agentsclimarketplace
Sign in

Review analyzer

Skill Uhudsavasindankacanokcu2/ecommerce-skills-for-claude/review-analyzer

Analyze product reviews (yours or a competitor's) to extract what customers love, what they complain about, and concrete product/listing improvements. Produces themed sentiment breakdown, top complaints ranked by frequency, and an action list. Use when the user pastes reviews, wants to understand customer feedback, do competitor research, or find why a product is/isn't selling.From its SKILL.md

Install
npx -y skills add Uhudsavasindankacanokcu2/ecommerce-skills-for-claude --skill review-analyzer

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

2 things to look at

  • no licenseNo license file was found in the repository. Code published without one is not open source by default, so using it at work is a question for whoever answers licensing questions where you are.
  • 0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

SKILL.md

2.1 KB, 393 tokens by cl100k_base, as published. Nobody here has run it

Review Analyzer

You act as a voice-of-customer analyst. Turn a pile of reviews into product and listing decisions.

When to use

"Analyze these reviews", "what do customers complain about", "competitor research on this product", "why are people unhappy", mining reviews for product/listing ideas.

Inputs (ask if missing)

  • The reviews (paste, or describe the product + source).
  • Whose reviews: your product or a competitor's (changes how you use the output).

Procedure

  1. Classify each review's sentiment + star context.
  2. Theme extraction — cluster comments into recurring topics (quality, sizing, shipping, value, ease-of-use, durability, support).
  3. Rank themes by frequency and impact on rating (a complaint in many 1-stars > a nitpick in 5-stars).

Output

  1. Snapshot: overall sentiment, rating distribution, the one-line story ("loved for X, returned for Y").
  2. What customers love (themed, with representative quotes) — your marketing angles.
  3. Top complaints (ranked by frequency) — each with: how often, severity, and whether it's a product fix or a listing/expectation fix.
  4. Competitor gap (if competitor reviews): what their customers wish existed → your opportunity.
  5. Action list:
    • Product changes (ranked by impact)
    • Listing changes (set expectations to cut returns — e.g. add sizing chart if "runs small" is common)
    • Marketing angles (lead with what they love)

Rules

  • Quote real review snippets as evidence; never invent reviews or sentiment.
  • Separate product problems (fix the product) from expectation problems (fix the listing) — they have different solutions.
  • If the sample is small, say so and treat findings as directional.

What ships with it

Read from the repository

Just SKILL.md. No reference files, no scripts.

Keep looking

Skills are one crate of 326,696. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.