agentleFS
surfmind-spacesurfmind-space/awesome-surfmind/skills/product-review-summarizer/SKILL.md

product-review-summarizer

Skill8 starsChanged 5 months agoMITView on GitHub

Summarizes product reviews into recurring pros, cons, reliability issues, buyer-fit notes, and repeated red flags. Use when the user asks to summarize, analyze, or compare product reviews, customer feedback, ratings, or user reviews on a store, app, restaurant, or marketplace listing.

The file

We split this skill into the rules it gives an agent

1 rule. About 0 are common, 1 is distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Call out reliability, quality control, support, delivery, sizing, compatibility, or safety issues when they recur.

    line 18

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Review Summarizer

Condense a pile of reviews into the patterns that matter for a buying decision — recurring pros and cons, reliability issues, who it fits, and the red flags that show up again and again. Work only from the reviews actually present, and don't treat one dramatic review as the verdict.

  1. Identify repeated positive and negative themes instead of over-weighting single dramatic reviews.
  2. Note review recency, product versions, verified-purchase hints, and possible review manipulation when visible.
  3. Call out reliability, quality control, support, delivery, sizing, compatibility, or safety issues when they recur.
  4. Translate vague sentiment into practical buyer-fit guidance, and flag what to check before buying.

If fewer than ~5 reviews are available, note the small sample size prominently and caveat every pattern claim. Return concise headings and include these sections when they fit: Overall pattern, Pros, Cons, Repeated red flags, Best-fit buyer, Questions before buying. Don't invent statistics that aren't visible; if the context is insufficient, say what's missing and give the best supported next step.

Example

Reviews (selected text from a product page):

"Battery died after 3 months." · "Great sound but the app keeps disconnecting." · "Comfortable for small ears." · "Stopped charging in week 6 — second pair with the same issue." · "Love them, perfect for the gym."

Summary:

Overall pattern: Well-liked sound and fit, but a recurring hardware-reliability problem (battery/charging failures within weeks) shows up across multiple reviewers.

Pros

  • Sound quality and comfort praised repeatedly; works well for workouts and smaller ears.

Cons

  • Companion app disconnects mid-use.

Repeated red flags

  • Two separate reviewers report charging/battery failure within 3–6 weeks — a pattern, not a one-off.

Best-fit buyer: Someone who wants comfortable gym earbuds and values sound over long-term durability.

Questions before buying: What's the warranty and return window? Are the charging complaints addressed in a newer firmware or hardware revision?

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.