By agent-data
Run a private, local-first job search assistant that pulls postings from saved queries, judges each against your prose preferences, and digests matches on a schedule you control.
Judge whether a single job posting matches the user's Job Preferences Brief — relevant or not, and if relevant a weak/moderate/strong match — with plain-language reasoning, dealbreakers, and unknowns. Use when the user pastes or references a job posting and asks if it fits their preferences, whether to apply, or how good a match it is, or when job-search-run needs to evaluate postings. For many postings at once, job-search-run drives this skill per posting — do not batch here.
Build or update the user's Job Preferences Brief at a depth they choose — a quick free-form sketch (~1 question), a standard interview, or a thorough pass — producing a prose preferences.md (Summary, Must-haves/dealbreakers, Strong preferences, Nice-to-haves, Red flags). Imports an existing brief too, and can deepen a light brief later. Use when the user wants to set up or refine what they want in a job, or when job-search onboarding needs a brief — "set up my job preferences", "what I want in a job", "redo my preferences interview", "change my must-haves", "import my preferences brief". Not for judging a specific posting (→ evaluate-job-fit).
The operator manual for the Job Search Agent — configure, customize, extend, or troubleshoot the agent itself, or explain how it works. Use when the user asks how the agent works, why a run failed, what it can do, or how to change its behavior — a query, the schedule, the recency window, the detail-read model — "how does my job search agent work", "why did the run fail", "how do I change/add/customize …", "change how often it runs". Not for daily use — onboarding, the home view, and running a search are job-search; the search pass itself is job-search-run.
Run one headless, non-interactive job-search pass — load the preferences brief and config, search agent-data for each saved query, skip postings it has already seen, judge each new posting's relevance, read full descriptions for promising matches, and write a digest. Use to run the scheduled search, check for new jobs, or to run a search on demand — "run a job search now", "pull jobs now", "do a fresh search", or when invoked by a schedule. (For interactive setup or the home view, use job-search; for a single pasted posting, use evaluate-job-fit.)
Set up, check on, and steer the user's job search — the front door and home screen. Use when they want to start or set up a job search, see status, matches, the latest digest, or the pipeline, or change what they're looking for — "set up job search", "start my job search", "I'm looking for a new job", "check my job search", "show me my matches", "what's new in my pipeline", or /job-search. First run onboards end-to-end (prereqs, workspace, preferences interview, queries + frequency, first live search, scheduling); afterward it shows the job-search home with quick actions. Not for a fresh headless pull ("check for new jobs" → job-search-run) or for configuring/troubleshooting the agent itself (→ job-search-agent).
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
Job Search is a plugin that turns your coding agent into a job search assistant. Describe what you want, and the agent pulls fresh job postings, judges each against your preferences, and generates a ranked digest of the matches.
Set your agent-data API key. Grab one at agent-data.motie.dev (Profile → API Key), then export it:
export AGENT_DATA_API_KEY=mtk_…
Give your agent Job Search: Claude Code · Codex · Cursor · opencode · Gemini CLI · GitHub Copilot CLI · Factory Droid · Pi.
/job-search).See an example digest in examples/sample-digest.md.
Installation differs by harness. If you use more than one, install Job Search separately for each one.
Register our marketplace, then install:
/plugin marketplace add agent-data/job-search
/plugin install job-search@agent-data
Then run /job-search to start.
Register our marketplace, install the plugin, and launch Codex:
# Run in the normal shell
codex plugin marketplace add agent-data/job-search
codex plugin add job-search@agent-data
# Then launch or restart Codex
codex
Then run $job-search to start.
Clone the repo and open it in Cursor — it loads the bundled skills from the repo's .cursor-plugin/ manifest:
git clone https://github.com/agent-data/job-search
Then tell Cursor to run the job-search skill.
Add Job Search to the plugin array in your opencode.json (global or project-level):
{
"plugin": ["job-search@git+https://github.com/agent-data/job-search.git"]
}
Restart opencode — it installs the plugin and registers the skills. Details and troubleshooting: .opencode/INSTALL.md. (Or run from a local clone: cd /path/to/job-search && opencode.)
Then tell opencode to run the job-search skill.
Install the extension straight from git:
gemini extensions install https://github.com/agent-data/job-search
Update later with gemini extensions update job-search.
Then tell Gemini to run the job-search skill.
Register our marketplace, then install:
copilot plugin marketplace add agent-data/job-search
copilot plugin install job-search@agent-data
Then tell Copilot to run the job-search skill.
Register our marketplace, then install:
droid plugin marketplace add https://github.com/agent-data/job-search
droid plugin install job-search@agent-data
Then tell Droid to run the job-search skill.
Install from git:
pi install git:github.com/agent-data/job-search
For an editable/development install, point Pi at a local clone: pi -e /path/to/job-search.
Then tell Pi to run the job-search skill.
Building on or exploring the repo with an AI agent? Start at AGENTS.md, the map of the architecture, design beliefs, and plans — including how one skills/ tree runs across every supported agent. See CONTRIBUTING.md for the dev workflow and TESTING.md for the test harness.
MIT — see LICENSE.
npx claudepluginhub agent-data/job-search --plugin job-searchAI-powered job search, resume tailoring, and cover letter writing
AI-powered end-to-end job search companion. Combines recruiter, career coach, reverse recruiter, and market analyst into a single intelligent platform with a feedback loop that learns what works for you.
Job search copilot for any industry. Evaluate job postings, generate ATS-optimized resumes, scan career portals, track applications, draft outreach, and research companies. Works for engineers, marketers, nurses, lawyers, and everyone in between.
Intelligence-driven job application system - resume development, interview prep, OSINT intelligence, career strategy, and crisis management using HAM-Z methodology
AI-powered resume builder with job discovery, dual ATS + HR scoring, and cover letter generation. Finds and ranks live job listings by fit, tailors your resume to any JD, auto-detects 6+ professional domains, and produces Workday-compatible DOCX output.
Claude Code skill pack for Juicebox (24 skills)