akbardevop/ai-job-agent/job-apply
Claude Code and agent skill by akbardevop/ai-job-agent
- community
Checking that the SKILL.md file is still in the repository.
Apply to a job by URL — auto-routes to the right ATS filler (LinkedIn Easy Apply / Greenhouse / Lever / Jobvite / Ashby), dry-run by default, renders an emoji-tagged result table. Proactively invoke this skill (do NOT answer conversationally) when the user pastes a LinkedIn/Greenhouse/Lever/Jobvite/Ashby job URL (with or without the word "apply"), says "apply to this", "try this one", "fill the form", "run the filler", "can you apply for me", "submit this application", drops a job posting into chat, or invokes /job-apply.
Install
npx vskill@latest install akbardevop/ai-job-agent/job-applySKILL.md
Job Apply
Fills out a job application form on the 5 ATS platforms this repo supports. Default is dry-run — the form is filled but not submitted.
Repo location
Resolve the repo root in this order:
$AI_JOB_AGENT_ROOTenv var~/.claude/skills/ai-job-agent/(gstack-style install — recommended)~/.claude/skills/ai-job-agent/REPO_PATHfile (legacy, when repo is elsewhere)~/ai-job-agent/(legacy manual-clone fallback)
Check for package.json in the candidate path to confirm it's really the repo. Fail with a clear message if none exist.
Workflow
1. Parse $ARGUMENTS
Expect <URL> [--submit]. If no URL, ask the user for one.
2. Route by URL host
| Host pattern | Script | |
|---|---|---|
linkedin.com/jobs/view/* | scripts/linkedin-easy-apply.js | |
boards.greenhouse.io/* or job-boards.greenhouse.io/* | scripts/greenhouse-apply.js | |
jobs.lever.co/* | scripts/lever-apply.js | |
jobs.jobvite.com/* or *.jobs.jobvite.com/* | scripts/jobvite-apply.js | |
jobs.ashbyhq.com/* or ashbyhq.com/* | scripts/ashby-apply.js |
If the URL doesn't match, print the table of supported hosts and stop.
3. Check config
For LinkedIn: config/linkedin-config.json must exist. For the other four: the user provides a second argument pointing to their form config JSON (per-job, by convention).
If missing, tell the user to run bash wizard.sh (for LinkedIn) or point to their filled form config.
4. Run the filler
Dry-run by default:
With --submit, set autoSubmit: true in the config temporarily (or instruct the user to — do not silently flip it without confirming). Prefer: ask the user to set it themselves if they haven't, to preserve the truthfulness guardrail baked into CLAUDE.md.
Environment variables to surface:
HEADLESS=0if the user wants to watch the browserKEEP_OPEN_ON_BLOCK=1if they want to inspect a stalled formCDP_URLif they want to connect to an already-open Chrome
5. Parse the script's JSON output
All five fillers emit structured JSON on stdout. Exit codes:
| Code | Meaning | |
|---|---|---|
| 0 | Success (submitted, or ready in dry-run) | |
| 1 | Crash / unexpected error | |
| 2 | Blocked on unknown required field | |
| 3 | CAPTCHA or submission timeout | |
| 4 | Step limit exceeded (LinkedIn only) |
6. Render result table
Show the user a compact markdown table:
| Field | Value | |
|---|---|---|
| Company | … | |
| Role | … | |
| Platform | LinkedIn / Greenhouse / Lever / Jobvite / Ashby | |
| Result | ✅ submitted / ⏳ dry-run filled / 🚫 blocked / 🤖 captcha / 💥 crash | |
| Exit code | 0 / 1 / 2 / 3 / 4 | |
| URL | <url> |
Pick the single emoji that matches the exit code, don't list all four — one of ✅ ⏳ 🚫 🤖 💥 in the Result cell.
Then ask: "Log this to the tracker? (y/n)" — if yes, append a row to application-tracker.csv with the columns in templates/tracker.template.csv, then optionally kick off /job-track to sync.
Rules (from root CLAUDE.md)
- Truthfulness first — CAPTCHA stalls are logged as
blocked, neversubmitted. - Skip hard citizen/green-card gated roles unless the form provides a truthful path.
- Resume routing — software/AI roles use the software resume; EE/embedded roles use the EE resume. See
config/candidate-profile.mdfor the mapping.
Security
- Security scanPassed, 100 of 100Pattern checks on the skill's files.
- Model reviewNot runA model review is scheduled for the next rescan.
Quality evaluation
- Task evaluationNot runNo evaluation yet. Run one in Skill Studio.
Source
- SKILL.md in the repositoryCheckingskills/job-apply/SKILL.md
Popularity
- 7-day trend score
- 0
Not refreshed yet.
Works with
Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.
- Claude Code
- Cursor
- GitHub Copilot
- Windsurf
- Codex
- Gemini CLI
- Cline
- Amp
- Roo Code
- Goose
- Continue
- Kilo Code
- Junie
- Trae
- OpenHands
- Qwen Code
- AI Agent
- Tabnine Chat
- Sourcegraph Cody
- Amazon Q
- Firebase Genkit
- Sweep
- Devin
- Phind
- Mentat
- Claude Desktop
- Aider
- GPT Pilot
- Plandex
- bolt.new
- v0
- Replit Agent
- Anse
- TypingMind
- BetterChatGPT
- LibreChat
- Warp AI
- Pieces
- Fig AI
Embed badge
[](https://verified-skill.com/skills/akbardevop/ai-job-agent/job-apply)