gooseworks-ai/goose-skills / skills/shared/job-posting-intent
job-posting-intent
VerifiedDetect 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.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 8.6 KB |
| scripts/create_sheet.py | script | 3.7 KB |
| scripts/create_sheet_mcp.py | script | 6.1 KB |
| scripts/search_jobs.py | script | 26.7 KB |
| skill.meta.json | config | 173 B |
scripts/create_sheet.py
View on GitHub#!/usr/bin/env python3
"""
Create a Google Sheet with job posting intent results via Rube/Composio API.
"""
import json
import os
import sys
import requests
RUBE_URL = "https://rube.app"
RUBE_TOKEN = os.getenv("RUBE_TOKEN", "")
headers = {
"Authorization": f"Bearer {RUBE_TOKEN}",
"Content-Type": "application/json",
}
def call_rube_tool(tool_name, params):
"""Call a Composio tool via Rube's MCP endpoint."""
if not RUBE_TOKEN:
print("ERROR: RUBE_TOKEN environment variable is not set.")
print("Set it with: export RUBE_TOKEN='your_jwt_token_here'")
sys.exit(1)
resp = requests.post(
f"{RUBE_URL}/api/composio/execute",
headers=headers,
json={"toolName": tool_name, "params": params},
)
resp.raise_for_status()
return resp.json()
def create_sheet(title, header, rows):
"""Create a Google Sheet and populate it."""
# Step 1: Create the spreadsheet
print(f"Creating Google Sheet: {title}")
result = call_rube_tool("GOOGLESHEETS_CREATE_GOOGLE_SHEET1", {"title": title})
data = result.get("data", result)
spreadsheet_id = None
# Try to extract spreadsheet ID from various response formats
if isinstance(data, dict):
spreadsheet_id = data.get("spreadsheetId") or data.get("data", {}).get("spreadsheetId")
if not spreadsheet_id and "response_data" in data:
rd = data["response_data"]
if isinstance(rd, dict):
spreadsheet_id = rd.get("spreadsheetId")
elif isinstance(rd, str):
try:
rd_parsed = json.loads(rd)
spreadsheet_id = rd_parsed.get("spreadsheetId")
except:
pass
if not spreadsheet_id:
print(f"DEBUG: Full response: {json.dumps(result, indent=2)[:2000]}")
print("ERROR: Could not extract spreadsheet ID from response")
sys.exit(1)
sheet_url = f"https://docs.google.com/spreadsheets/d/{spreadsheet_id}"
print(f"Created: {sheet_url}")
# Step 2: Write data
all_values = [header] + rows
print(f"Writing {len(rows)} rows...")
result = call_rube_tool("GOOGLESHEETS_BATCH_UPDATE", {
"spreadsheet_id": spreadsheet_id,
"sheet_name": "Sheet1",
"first_cell_location": "A1",
"values": all_values,
"valueInputOption": "USER_ENTERED",
})
print("Data written.")
# Step 3: Format header
print("Formatting...")
try:
call_rube_tool("GOOGLESHEETS_FORMAT_CELL", {
"spreadsheet_id": spreadsheet_id,
"range": f"A1:{chr(64+len(header))}1",
"bold": True,
"fontSize": 11,
"red": 0.15,
"green": 0.15,
"blue": 0.15,
})
except Exception as e:
print(f" Format warning: {e}")
print(f"\nDone! Sheet URL: {sheet_url}")
return sheet_url
if __name__ == "__main__":
results_file = sys.argv[1] if len(sys.argv) > 1 else None
if not results_file:
print("Usage: python3 create_sheet.py <results.json>")
sys.exit(1)
data = json.load(open(results_file))
# Build sheet data from the qualified results JSON
header = [
"Tier", "Signal", "Company", "Employees", "Industry",
"Website", "LinkedIn", "# Postings", "Job Titles",
"Job URL", "Location", "Decision Maker", "Outreach Angle",
"Tech Stack", "Growth Signals", "Pain Points", "Company Description"
]
# data should already be a list of rows
if isinstance(data[0], list):
rows = data
else:
print("ERROR: Expected pre-formatted rows")
sys.exit(1)
create_sheet("Job Posting Intent Signals - 2026-02-22", header, rows)
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness. | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |