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

amazon-analyse

Skill2 starsChanged 4 months agoMITView on GitHub

Amazon single-product analysis workflow. Use when the user runs `/amazon-analyse {ASIN} {SITE}` to collect marketplace data, produce a Markdown product analysis report, optionally export a product-manager meeting Excel workbook, and run data validation without exposing secrets.

  • Reads credentials

1 other project uses a version of this.

Adopted by

Most recently taken up by

  • Other versions1 project uses a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 1

    1. liangdabiao/amazon-sorftime-research-MCP-skill★ 1.1ksame name

    How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.

  • In this repository6 other files it gives its agents.

The file

Show its rules and text

We split this skill into the rules it gives an agent

23 rules. About 0 are common, 17 are distinctive, and 6 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈17

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 6

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  • could be automatic: a setting could enforce it
  1. Distinctive:

    Always create and preserve the Markdown report.

    line 22
  2. Distinctive:

    When Excel is generated, include the raw MCP responses used for the report in a dedicated workbook sheet.

    line 24
  3. Distinctive:

    Do not print, store, or commit API keys.

    line 25
  4. Distinctive:

    Do not include raw secrets in generated reports.

    line 26
  5. Distinctive:

    Keep filenames aligned with the report title when possible.

    line 27
  6. Very specific:

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

    line 32
  7. Distinctive:

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

    line 34
  8. Distinctive:

    If Gemini or GLM credentials are missing, ask for the missing model key before claiming real Gemini/GLM validation.

    line 35
  9. Distinctive:

    Do not continue with mock MCP data or fake model validation.

    line 36
  10. Distinctive:

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

    line 37
  11. Distinctive:

    Use SellerSprite MCP or a compatible marketplace data source.

    line 41
  12. Distinctive:

    Before collecting data, read the bundled SellerSprite MCP reference when available:

    line 43
  13. Very specific:

    Prefer the official MCP configuration style: clean URL plus a secret-key header.

    line 56
  14. Distinctive:

    If a needed evidence point is not supported by MCP, mark it as a data gap first.

    line 75
  15. Distinctive:

    Add a final data validation section.

    line 84
  16. Very specific:

    When Gemini/GLM keys and network are available, use them as judges.

    line 104
  17. Distinctive:

    After the Markdown report has been saved, ask the user:

    line 108
  18. Distinctive:

    Always preserve the Markdown report regardless of whether Excel conversion is requested.

    line 121
  19. Distinctive:

    If Excel is generated, return both paths: Markdown report and Excel workbook.

    line 122
  20. Very specific:

    If Excel is generated, add a MCP原始数据 sheet that contains the report's raw MCP files or compact raw JSON payloads.

    line 123
  21. Very specific:

    Use templates/excel-workbook-layout.md as the layout reference.

    line 127
  22. Very specific:

    Prefer conservative .xlsx generation.

    line 140
  23. Distinctive:

    Use this sheet to preserve the evidence trail behind the Markdown and meeting views.

    line 151

≈ “Common” is an estimate: at least 1 in 5 of the 372,429 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

Amazon Analyse

Command

/amazon-analyse {ASIN} {SITE}

Examples:

/amazon-analyse {ASIN} US

Core Rules

  • Always create and preserve the Markdown report.
  • Excel is optional and must never replace the Markdown report.
  • When Excel is generated, include the raw MCP responses used for the report in a dedicated workbook sheet.
  • Do not print, store, or commit API keys.
  • Do not include raw secrets in generated reports.
  • Keep filenames aligned with the report title when possible.
  • Store raw data separately from final reports.

Credential Preflight

Before any data or validation 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 data collection.
  • If Gemini or GLM credentials are missing, ask for the missing model key before claiming real Gemini/GLM validation.
  • Do not continue with mock MCP data or fake model validation.
  • Do not write provided keys into reports, raw files, Excel workbooks, templates, examples, or the open-source repository.

Data Provider

Use SellerSprite MCP or a compatible marketplace data source.

Before collecting data, read the bundled SellerSprite MCP reference when available:

references/sellersprite-mcp-api.md

Load the MCP endpoint and key from environment variables, for example:

SELLERSPRITE_API_KEY=YOUR_KEY
SELLERSPRITE_MCP_URL=https://mcp.sellersprite.com/mcp

Prefer the official MCP configuration style: clean URL plus a secret-key header. Never hard-code the real MCP URL with a key or print the key.

Normalize user input GB to SellerSprite MCP UK before tool calls.

Recommended Data Calls

  • asin_detail: product metadata.
  • asin_sales_trend: sales, revenue, and price trend.
  • asin_prediction, bsr_prediction, keepa_info: forecast/history context when available.
  • asin_coupon_trend or asin_detail_with_coupon_trend: promotion/coupon context when available.
  • traffic_keyword_stat: ASIN traffic keyword source overview.
  • traffic_keyword: ASIN traffic keywords.
  • traffic_source: organic/recommendation/ad traffic source structure.
  • traffic_extend: keyword and competitor traffic context.
  • traffic_listing: keyword/listing traffic context when available.
  • keyword_miner, keyword_order, keyword_research_trends: keyword demand, ranking, PPC, and trend checks.
  • review: positive and negative review samples.
  • trademark_list / trademark_stats: only when brand, naming, or IP risk is discussed.

If a needed evidence point is not supported by MCP, mark it as a data gap first. Only then use a browser/crawler fallback and label it as external supplemental data.

Markdown Report Flow

  1. Parse ASIN and site.
  2. Normalize site code for SellerSprite MCP.
  3. Collect MCP data and save raw or compact responses under a report-specific directory.
  4. Build conclusions only from MCP evidence, existing user files, or clearly labeled assumptions.
  5. Generate a Chinese Markdown report.
  6. Add a final data validation section.
  7. Save the Markdown report before any Excel conversion step.

Data Validation

Append a section named:

Gemini Eval Harness 数据验证

Check:

  • price/rating/review count/rank consistency;
  • sales and keyword metric consistency;
  • source and data-gap transparency;
  • reasoning reliability;
  • risk completeness;
  • actionability of P0/P1/P2 recommendations.

When Gemini/GLM keys and network are available, use them as judges. Otherwise write 未执行真实调用 and include a manual validation summary.

Optional Excel Output Prompt

After the Markdown report has been saved, ask the user:

是否需要转换为Excel表格输出?

Offer:

  • 需要: create an additional Excel workbook using the meeting workbook layout.
  • 不需要: stop after Markdown and return the Markdown path.

Hard rule:

  • Always preserve the Markdown report regardless of whether Excel conversion is requested.
  • If Excel is generated, return both paths: Markdown report and Excel workbook.
  • If Excel is generated, add a MCP原始数据 sheet that contains the report's raw MCP files or compact raw JSON payloads. Redact secrets, tokens, local absolute paths, and any user-private credentials before writing the sheet.

Excel Workbook Layout

Use templates/excel-workbook-layout.md as the layout reference.

Recommended sheets:

  • 会议摘要
  • 产品基础信息
  • 销售趋势
  • 关键词布局
  • 评论VOC
  • 竞争策略
  • 数据来源
  • MCP原始数据

Prefer conservative .xlsx generation. If direct chart XML editing is unreliable, use in-cell bars and styled tables instead of chart objects.

MCP原始数据 should be audit-oriented, not decorative. Recommended columns:

  • 数据文件/接口
  • 采集时间
  • 记录序号
  • 字段路径
  • 原始值
  • 备注

Use this sheet to preserve the evidence trail behind the Markdown and meeting views. Keep raw review text compact when it is long, but do not silently drop metric fields that support report conclusions.

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.