Search LinkedIn job postings for roles tied to a product’s problem area, group results by company, and qualify potential leads using posting volume and seniority. The output includes reasons, suggested decision-maker roles, and personalization context in a Google Sheet; it does not contact prospects.
Detect buying intent from job postings. When a company posts a job in your problem area, they've allocated budget and are actively thinking about the problem. This skill finds those companies, qualifies them, extracts personalization context, and outputs everything to a Google Sheet. Does NOT do outreach — just delivers qualified leads with reasoning.
Run score Not tested
See how to installReview the instructions the agent will receive before you install.
Find companies that are hiring for roles related to the problem you solve. A job posting is a budget signal — the company has allocated money to solve a problem your product addresses.
Results are automatically exported to a Google Sheet with signal strength, decision-maker suggestions, outreach angles, and personalization context.
When a company posts a job, they've:
If your product helps solve that problem faster, cheaper, or better than a hire alone, the timing is perfect.
Apify Actor: harvestapi/linkedin-job-search (pay-per-event)
| Component | Cost |
|---|---|
| Actor start (per run) | $0.001 |
| Per job result | $0.001 |
| Apify platform fee | +20% |
Typical run costs:
| Scenario | Titles | Jobs/title | Runs | Est. Cost |
|---|---|---|---|---|
| Quick scan | 3 | 25 | 3 | ~$0.09 |
| Standard | 5 | 25 | 5 | ~$0.16 |
| Deep search | 5 | 100 | 5 | ~$0.60 |
| Multi-location | 5×3 | 25 | 15 | ~$0.47 |
Google Sheet creation is free (uses Rube/Composio integration).
Always run --estimate-only first to see the Apify cost before executing.
Track usage: https://console.apify.com/billing
# Get your token at https://console.apify.com/account/integrations
export APIFY_API_TOKEN="apify_api_YOUR_TOKEN_HERE"
pip3 install requests
Google Sheet creation uses Rube MCP with Composio. Nothing is preconfigured: set the
RUBE_TOKEN env var to your own Rube token before running the sheet step. Without it the
sheet scripts stop with an error; the job search itself still works.
Think about it this way: "If a company is hiring for [role], it means they're investing in [problem area you solve]."
Examples:
python3 scripts/search_jobs.py \
--titles "GTM Engineer,SDR Manager,Head of Demand Gen" \
--locations "United States" \
--max-per-title 25 \
--estimate-only
The script searches LinkedIn Jobs, groups results by company, qualifies leads, and creates a Google Sheet automatically.
# Standard search (creates Google Sheet)
python3 scripts/search_jobs.py \
--titles "GTM Engineer,SDR Manager,RevOps Engineer" \
--locations "United States" \
--max-per-title 25
# Deep search with custom sheet name
python3 scripts/search_jobs.py \
--titles "AI Engineer,ML Ops Engineer,Prompt Engineer" \
--locations "United States" \
--max-per-title 50 \
--sheet-name "AI Hiring Signals - Feb 2026"
# Filter results to only relevant titles (LinkedIn search is fuzzy)
python3 scripts/search_jobs.py \
--titles "GTM Engineer,Growth Marketing Manager,SDR Manager" \
--locations "United States" \
--relevance-keywords "gtm,growth,sdr,marketing,demand gen,revops"
# Also save raw JSON alongside the sheet
python3 scripts/search_jobs.py \
--titles "GTM Engineer,SDR Manager" \
--locations "United States" \
--output results.json
# Skip Google Sheet, console + JSON only
python3 scripts/search_jobs.py \
--titles "GTM Engineer" \
--no-sheet --json
Required:
--titles Comma-separated job titles to search
Optional:
--locations Comma-separated locations (default: no filter)
--max-per-title Max jobs per title per location (default: 25)
--posted-limit Recency: 1h, 24h, week, month (default: week)
--output, -o Also save raw JSON to this file path
--json Print JSON output to console
--estimate-only Show cost estimate without running
--no-sheet Skip Google Sheet creation
--sheet-name Custom Google Sheet title (default: "Job Posting Intent Signals - {date}")
--relevance-keywords Comma-separated keywords to filter truly relevant postings
| Column | Description |
|---|---|
| Signal | HIGH / MEDIUM / LOW based on # postings + seniority |
| Company | Company name |
| Employees | Employee count |
| Industry | Company industry |
| Website | Company website |
| Company LinkedIn URL | |
| # Postings | Number of relevant job postings found |
| Job Titles | The actual job titles posted |
| Job URL | Link to the primary job posting |
| Location | Job location(s) |
| Decision Maker | Suggested title of person to contact |
| Outreach Angle | Accelerate / Replace / Multiply the hire |
| Tech Stack | Technologies mentioned in job descriptions |
| Growth Signals | Growth indicators (first hire, scaling, series stage) |
| Pain Points | Pain indicators (automate, optimize, manual processes) |
| Description | Company description snippet |
When using this skill as an agent, the typical flow is:
--estimate-only and confirms cost with userExample prompt:
"Find companies hiring growth marketers and SDRs in the US this week. These are signals they need GTM help. We sell AI-powered GTM systems to Series A-C B2B SaaS companies with 20-200 employees."
The agent should NOT:
The agent SHOULD:
The script auto-assigns an angle based on job posting context:
"Accelerate while you hire" — Best when: posting is recent, role is junior/mid
They're looking for someone to do X. Your product can deliver X outcomes while they ramp the hire.
"Replace the hire" — Best when: small company, "first hire" signals, building from scratch
They want the output of a [role] but may not need a full-time person if they use your product.
"Multiply the hire" — Best when: company is clearly scaling, multiple related roles
When their new hire starts, your product makes them 10x more effective from day one.
--posted-limit month--relevance-keywords to filter by title keywords--no-sheet --json --output results.json to save results without a sheetscripts/create_sheet_mcp.py--max-per-title (25 is usually enough)--posted-limit 24h for a quick daily scanNo reviews yet. Tell others what you thought.
No login needed. Share how it worked for you, ask a question, or note where it did not run.
No comments yet. Be the first to write one.
The supplied material contains only placeholder text for the skill’s purpose, inputs, steps, and completion criteria. It does not provide enough information to describe a task or result reliably.
Research supported advertising angles using buyer context, current product facts, customer language, and observed ads. Turn the evidence into static ad, video, or copy ideas, matching video concepts to available recipes. Scores rank ideas for testing; they do not predict results.
Analyze campaign data from Google, Meta, and LinkedIn to find strong and wasteful spend. The skill checks funnel performance and test results, then recommends which campaigns to pause, scale, or test and how to shift budget across channels.
Compare ad spend and signups with downstream outcomes to calculate the cost of each qualified lead. The skill checks tracking coverage, accounts for how long leads need to mature, and groups creatives into actionable categories with confidence notes.
Prepare the intake for a Meta ad campaign by reviewing available brand information first, stating reasonable assumptions, and asking only questions whose answers could affect budget, claims, or legal exposure. It records stable brand facts, a campaign brief, and what was asked versus assumed.
Review ad copy, image text, visuals, and people against platform and brand category rules. It suggests honest fixes and needed disclosures, then flags issues requiring human or legal review, with a separate result for each ad and platform.