review-site-scraper

Scrape product reviews from G2, Capterra, and Trustpilot using Apify. Single script with platform dispatch. Use when you need to monitor competitor reviews, track product sentiment, or gather customer feedback from review sites.

Quality

81%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Quality

Content

76%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

Highly actionable content with executable commands, a complete CLI reference, and a real one-level script reference. The main gap is the absence of any validation/verification checkpoint for a batch scraping operation, which caps workflow clarity.

Suggestions

Add a short verification step after the run command, e.g. check the exit code / output file and inspect a sample review to confirm the scrape succeeded before relying on the data.

Trim or externalize the three full JSON output schemas (e.g. move to references/output_schema.md) to reduce inlined bulk and lift conciseness and progressive_disclosure.

Remove the redundant opening sentence that restates the frontmatter description, since the body's first line repeats what the description field already says.

Dimension	Reasoning	Score
Conciseness	The body is mostly lean tables and code blocks with no padding of concepts Claude already knows, but the opening line restates the frontmatter and the three inlined JSON output schemas could be trimmed or externalized, keeping it just below a 5.	4 / 5
Actionability	Quick Start gives copy-paste-ready executable bash commands for all three platforms, the CLI Reference table enumerates every flag with defaults, and the output schemas are concrete JSON — fully executable and covering the common cases per the 5 anchor.	5 / 5
Workflow Clarity	This is a batch scraping operation yet the body provides only the run command with no validation or verification step (e.g., confirming the scrape succeeded or inspecting output for errors); per the rubric's batch-operation rule, workflow_clarity is capped at 3 even though the single action is unambiguous.	3 / 5
Progressive Disclosure	Sections are well organized (Quick Start, Supported Platforms, CLI Reference, Output Schema) and the single bundle file scripts/scrape_reviews.py is referenced by real path at one level deep; the inlined output schemas are slightly heavy for SKILL.md, keeping it just below a 5.	4 / 5
	Total	16 / 20 Passed

Description

87%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong, well-targeted description that clearly states capability and trigger conditions with named platforms and natural use-case language. Minor room to broaden action verbs and trigger synonyms for a marginally higher specificity/trigger score.

Dimension	Reasoning	Score
Specificity	Names the concrete action ('Scrape product reviews'), the specific mechanism ('using Apify', 'platform dispatch'), and three named platforms (G2, Capterra, Trustpilot); only marginally short of comprehensive multi-action coverage, so above the 3 anchor but not a clean 5.	4 / 5
Completeness	Explicitly states both what it does ('Scrape product reviews from G2, Capterra, and Trustpilot using Apify') and when to use it ('Use when you need to monitor competitor reviews, track product sentiment, or gather customer feedback'), matching the 5 anchor's concrete trigger phrasing.	5 / 5
Trigger Term Quality	Natural trigger phrases are present ('monitor competitor reviews', 'track product sentiment', 'gather customer feedback', 'review sites'); coverage is good but misses a few common synonyms a user might say, so between the 3 and 5 anchors.	4 / 5
Distinctiveness Conflict Risk	The niche is clearly delimited to scraping reviews from three named platforms via Apify, with distinct triggers unlikely to fire for unrelated skills, matching the 5 anchor.	5 / 5
	Total	18 / 20 Passed

Validation

100%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: gooseworks-ai/goose-skills
Path: skills/monitoring/capabilities/review-site-scraper/SKILL.md
Commit: 2523432

Reviewed: 7 days ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.