A job-search workflow that finds daily listings, compares them with a user's profile, writes cover letters, and supports applications through a web dashboard. It also records application history.

Use it to run job searches, review and approve listings, tune a profile, generate cover letters, prepare application folders, and view or delete application-history records.

It reduces the repeated work of searching for suitable jobs, tailoring applications, and tracking what has already been submitted.

How PARK0301/job-agent configures Cursor

Reuse

Borrowing it

Nothing to install: this file belongs to PARK0301/job-agent. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/PARK0301/job-agent/main/.cursor/skills/job-hunt/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/PARK0301/job-agent

Made for: Cursor.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/skills/park0301/job-agent/job-hunt/github.svg)](https://agentmods.dev/skills/park0301/job-agent/job-hunt)

Your own site

<a href="https://agentmods.dev/skills/park0301/job-agent/job-hunt"><img src="https://agentmods.dev/badge/skills/park0301/job-agent/job-hunt/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/skills/park0301/job-agent/job-hunt"><img src="https://agentmods.dev/badge/skills/park0301/job-agent/job-hunt.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 38 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,491 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5.1	$0.00038	$0.01491
Opus 5	$0.00019	$0.00745
Sonnet 5	$0.00008	$0.00298
Haiku 4.5	$0.00004	$0.00149

Measured 11d ago against content hash a78156ac17e8, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

job-hunt scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 11d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.cursor/skills/job-hunt/SKILL.md · 120 lines

How it starts

The opening of the file, as written. The whole thing — 120 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Job Hunt Skill

Paths (fixed)

Project root: ~/job-agent
Profile: ~/job-agent/profile/profile.json
Answers: ~/job-agent/profile/answers.json
Today jobs: ~/job-agent/jobs/today.json
Cover letters / application folders: ~/job-agent/applications/{company}_{role}/ (config applications_dir; override in config.yaml)

Desktop daily launcher (no Terminal)

Install once:

cd ~/job-agent && ./scripts/install_desktop_shortcut.sh

Job Hunt.app → starts debug Chrome + opens http://127.0.0.1:8787 (dashboard only; start hunts with Run job search).

In the dashboard: Prepare apply environment → one-time LinkedIn + SEEK login → then approve jobs (no Terminal needed).

Prefer the web UI over Terminal prompts. Canvas sidecars stay in sync for Cursor:

daily-jobs.canvas.tsx
profile-tune.canvas.tsx
applied-history.canvas.tsx

Applied history tab: compact table (company, title, link, status, date) + expandable row detail; multi-delete / single delete → DELETE /api/applications {job_ids}.

Onboarding / continuous tune

If profile/profile.json has placeholder name Your Name or empty/placeholder email ([email protected]), run onboard or tune before hunting:

cd ~/job-agent
python -m src.cli onboard     # field-by-field wizard
python -m src.cli tune        # OpenAI asks about CV/profile gaps; re-run anytime
python -m src.cli tune --once # up to 3 top questions

Or ask the user in chat for: name, email, skills, years, target_roles, target_countries, salary_min, visa_status, dealbreakers, linkedin_url, prefer_remote, notice_period — then save to profile/profile.json / answers.json.

Daily hunt checklist

- [ ] Load profile.json — if placeholder, run onboard/tune first
- [ ] Prefer: python -m src.cli launch  (or Desktop Job Hunt.command)
- [ ] Search jobs (LinkedIn + JobsDB — default HK sources in config.yaml)
- [ ] OpenAI match each job (gpt-4o-mini); threshold 60 in config.yaml
- [ ] Filter score below threshold and dealbreakers
- [ ] Save jobs/today.json + daily_report.md
- [ ] Sync Canvas: automatic via hunt/launch, or `python scripts/sync_canvas.py`

Read the full file on GitHub · 120 lines

Files

What ships with it

5 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

11d ago First seen · 120 lines · 38 tokens per session scan A a78156ac17e8

Subscribe to this mod's changes

job-hunt is a skill published in the GitHub repository PARK0301/job-agent (0 stars, last pushed 1mo ago), licensed MIT. It adds 38 tokens to every session and 1,491 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Productivity ai-agent automation mcp openai playwright

playwright-praman-sap-testing

Playwright plugin for SAP UI5 test automation. Provides fixtures for UI5 control discovery, SAP authentication (BTP SAML, Basic, Office365), FLP navigation, OData V2/V4 data access, Fiori Elements testing (ListReport, ObjectPage), AI-powered test generation, and business intent APIs (Procurement MM, Sales SD, FI, PP).…

mrkanitkar/playwright-praman · 115 tokens

job-agent: Skill for Cursor

Borrowing it

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

Job Hunt Skill

Paths (fixed)

Desktop daily launcher (no Terminal)

Onboarding / continuous tune

Daily hunt checklist

What ships with it

What this file has done since we first saw it

Other skills, from other repositories

playwright-praman-sap-testing

gws-gmail

recipe-save-email-attachments

peekaboo

bear-notes

happiness-skill