Prepare drafts, executive summary by priority, hybrid validation and auto-send |
  61. | `apply` | `apply` | Search jobs on LinkedIn, filter by Must-haves, apply via Easy Apply, register in DB |
  62. | `referrals` | `referrals` | Warm sourcing: discover internal contacts, alumni, ex-colleagues, and recruiters at target companies, stage referral requests/outreach DMs, and micro-align CV keywords to JD |
  63. | `daily` | `daily` | Periodic routine: runs `news` -> inbox cleanup -> applies if no recent activity |
  64. | `memory` | (always on) | Autonomous preference detection, storage and injection. Detects preferences from conversation, saves to DB, loads active ones at the start of every flow |
  65. | `dashboard` | `dashboard` | Opens a local web dashboard with kanban, funnel, stats, messages, and target companies. Auto-refreshes every 30s |
  66. **Tools (not flows):**
  67. | Tool | Location | Usage |
  68. |---|---|---|
  69. | `agent-browser` | `.agents/skills/browser-automation/scripts/browser.js` wrapper | Browser automation: open/close/goto/tabs via wrapper. Other commands (click, fill, snapshot) via `exec` passthrough |
  70. | `db` | `scripts/db.js` | Safe Postgres CLI. Reads `DATABASE_URL` from `.env`, JSON output, read-only by default (`--write` for writes) |
  71. | `linkedin-warm-sourcing` | `scripts/linkedin-warm-sourcing.js` | Discover internal contacts, alumni, ex-colleagues, and recruiters at target companies |
  72. | `pipeline` | `scripts/pipeline.js` | Kanban board CLI for application tracking. Print board, move cards, view funnel, card details |
  73. | `dashboard` | `scripts/dashboard.js` | Local web dashboard. Serves at `http://localhost:7531`. The agent opens it at the end of a round |
  74. ## Who is this for?
  75. Works best for tech professionals who use LinkedIn as their primary job platform and Gmail for email. The system is designed to be extensible to other platforms.
  76. ## Requirements
  77. - Node.js 22+
  78. - npx
  79. - A LinkedIn account
  80. - A Gmail account
  81. - A Postgres database (Neon recommended, free tier works)
  82. `npm install` handles all dependencies. `agent-browser` needs no install — the wrapper resolves it (node_modules/.bin → global → `npx -y agent-browser`); `npm i -g agent-browser` is optional and only saves the npx lookup.
  83. ## Quick Start
  84. ```bash
  85. git clone https://github.com/<your-username>/job-seeker.git
  86. cd job-seeker
  87. npm install
  88. ```
  89. Create `.env` with your connection string:
  90. ```
  91. DATABASE_URL=postgresql://user:pass@ep-xxx.neon.tech/dbname?sslmode=require
  92. ```
  93. Open your coding agent in the repo and say: "run the onboarding skill"
  94. After onboarding, try:
  95. - "profile" - set up your professional profile
  96. - "strategy" - configure your search aggressiveness
  97. - "apply to 5 jobs" - search and apply
  98. - "news" - check for updates from recruiters
  99. ## Platforms
  100. `PLATFORMS.md` is a catalog of 35 platforms in 5 categories (general, tech, AI, executive, latam), community-maintained. The agent consults it to decide where to search based on your profile. You don't choose platforms, the agent deduces them. See the [platforms reference](https://<your-username>.github.io/job-seeker/reference/platforms) in the docs.
  101. ## Stack
  102. - **Browser:** `agent-browser` (resolved by the wrapper, no install required). Persistent `.browser-profile`, `headed` per `agent-browser.json`
  103. - **DB:** PostgreSQL via Neon (cloud). Portable across machines
  104. - **Node:** `pg` for DB access, `agent-browser` for browser automation
  105. - **Skills:** Markdown in `.agents/skills/`. Universal, not tied to one agent
  106. - **Tests:** Vitest for browser wrapper and script tests
  107. ## Structure
  108. ```
  109. .agents/skills/ # Skills consumed by any agent
  110. apply/SKILL.md # Job search and application
  111. daily/SKILL.md # Periodic routine
  112. db/SKILL.md # Safe Postgres CLI usage
  113. memory/SKILL.md # Autonomous preference detection and injection
  114. news/SKILL.md # Updates review and follow-up
  115. onboarding/SKILL.md # Onboarding
  116. profile/SKILL.md # Profiling
  117. radar/SKILL.md # Passive sourcing (alerts)
  118. referrals/SKILL.md # Warm sourcing & referral request staging
  119. strategy/SKILL.md # Search aggressiveness configuration
  120. targets/SKILL.md # Active direct sourcing
  121. scripts/ # Automation scripts (browser via .agents/skills/browser-automation/scripts/browser.js)
  122. db.js # Safe Postgres CLI
  123. linkedin-search.js # Search LinkedIn posts for job openings
  124. linkedin-warm-sourcing.js # Discover internal contacts, alumni, ex-colleagues, recruiters
  125. linkedin-invite.js # Send LinkedIn connection requests
  126. linkedin-easy-apply.js # Search + apply to Easy Apply jobs
  127. gmail-send.js # Send emails via Gmail web UI with CV attached
  128. pipeline.js # Kanban board CLI for application tracking
  129. dashboard.js # Local web dashboard (serves at localhost:7531)
  130. easy-apply-helper.sh # Helper for Easy Apply form filling
  131. templates/ # ATS-specific apply playbooks
  132. teamtailor-apply.md # Teamtailor application flow
  133. humand-apply.md # Humand.co application flow
  134. tests/browser/ # Vitest tests for browser wrapper
  135. 01-syntax-config.test.mjs # Config and syntax validation
  136. 02-failfast.test.mjs # Fail-fast behavior
  137. 03-lifecycle.test.mjs # Browser lifecycle
  138. 04-tabs.test.mjs # Tab management
  139. 05-sessions.test.mjs # Session management
  140. 06-parallel.test.mjs # Parallel subagent sessions
  141. 07-state-debug.test.mjs # Auth state and debugging
  142. helpers.mjs # Test helpers
  143. assets/ # Visual assets for README
  144. social-preview.png # Social preview image (1280x640)
  145. pipeline-demo.png # Pipeline kanban screenshot
  146. demo-terminal.webm # Demo video of apply flow
  147. vitest.config.mjs # Vitest configuration
  148. agent-browser.json # agent-browser config (namespace, profile, headed)
  149. .env # DATABASE_URL (not tracked)
  150. .browser-profile/ # Persistent Chrome profile (not tracked)
  151. PLATFORMS.md # Platform catalog (community)
  152. STRATEGIES.md # Job search and networking strategies (ordered by effectiveness)
  153. DATA.md # Data map: tables, JSONB keys, flow ownership
  154. ADR.md # Architecture decisions
  155. AGENTS.md # Operational rules + Gold Rules
  156. DESIGN.md # Design tokens (placeholder, no UI yet)
  157. CONTRIBUTING.md # How to contribute
  158. LICENSE # MIT
  159. ```
  160. ## Key decisions
  161. See `ADR.md` for details, or the [architecture reference](https://<your-username>.github.io/job-seeker/reference/architecture) in the docs. Summary:
  162. - **agent-browser** over MCP: native CLI, token-efficient snapshot refs
  163. - **Postgres** over Mongo: 70% of data is relational. JSONB for semi-structured
  164. - **Neon** for portability: clone on another machine, same `DATABASE_URL`, same profile
  165. - **npx** over global installs: zero friction on clone
  166. - **Headless** by default: headed only for manual login and 2FA
  167. - **Skills in `.agents/skills/`**: universal format, works with any agent
  168. ## Disclaimer
  169. > **Disclaimer:** This tool automates browser interactions with job platforms. Review the Terms of Service of each platform before use. The authors are not responsible for account restrictions resulting from automated activity. Use responsibly.
  170. ## Contributing
  171. Contributions are welcome. See `CONTRIBUTING.md` for guidelines, or the [contributing guide](https://<your-username>.github.io/job-seeker/reference/contributing) in the docs.
  172. Areas where help is most useful:
  173. - **`PLATFORMS.md`**: add platforms with the fields from the existing table
  174. - **Skills**: improve existing checklists, rules, and step-by-step detail
  175. - **Scripts**: add support for new ATS platforms, improve form-filling logic
  176. - **Tests**: expand browser wrapper coverage, add script tests
  177. - **ADR**: append-only. To reverse a decision, add a new ADR that supersedes it
  178. ## License
  179. MIT - use it, fork it, contribute.

Ratings and comments

Sign in to rate this skill.

Sign in

Free to use. If it’s helped, pass it on.