DEV Community: krammer liu

I made Claude Code read job posts against my resume every morning (and it never clicks Apply)

krammer liu — Fri, 13 Nov 2026 01:24:16 +0000

Looking for a job has two slow parts. Reading 30 new postings a day to find the 3 that fit. Then changing your resume for each one.

Both parts are reading and matching text. An LLM is good at that. So I wrote a Claude Code skill that does this every morning:

1. Get new jobs
   │
2. Score each job against your resume
   │
3. Check Gmail: did you already apply?
   │ no
4. Pick resume points to highlight
   │
5. Write a cover letter        (next post)
   │
6. You click Apply             (always you)

Steps 1 to 4 are in this post. Step 6 stays with you. More on that below.

What you get

One Markdown file per day. This is part of a real one (2026-11-12, Seattle, backend roles, with a sample resume). I wrapped the long lines:

# Job hunt: 2026-11-12

28 new jobs. 8 to apply (score 7+), 0 already applied, 20 below 7.

### 1. Senior Backend Engineer, FinTech Lending Platforms
###    at Coinbase, Inc. (9/10)

- Why it fits:
  - Senior backend; requires Go or Java and cloud-native
    tools; resume has Go on AWS
  - Lending and real-time tracking in distributed systems;
    resume has payments platform
- Gaps:
  - Lending and risk domain
- Highlight on your resume:
  - Go services on AWS (Example Payments)
  - Kafka pipeline for payment events, 2M events per second
  - On-call lead for the payments platform
- Apply: https://...

The 20 jobs below 7 go into one table with a single reason each ("Graduate role for 2025 CS graduates", "Requires a Master's degree; resume has a B.S."). You can see what was dropped and why.

How it works

The skill is a SKILL.md and two small Python scripts. Code and LLM each do what they are good at:

Step	Who does it	Why
Get jobs, drop the ones you saw	`fetch_jobs.py`	Same input, same output. No reason to ask a model.
Score 0-10, reasons, gaps	Claude	Needs reading and judgment.
Check Gmail	Claude + Gmail tool	Needs judgment: a job alert is not an application.
Resume points	Claude	Only points that are already in the resume.
Check the scores, write the list	`report.py`	Catches a missing score or an unchecked top job, then Claude fixes it.

The scoring rubric is in the skill, so scores mean the same thing every day:

0-3   wrong role or a hard blocker
      (seniority off by 2+ levels, location,
       missing skill family)
4-6   same role family, 1-2 core requirements missing
7-8   meets the core requirements,
      at most 1 nice-to-have missing
9-10  meets core and most nice-to-haves,
      and the level fits

report.py is the part I like most. Claude writes the scores to a JSON file. The script refuses it if a job has no score, a score is not 0-10, a top job was not checked in Gmail, or a top job has no resume points. It prints the problems, Claude fixes them, and it runs again. The jobs go into seen.json only after the list is written, so a failed run loses nothing.

The jobs come from Google Jobs (the job panel in Google Search). Google has no API for it, so step 1 uses my Google Jobs Scraper on Apify. The first post shows that part.

Why it does not click Apply

I thought about it. I decided no, for three reasons:

Your accounts. LinkedIn and Indeed do not allow bots to apply. You can lose the account you need most right now.
Every form is different. Workday, Greenhouse, Lever and company forms all ask different questions. That is more work than steps 1 to 5 together, and it breaks often.
It does not help. Sending 200 weak applications is worse than sending 5 good ones. The slow part was never clicking the button.

So the skill picks and prepares. You read the list over coffee and apply to the 2 or 3 that are worth it.

Things I learned from real data

Use datePosted: 7d, not 24h. I started with "jobs from the last 24 hours". Google returned 30 results per search, but only 1 was from the last 24 hours. The date filter runs on the results Google returns, so you pay for the same pages and keep much less. With 7d and seen.json you get the same "only new jobs" effect and many more jobs.

Update (2026-11-13): the Actor now sends the date filter to Google too, and you pay only for result pages that put at least one job into your dataset. A test run with 24h ("registered nurse", Chicago) returned 25 jobs, all from the last 24 hours, on 4 pages. 7d with seen.json is still what the skill uses, because Google sometimes lists a job a few days after it was posted.

The company name is sometimes a reposting site. One job said "MeeBoss", but the text said TestSprite. Another said "Nubeero Limited" for a Stripe job. So the skill tells Claude to search Gmail for the employer named in the description, not the company field.

Many apply links are reposting sites. In this run, 7 of the 8 jobs to apply to had only reposting links. The script ranks links (company page or ATS first, big job boards next, reposts last) and marks a job when it found only reposts, so you know to look for it on the company careers page.

Search Gmail by subject. My first query matched newsletters and LinkedIn salary reports. "<employer>" subject:(application OR applying OR applied) works much better.

Try it

git clone https://github.com/krammer0/google-jobs-scraper-examples.git
cd google-jobs-scraper-examples
cp -r job-hunt ~/.claude/skills/job-hunt
mkdir -p ~/job-hunt
cp job-hunt/job-hunt.example.json ~/job-hunt/job-hunt.json
cp my-resume.md ~/job-hunt/resume.md
pip install apify-client
export APIFY_TOKEN=<your token>
claude "/job-hunt"

Edit queries, locations and notes in job-hunt.json first. No Gmail tool in Claude Code? Set "maxGmailChecks": 0.

Cost: one search of 30 jobs is about 3 to 4 result pages, $0.028 to $0.09 per page on Apify. Claude runs in your own Claude Code, so there is no extra API key.

Next post: step 5, a cover letter and form answers for the top jobs. Tell me in the comments what you want it to do.

How to get Google Jobs listings as JSON with Python (with salary data)

krammer liu — Thu, 12 Nov 2026 07:33:57 +0000

When you search "data engineer jobs in Austin" on Google, you get the job panel: postings from LinkedIn, Indeed, company career pages and many smaller boards, merged in one list. This is Google Jobs (also called Google for Jobs).

It is a very good data source. The problem: Google does not offer an API for it. (Google Cloud Talent Solution is a different product. It searches your own job postings, not Google's.)

So the usual options are:

Scrape it yourself. Google blocks automated requests fast. You need proxies, retries, and parsing code that you fix every time Google changes the page.
Use a SERP API subscription. It works, but most plans are monthly subscriptions, and you get the raw text: "$150K–$200K a year", "3 days ago". You still parse it.
Use a ready-made scraper and pay per use. This is what this post shows.

The 10-line version

I built a Google Jobs Scraper on Apify. You give it search queries and locations; it returns one JSON item per job posting.

pip install apify-client
export APIFY_TOKEN=<your token>   # free account: Apify Console > Settings > API & Integrations

import os
from apify_client import ApifyClient

client = ApifyClient(os.environ["APIFY_TOKEN"])
run = client.actor("krammer/google-jobs-scraper").call(run_input={
    "queries": ["data engineer"],
    "locations": ["Austin, TX"],
    "country": "us",           # us, gb, in, de
    "datePosted": "7d",        # any, 24h, 3d, 7d, 30d
    "maxResultsPerSearch": 50, # 1 to 200
})
for job in client.dataset(run["defaultDatasetId"]).iterate_items():
    print(job["title"], "|", job["company"], "|", job["salaryMin"], job["salaryMax"])

What you get back

One item per posting (abridged, company name replaced):

{
  "job_id": "RtLv7vlPTbn2E40SAAAAAA==",
  "title": "Staff Software Engineer - Card Technology",
  "company": "Example Corp",
  "location": "New York, NY (+3 others)",
  "description": "Example Corp is hiring a Staff Software Engineer ...",
  "apply_options": [{ "title": "Example Corp Careers", "link": "https://careers.example.com/jobs/12345" }],
  "salary": "$150K–$200K a year",
  "posted": "3 days ago",
  "salaryMin": 150000,
  "salaryMax": 200000,
  "salaryCurrency": "USD",
  "salaryPeriod": "year",
  "postedDate": "2026-11-05",
  "jobTypes": ["FULLTIME"],
  "workMode": null
}

The raw Google text is kept (salary, posted), and the Actor also parses it into fields you can sort and filter on: salaryMin, salaryMax, salaryCurrency, salaryPeriod, postedDate, jobTypes and workMode (remote or hybrid). Postings that do not show a salary on Google have null there.

Three things to build with it

The full scripts are in this repo: krammer0/google-jobs-scraper-examples. search_jobs() below is the 10-line call above, wrapped in a function (common.py).

1. Compare salaries across cities

Search one role in several cities and take the median of the yearly ranges:

from statistics import median

jobs = search_jobs(["data engineer"], ["New York, NY", "Austin, TX", "Seattle, WA"])
yearly = [j for j in jobs if j["salaryPeriod"] == "year" and j["salaryCurrency"] == "USD"
          and j["salaryMin"] is not None and j["salaryMax"] is not None]
for city in {j["searchLocation"] for j in yearly}:
    js = [j for j in yearly if j["searchLocation"] == city]
    print(city, len(js), median(j["salaryMin"] for j in js), median(j["salaryMax"] for j in js))

2. Find the companies that are hiring

Recruiters and sales teams use this to see who is hiring for what, and where:

from collections import Counter

jobs = search_jobs(["registered nurse"], ["Chicago, IL"])
for company, count in Counter(j["company"] for j in jobs).most_common(20):
    print(count, company)

3. Daily job alerts without duplicates

Run with datePosted: "24h" once a day and keep the job_id values you have already seen:

fresh = [j for j in search_jobs(["python developer"], ["London"], country="gb", datePosted="24h")
         if j["job_id"] not in seen]

You can schedule the run in Apify Console, or call it from cron, n8n or an AI agent (the Actor works with the Apify MCP server).

What it costs

You pay per Google results page (up to 10 jobs): $0.028 to $0.09 per page, depending on your Apify plan. Searches that return nothing are free. For example, 50 jobs is about 5 pages, so $0.45 or less on the Free plan, and Apify's free plan includes monthly credit to try it.

Supported countries right now: United States, United Kingdom, India and Germany.