agentleFS
Ethan-paseyaEthan-paseya/amazon-sellersprite-research-MCP-skill/.claude/skills/review-analysis/SKILL.md

review-analysis

Skill2 starsChanged 4 months agoMITView on GitHub

Amazon review and VOC analysis using SellerSprite MCP. Use when the user runs `/review-analysis {ASIN} {SITE}` to analyze positive and negative reviews, identify product pain points, listing mismatch, service risks, and product improvement actions.

6 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use growth-analysis, revenue-analysis and 4 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • asospySkill

    growth-analysis

    Explain how an app grew or declined over a period, using ASOSpy installs, revenue, ratings and chart-rank history, and find likely causes in reviews and release dates. Use when the user asks why an app's downloads, revenue or rank changed, or wants a growth timeline. Needs the ASOSpy MCP server.

    Also in 3 projects that use this

  • trysonarSkill

    revenue-analysis

    When the user wants to estimate or benchmark app revenue and downloads — validating an app idea, sizing a niche, comparing monetization across apps, or reading their own App Store Connect sales on the App Store or Google Play. Also use when the user mentions "how much does this app make", "revenue estimate", "app downloads estimate", "market size", "is this niche profitable", or "my sales". For finding the apps to benchmark, see market-discovery. For full competitor teardowns, see competitor-analysis.

    Also in 3 projects that use this

  • aws-solutionsSkill

    app-discovery

    Navigates a deployed web application, discovers all pages and interactive elements, and produces a structured discovery report. Use when a test plan or spec needs a map of a live web app's pages, controls and form rules, or the user asks to crawl an app before writing E2E tests. Loads dom-inspection to extract form validation rules, error selectors, and conditional visibility. Used as input to k-light-ui-testing and k-e2e-test-generation workflows.

    Also in 3 projects that use this

  • Kungfookenny123Skill

    app-marketing-context

    When the user wants to create or update their app marketing context document. Also use when the user mentions "app context", "marketing brief", "app positioning", or when starting any ASO or app marketing project. This is the foundation skill — all other skills check for this context first.

    Also in 3 projects that use this

  • Kungfookenny123Skill

    metadata-optimization

    When the user wants to optimize App Store metadata — title, subtitle, keyword field, or description. Also use when the user mentions "optimize my title", "ASO metadata", "keyword field", "character limits", "app description", or "write my subtitle". For keyword discovery, see keyword-research. For full ASO audits, see aso-audit.

    Also in 3 projects that use this

  • LangChainSkill

    competitor-analysis

    Analyze competitors in a given market segment. Trigger on: competitive landscape, competitor analysis, market comparison, competitive positioning.

    Also in 4 projects that use this

The file

We split this skill into the rules it gives an agent

8 rules. 0 are common, 6 are distinctive, and 2 are very specific to this project.

  • 0

    Common

    Most of the 4 edited versions we read keep these.

  • 6

    Distinctive

    This author's own choices. Worth a look.

  • 2

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Before any data call, read references/runtime-credential-preflight.md when it is available.

    line 20
  2. Distinctive:

    If SellerSprite MCP is not configured, unavailable, or returns an authentication error, ask the user for the SellerSprite MCP API key …

    line 22
  3. Distinctive:

    If Gemini/GLM validation is part of the requested output and model keys are missing, ask for the missing keys before validation.

    line 23
  4. Distinctive:

    Do not continue with mock reviews or fabricated VOC conclusions.

    line 24
  5. Distinctive:

    Do not write provided keys into reports, raw files, examples, or the open-source repository.

    line 25
  6. Very specific:

    Read references/sellersprite-mcp-api.md before execution when it is available.

    line 29
  7. Distinctive:

    Only mark an issue as a confirmed pain point when it appears in MCP review evidence or an existing user-provided source.

    line 54
  8. Distinctive:

    Do not publish raw review dumps or customer-identifying data.

    line 64

“Common” is measured: kept by at least 6 in 10 of the 4 edited versions of this file we could read. “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 Analysis

Command

/review-analysis {ASIN} {SITE}

Goal

Turn review data into product decisions: what users love, why users complain, and what should be fixed first.

Credential Preflight

Before any data call, read references/runtime-credential-preflight.md when it is available.

  • If SellerSprite MCP is not configured, unavailable, or returns an authentication error, ask the user for the SellerSprite MCP API key before review analysis.
  • If Gemini/GLM validation is part of the requested output and model keys are missing, ask for the missing keys before validation.
  • Do not continue with mock reviews or fabricated VOC conclusions.
  • Do not write provided keys into reports, raw files, examples, or the open-source repository.

Required Reference

Read references/sellersprite-mcp-api.md before execution when it is available. Normalize GB to SellerSprite MCP UK before tool calls.

Data Calls

  • asin_detail: product context.
  • review with starList: [4,5]: positive reviews. Use pagination and record sample size.
  • review with starList: [1,2,3]: negative reviews. Use pagination and record sample size.
  • Optional review filters: typeList for image/video/VP/vine reviews, startTimestamp, endTimestamp, page, size, and returnFields.
  • asin_sales_trend and traffic_keyword: optional context for whether VOC issues correlate with sales or keyword expectation gaps.
  • keepa_info: optional price/rank history context when available.

Save raw or compact review responses before summarization. Do not quote large review dumps in public reports; aggregate themes and keep customer-identifying data out.

Analysis Dimensions

DimensionWhat to Identify
Product defectbroken parts, durability, failure
Design/function gapusability, missing function, poor fit
Material/appearancesmell, scratches, color, texture
Description mismatchexpectation gap from title/images/bullets
Service/logisticsused item, missing parts, late delivery
Return riskhigh-friction issues likely to cause returns

Only mark an issue as a confirmed pain point when it appears in MCP review evidence or an existing user-provided source. Otherwise label it as a hypothesis.

Output

Save under:

review-analysis-reports/{ASIN}_{SITE}_{YYYYMMDD}/report.md

Do not publish raw review dumps or customer-identifying data.

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.