Review Surfacing
by
Review selection for ecommerce teams: pick which reviews to pin on each product page based on the hesitation that page actually has to resolve.
Review widgets sort by recency or by rating, which surfaces whatever arrived last or whatever said five stars and nothing else. Neither corresponds to what a hesitating customer needs to read. The review that converts is the one addressing the specific doubt that page creates: fit on a garment, durability on something expensive, setup time on anything technical. That doubt is knowable from support tickets and site search, and no review widget has access to either. This skill picks which reviews to pin on each product page based on the hesitation that page has to resolve.
What It Does
- Identifies the hesitation each product page has to overcome.
- Scores reviews on how directly they address that specific doubt.
- Prefers a specific four star review over a generic five star one.
- Checks the pinned set covers different objections rather than repeating one.
- Detects when a product's doubts have changed and the pins are stale.
- Sets the pinned reviews per page, with the objection each one answers.
Use Cases
- Replace recency sorting with reviews chosen for what they answer.
- Surface the review that addresses the question support keeps getting.
- Cover three different objections rather than three versions of one.
- Catch pins that have gone stale after a product change.
Example Session
Which reviews should be pinned on the navy jacket page?
None of the current three. They all say the same thing about color.
- Objection | Share of tickets | Best review available | Rating | Pin
- Runs small or large | 28% | Detailed fit note, 5ft9 wearer | 4 stars | Yes
- Warmth for winter | 19% | Wore it at -5C, specific | 5 stars | Yes
- Durability after a season | 14% | 8 months, still good | 4 stars | Yes
- Color accuracy | 3% | Three pinned reviews | 5 stars | Unpin two
All three current pins are about color, which accounts for 3% of hesitation. Fit accounts for 28% and has a detailed four star review sitting on page three that nobody sees. A specific four star review outperforms a generic five star one on conversion because it reads as real, and the fit review answers the question most visitors arrive with.
Why This Beats Prompting It Yourself
Recency Or Rating vs The Objection The Page Creates: The Hidden Risk
A generic prompt sorts by rating and recency, which is what every review widget already does. That surfaces short five star reviews saying nothing, and buries the detailed four star review that answers the question 28% of your customers are actually asking. Sorting cannot see what the page fails to explain.
When You Still Need The Four Star Review
Rating-sorted widgets never show anything below five stars, which is precisely why they convert worse than they could. A specific four star review reads as honest and resolves a real doubt. This skill will pin one over a generic five star, and that is usually the change that moves the page.
Known Limitations
Identifying the hesitation per page needs support tickets or site search attributable to products, and without them the skill falls back to review themes and says the objection ranking is inferred. Review scoring reads text, so it is weaker on very short reviews and on languages outside your configured set. It sets the pins and does not write into your review platform.
Install It
- Download the ZIP.
It is free and there is no account to create. - Unzip it into your agent's skills folder.
Claude Code reads ~/.claude/skills/, which is hidden by default: the command in the folder block opens it. Other agents scan their own directory, so drop the same folder there instead. - Ask your agent to use it.
Restart the agent if it was already running, then it picks the skill up with no config.
skills folder
Copy
~/.claude/skills/review-surfacing/
SKILL.md
references/objection-map.md
pages/
# one file per page, with the pinned set
# macOS: create the folder and open it in Finder
mkdir -p ~/.claude/skills && open ~/.claude/skills
# Windows: paste in the Explorer address bar
%USERPROFILE%\.claude\skills\Frequently asked questions
How is this different from sorting reviews by helpfulness?
Helpfulness votes tell you what previous readers liked, which correlates with the doubts they had rather than the doubts on this page today. This reads support volume and site search to find what the page is failing to explain, then picks reviews that answer it.
Which agents does the skill run in?
Any agent that supports the open SKILL.md format: Claude Code, Cursor, Codex CLI, GitHub Copilot, Gemini CLI, Manus, Grok and others load it unmodified. The format is portable, the location is not. Each agent scans its own skills directory, so you drop the same folder into whichever one yours uses. There is no config file to edit and no API key to provision.
What does it need connected to work?
Your reviews with text and ratings, page-level traffic and conversion, and support tickets or site search tied to products. The tickets are what make objection ranking specific rather than inferred.
Why pin a four star review?
Because a page of identical five star reviews reads as filtered, and a specific four star review that resolves a real doubt converts better than a generic superlative. The skill will not pin anything genuinely negative; it pins the honest and useful.
How often should pins change?
When the product changes, when a new objection appears in support volume, or when the review pool gains something better. The skill flags stale pins rather than requiring a schedule, which is usually a few times a year per page.
What is included with the skill?
The skill itself, the objection map reference, the per-page pin format, and the review scoring rules. It is free and security scanned. We re-publish the ZIP when the scoring changes, so download it again if your pins start shifting.
The review worth pinning is the one that converts.
Polar ties product page behavior to orders and margin in one semantic layer, so the review you surface is chosen on revenue rather than star rating.
<script type="application/ld+json">{"@context":"https://schema.org","@type":"FAQPage","mainEntity":[{"@type":"Question","name":"How is this different from sorting reviews by helpfulness?","acceptedAnswer":{"@type":"Answer","text":"Helpfulness votes tell you what previous readers liked, which correlates with the doubts they had rather than the doubts on this page today. This reads support volume and site search to find what the page is failing to explain, then picks reviews that answer it."}},{"@type":"Question","name":"Which agents does the skill run in?","acceptedAnswer":{"@type":"Answer","text":"Any agent that supports the open SKILL.md format: Claude Code, Cursor, Codex CLI, GitHub Copilot, Gemini CLI, Manus, Grok and others load it unmodified. The format is portable, the location is not. Each agent scans its own skills directory, so you drop the same folder into whichever one yours uses. There is no config file to edit and no API key to provision."}},{"@type":"Question","name":"What does it need connected to work?","acceptedAnswer":{"@type":"Answer","text":"Your reviews with text and ratings, page-level traffic and conversion, and support tickets or site search tied to products. The tickets are what make objection ranking specific rather than inferred."}},{"@type":"Question","name":"Why pin a four star review?","acceptedAnswer":{"@type":"Answer","text":"Because a page of identical five star reviews reads as filtered, and a specific four star review that resolves a real doubt converts better than a generic superlative. The skill will not pin anything genuinely negative; it pins the honest and useful."}},{"@type":"Question","name":"How often should pins change?","acceptedAnswer":{"@type":"Answer","text":"When the product changes, when a new objection appears in support volume, or when the review pool gains something better. The skill flags stale pins rather than requiring a schedule, which is usually a few times a year per page."}},{"@type":"Question","name":"What is included with the skill?","acceptedAnswer":{"@type":"Answer","text":"The skill itself, the objection map reference, the per-page pin format, and the review scoring rules. It is free and security scanned. We re-publish the ZIP when the scoring changes, so download it again if your pins start shifting."}}]}</script>