Scrapes LinkedIn job postings using the JobSpy library (python-jobspy). Use this skill whenever the user wants to find jobs on LinkedIn, search for open roles, pull job listings, build a job pipeline, source job targets for GTM research, or monitor hiring signals. Even if the user just says "find me some jobs" or "what roles is [company] hiring for", use this skill. It runs a local Python script that outputs a CSV of job postings with title, company, location, salary, job type, description, and direct URLs.
インストールする前に、エージェントに与えられる指示の中身を確認できます。
This skill finds LinkedIn job postings by running tools/jobspy_scraper.py, a thin wrapper
around the JobSpy library. It handles installation,
parameter construction, execution, and result interpretation.
Install the dependency once (requires Python 3.10+):
python3.12 -m pip install -U python-jobspy --break-system-packages
Run the scraper:
python3.12 tools/jobspy_scraper.py \
--search "software engineer" \
--location "San Francisco, CA" \
--results 25 \
--output .tmp/jobs.csv
Results are saved as CSV and printed as a summary table.
Identify from the user's message:
hours_old filter if user wants recent posts (e.g. "last 48 hours")linkedin_company_ids if targeting a specific company--fetch-descriptions if user needs job description textIf anything is ambiguous (e.g. "find AI jobs"), pick reasonable defaults and tell the user what you used.
Build the tools/jobspy_scraper.py command using the parameters below.
Always save output to .tmp/ so it's disposable and easy to find.
python tools/jobspy_scraper.py \
--search "<term>" \
--location "<location>" \
--results <N> \
[--hours-old <N>] \
[--fetch-descriptions] \
[--company-ids <id1,id2>] \
[--job-type fulltime|parttime|contract|internship] \
[--remote] \
--output .tmp/<descriptive_filename>.csv
Note: --hours-old and --easy-apply cannot be used together (LinkedIn API constraint).
Execute the command. The script will print a progress message and a summary of results found.
If the script is not found at tools/jobspy_scraper.py, check whether the file needs to be created
by reading skills/linkedin-job-scraper/scripts/jobspy_scraper.py and copying it to tools/.
After the run:
| Flag | Description | Default |
|---|---|---|
--search | Job title / keywords | required |
--location | City, state, or country | none |
--results | Number of results to fetch | 25 |
--hours-old | Only jobs posted within N hours | none |
--fetch-descriptions | Fetch full job descriptions (slower) | false |
--company-ids | Comma-separated LinkedIn company IDs | none |
--job-type | fulltime, parttime, contract, internship | any |
--remote | Filter for remote jobs only | false |
--output | Path for CSV output | .tmp/jobs.csv |
The CSV output includes:
| Column | Description |
|---|---|
TITLE | Job title |
COMPANY | Employer name |
LOCATION | City / State / Country |
IS_REMOTE | True/False |
JOB_TYPE | fulltime, contract, etc. |
DATE_POSTED | When the listing was posted |
MIN_AMOUNT | Minimum salary |
MAX_AMOUNT | Maximum salary |
CURRENCY | Currency code |
JOB_URL | Direct link to the LinkedIn posting |
DESCRIPTION | Full job description (if --fetch-descriptions used) |
JOB_LEVEL | Seniority level (LinkedIn-specific) |
COMPANY_INDUSTRY | Industry classification |
Find recent engineering roles at a startup:
python tools/jobspy_scraper.py --search "growth engineer" --location "New York" \
--results 50 --hours-old 72 --output .tmp/growth_eng_nyc.csv
Monitor what a specific company is hiring for:
# First find the LinkedIn company ID from the company's LinkedIn URL
python tools/jobspy_scraper.py --search "engineer" --company-ids 1234567 \
--results 100 --fetch-descriptions --output .tmp/company_hiring.csv
Find remote contract roles:
python tools/jobspy_scraper.py --search "data analyst" --remote \
--job-type contract --results 30 --output .tmp/remote_contracts.csv
| Error | Fix |
|---|---|
ModuleNotFoundError: jobspy | Run pip install -U python-jobspy |
| 0 results returned | Broaden search term, remove location, increase --results |
| Rate limited / blocked | Wait a few minutes; avoid running back-to-back large scrapes |
hours_old and easy_apply cannot both be set | Remove one of those flags |
The scraper script lives at tools/jobspy_scraper.py.
If it doesn't exist, copy it from skills/linkedin-scraper/scripts/jobspy_scraper.py to tools/:
cp skills/linkedin-job-scraper/scripts/jobspy_scraper.py tools/
まだレビューはありません。使ってみた感想をお寄せください。
概要と使いどころ
Research supported advertising promises from a specific buyer's context, current product facts, customer language and observed ads. Turn them into static, video or copy ideas; match video ideas to actual recipes and save a product-scoped angle bank for write-video-ad-script. Product-led discovery can use verified facts without reviews. Reference persistence and reach are observations, not proof of performance.
日本語の概要は準備中です。原文の説明を表示しています。
Analyze ad campaign performance data (Google, Meta, LinkedIn) to identify what's working, what's wasting budget, and specific cut/scale/test recommendations. Runs statistical analysis, funnel diagnostics, and multi-channel budget reallocation with specific dollar-amount shift recommendations and scenario modeling.
日本語の概要は準備中です。原文の説明を表示しています。
For paid lead-gen and participant-recruitment ads, replaces vanity CPA with true CAC per qualified lead by joining ad-platform data with downstream funnel events, surfaces tracking gaps, and classifies every creative into Scale / Keep / Investigate / Cut.
日本語の概要は準備中です。原文の説明を表示しています。
The intake stage of a Meta ad harness. Researches the brand first, states what it assumes, and asks only what it cannot infer and what would change money, claims or legal exposure if guessed wrong — at most four questions a turn, in plain business language. Writes the brand's stable facts (ads/brand.md), the campaign brief, and a log of what was asked vs assumed. Use it when someone wants to run Meta ads and the brand's ad facts are not yet recorded.
日本語の概要は準備中です。原文の説明を表示しています。
Analyze the message match between your ads and landing pages. Checks if the promise in the ad copy carries through to the landing page headline, body, and CTA. Flags disconnects that kill conversion rates. Works with Google, Meta, and LinkedIn ads.
日本語の概要は準備中です。原文の説明を表示しています。
Turn a brand's facts, a campaign brief and the product into a one-minute Meta ad strategy with its reasoning — goal, audience, objective and placements, budget split, how many ads and how different they must be (generate 3x so the user can choose), the test frame, the success metric, and safety rules for the user to accept. Decides what launch-meta-ad-campaign then executes, and re-reads the strategy after a deep check to show which assumption changed. Use it after intake and before any creative is generated or any campaign is built.
日本語の概要は準備中です。原文の説明を表示しています。