Daily industry intelligence scanner. Scans web, social media, news, blogs, and communities for industry-relevant events, trends, and signals. Produces a comprehensive intelligence briefing plus strategic GTM opportunity ideas. Orchestrates existing scraping skills — does not reimplement data collection.
SkillScore77Maintained
Automatic
◆Sales & GTM pack
Last verified 8/16/2026
What it changes
Passed 15 of 19 test cases with the skill, and 3 of 19 without it.
Without skill14%
With skill77%
Checks it passed that the model alone missed
Passes `--days 1 --output json`
Passes `--days 7 --output json`
Sets `--max-tweets 30 --output json`
and 19 more in the full report
14 fixed3 passed either way5 still failing0 broke
Pass-rate lift
+64 pp
Tokens
+165%
Agent turns
0%
Response time
-25%
Model gemini-3.6-flashMeasured 8/16/2026v117 of 22 cases passed with skill · 19 comparable
Tokens, turns and time describe resource use, not a dollar price.
See it in action
One of 14 test cases the skill fixed. Same model, same prompt, with and without the skill.
1 of 14
Prompt
When scanning LinkedIn posts during a weekly deep research run for 'SaaSMetrics', what date posted parameter should be passed to the research delegate tool?
What was checked, without and with the skill
Checked
Without skill
With skill
Uses `date_posted: "past-week"` for the weekly scan
Missed
Passed
case-11 · gemini-3.6-flash · 8/16/2026 · answers are capped and redacted
What's inside
The instructions your model reads when the skill loads.
SKILL.md359 lines2 files
Industry Scanner
Daily deep-research agent that scans the internet for everything relevant to a client's industry, then generates strategic GTM opportunities based on what it finds.
Quick Start
Run an industry scan for <client>. Use the config at clients/<client>/config/industry-scanner.json.
Or for a weekly deeper scan:
Run a weekly industry scan for <client> with --lookback 7.
Inputs
Client name — determines which config and context files to load
Lookback period (optional) — 1 for daily (default), 7 for weekly deep scan
Focus area (optional) — limit scan to specific categories (e.g., "competitors only", "events only")
Step-by-Step Process
Phase 1: Load Configuration
Read clients/<client>/config/industry-scanner.json — this contains all the keywords, sources, competitors, and URLs to scan
Read clients/<client>/context.md — need the ICP, value props, and positioning to generate relevant strategies
Set the lookback period: use 1 day for daily scans, 7 for weekly, or whatever the user specifies
Note today's date for the output filename
If no client config exists, ask the user for the key inputs and offer to create one from the example at skills/industry-scanner/config/example-config.json.
Phase 2: Data Collection
Run these data sources in parallel where possible. Skip any source that isn't configured. For each source, use the existing skill's CLI or tool as documented.
IMPORTANT: Run as many of these bash commands in parallel as possible to minimize total scan time. Sources are independent of each other.
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.