agentleFS
Ethan-paseyaEthan-paseya/amazon-sellersprite-research-MCP-skill/CLAUDE.md

amazon-sellersprite-research-MCP-skill

CLAUDE.md2 starsChanged 4 months agoMITView on GitHub

This repository contains sanitized Amazon research skills and templates for SellerSprite MCP. Use .claude/skills/*/SKILL.md for Claude Code style installs. Use skills/*/SKILL.md for generic/Codex style installs. Recommended cross-platform checks: All skills should save a Markdown report first. For /amazon-analyse {ASIN} {SITE} only: For /product-planning "{ASIN1;ASIN2;ASIN3}" {SITE} default V1 Excel:

The file

We split this CLAUDE.md into the rules it gives an agent

12 rules. About 0 are common, 5 are distinctive, and 7 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈5

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 7

    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:

    Never commit real credentials.

    line 18
  2. Distinctive:

    Never include raw marketplace responses in public examples.

    line 19
  3. Distinctive:

    Always preserve Markdown reports.

    line 20
  4. Very specific:

    Use environment variables or .mcp.json for local MCP configuration.

    line 24
  5. Very specific:

    Prefer the Python toolchain under scripts/python/ for package checks, sanitization, installation, and GitHub publishing.

    line 25
  6. Very specific:

    Use .claude/skills/*/SKILL.md for Claude Code style installs.

    line 29
  7. Very specific:

    Use skills/*/SKILL.md for generic/Codex style installs.

    line 30
  8. Distinctive:

    All skills should save a Markdown report first.

    line 44
  9. Distinctive:

    ask whether Excel is needed.

    line 51
  10. Very specific:

    if yes, generate Excel while preserving Markdown and include the MCP原始数据 sheet.

    line 52
  11. Very specific:

    use the sheet order 意向产品 → 市场分析 → 竞品分析与优化策略 → SWOT分析 → ABA排名【季度】 → MCP原始数据 → 数据来源.

    line 56
  12. Very specific:

    do not include 成本试算 or 销售计划 unless the user explicitly asks and provides assumptions.

    line 57

≈ “Common” is an estimate: at least 1 in 5 of the 28,029 CLAUDE.md 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
CLAUDE.md

Agent Instructions

This repository contains sanitized Amazon research skills and templates for SellerSprite MCP.

Skills

SkillCommand
amazon-analyse/amazon-analyse {ASIN} {SITE}
category-selection/category-select "{CATEGORY}" {SITE}
keyword-research/keyword-research {ASIN} {SITE}
review-analysis/review-analysis {ASIN} {SITE}
product-research/product-research "{PRODUCT_KEYWORD}" {SITE}
product-planning/product-planning "{ASIN1;ASIN2;ASIN3}" {SITE}

Rules

  • Never commit real credentials.
  • Never include raw marketplace responses in public examples.
  • Always preserve Markdown reports.
  • Excel output is optional and additional.
  • Excel output must include a MCP原始数据 worksheet with the raw MCP evidence used by the report, after redacting secrets and local paths.
  • Product planning output must separate evidence, assumptions, calculations, and decisions.
  • Use environment variables or .mcp.json for local MCP configuration.
  • Prefer the Python toolchain under scripts/python/ for package checks, sanitization, installation, and GitHub publishing.

Skill Paths

Use .claude/skills/*/SKILL.md for Claude Code style installs. Use skills/*/SKILL.md for generic/Codex style installs.

Tooling

Recommended cross-platform checks:

python scripts/python/sellersprite_skill_tools.py check-package
python scripts/python/sellersprite_skill_tools.py test-open-source-skills
python scripts/python/sellersprite_skill_tools.py scan-sensitive

Output Policy

All skills should save a Markdown report first.

For /amazon-analyse {ASIN} {SITE} only:

  1. collect data;
  2. generate and save Markdown;
  3. run data validation;
  4. ask whether Excel is needed;
  5. if yes, generate Excel while preserving Markdown and include the MCP原始数据 sheet.

For /product-planning "{ASIN1;ASIN2;ASIN3}" {SITE} default V1 Excel:

  1. use the sheet order 意向产品 → 市场分析 → 竞品分析与优化策略 → SWOT分析 → ABA排名【季度】 → MCP原始数据 → 数据来源;
  2. do not include 成本试算 or 销售计划 unless the user explicitly asks and provides assumptions.
  3. validate the three seed ASINs with asin_detail, infer the product direction from their shared evidence, and retain the three seeds plus at most one validated system supplement in the competitor sheet.

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.