Scrape G2, Capterra, and Trustpilot reviews for your product and competitors, then extract recurring themes, objections, proof points, and exact customer language for use in messaging. Chains review-site-scraper with LLM analysis. Produces a weekly or monthly digest that feeds directly into copywriting, positioning, and sales enablement.
SkillScore78Maintained
Automatic
◆Marketing & Content pack
Last verified 8/16/2026
What it changes
Passed 18 of 23 test cases with the skill, and 10 of 23 without it.
Without skill43%
With skill78%
Checks it passed that the model alone missed
Sets the historical timeframe parameter to 90 days.
Specifies --output json to generate structured JSON output.
Uses the APIFY_API_TOKEN environment variable for authentication.
and 8 more in the full report
9 fixed9 passed either way4 still failing1 broke
Pass-rate lift
+35 pp
Tokens
+48%
Agent turns
0%
Response time
-51%
Model gemini-3.6-flashMeasured 8/16/2026v118 of 23 cases passed with skill
Tokens, turns and time describe resource use, not a dollar price.
See it in action
One of 9 test cases the skill fixed. Same model, same prompt, with and without the skill.
1 of 9
Prompt
The review scraper relies on Apify scrapers for Capterra and Trustpilot. What environment variable name must be set to authenticate API calls to Apify?
What was checked, without and with the skill
Checked
Without skill
With skill
Uses the APIFY_API_TOKEN environment variable for authentication.
Missed
Passed
case-12 · 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.md214 linessingle file
Review Intelligence Digest
Scrape reviews for your product and top competitors, then extract what actually matters for marketing: the exact language customers use, recurring pain points, proof points that convert, and objections to pre-empt.
Core principle: Your best marketing copy is already written — by your customers, in their reviews. This skill surfaces it.
When to Use
"What are customers saying about us vs competitors?"
"Find proof points and objections from our G2 reviews"
"What language do our customers use to describe the problem we solve?"
"Run a review audit for [client]"
"What are [competitor]'s customers complaining about?"
Phase 0: Intake
Your product name + review page URLs (G2, Capterra, Trustpilot — any/all)
Competitor names + their review page URLs (1-3 competitors recommended)
What are you trying to learn? (Pick primary focus or do all):
Messaging mining — extract ICP language and proof points
Competitive displacement — find competitor pain points to exploit
Objection mapping — identify what's stopping people from buying/staying
Feature gaps — what do customers wish existed?
Time range: last 3 months (default), last 6 months, or all time?
Phase 1: Scrape Reviews
Run review-site-scraper for your product and each competitor: