agentleFS
Sign inStart free
EbrahimElbagoryEbrahimElbagory/claude-fba/skills/store-audit/SKILL.md

store-audit

Skill17 starsChanged 4 months agoMITView on GitHub

Full Amazon store audit via Helium 10 MCP + SP-API — listing quality scores, keyword rankings, BSR trends, review health, inventory cover — then diff against stored baselines. Use when the user says "audit my store", "how are my listings doing", "did the changes work", or asks for a weekly/monthly store review.

2 other projects use a version of this.

Adopted by

Most recently taken up by

  • Other versions2 projects use a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 2

    1. checkout-page/ecommerce-skills★ 5same name
    2. agshinrajabov/store-ready-kit★ 1same 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 repository4 other files it gives its agents.

The file

We split this skill into the rules it gives an agent

4 rules. About 0 are common, 2 are distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    Distinctive · estimate

    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:

    Check quota first: get_mcp_usage_info (a full audit uses ~20–25 of the 1,000 calls/period).

    line 14
  2. Very specific:

    Write a dated report + save a new baseline JSON with an interventions array — record every change made and its expected effect so the NEXT …

    line 40
  3. Distinctive:

    Every ASIN may have 2+ SKUs (FBA + FBM offers) — listing-content PATCHes go to the BUYABLE one.

    line 57
  4. Distinctive:

    Check the Product Type Definitions API before promising a fix.

    line 61

≈ “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

Store audit → fix → measure loop

Audits the user's whole catalog, compares against saved baselines, and feeds the other claude-fba skills with prioritized findings.

Phase 0 — Preconditions

  1. Helium 10 MCP connected (OAuth; mcp__helium10-mcp__* tools available). A paid Helium 10 plan is required for meaningful data.
  2. Check quota first: get_mcp_usage_info (a full audit uses ~20–25 of the 1,000 calls/period).
  3. Get the catalog: prefer the user's own cached inventory data or SP-API FBA inventory (SPAPI.fba_inventory in scripts/sp_api.py). Note: Helium 10's list_my_products requires the Profits module to be ingesting — it can return empty even on healthy accounts; don't treat that as "no products".

Phase 1 — Data pull (~20 MCP calls for a 10–20 ASIN catalog)

  • get_listing_score(main_asin=<top seller>, competitor_asins=[up to 10 own ASINs]) — ONE call returns the 13-point LQS audit for 11 listings.
  • get_top_keywords(main_asin=X) per variation-family head — top-10 keyword counts, captured search volume, per-keyword organic positions. Siblings in a variation family return identical family-level data; don't waste calls on them.
  • get_listing_details(main_asin=X) for the top ~6 sellers — sub-category BSR, reviews, rating, price, estimated sales, 30-day BSR history.
  • get_search_query_performance(...) if Brand Registered — the impression→click→ cart→purchase funnel vs. the market per query. First-ever call may return DATA_IN_PROGRESS (retry ~24h).
  • list_tracked_keywords / get_keywords_rank_history — only if the user has populated Helium 10 Keyword Tracker (no API write exists; setup is manual in the UI).

Phase 2 — Diff & report

  1. Compare against the newest data/baseline-<date>.json if one exists.
  2. Flag: sub-BSR moves >20 positions, keyword rank drops >5, review/rating changes, LQS regressions, week-over-week conversion shifts >2pts (from track_impact.py snapshots), days-of-cover >180 with Q4 storage-fee season approaching.
  3. Write a dated report + save a new baseline JSON with an interventions array — record every change made and its expected effect so the NEXT audit can attribute.

Phase 3 — Act (use the sibling skills)

  • Copy/keyword fixes → listing-guard (draft → user approval → PATCH → backup).
  • Review velocity → review-automation (backfill + cron health check).
  • Measurement → impact-tracker.
  • New/expanded keyword targets → keyword-research (gap analysis, CPR push list).
  • Everything not API-executable (bullets on restricted product types, coupons, removal orders, tracker setup) → a dated manual-actions list for the user.

Phase 4 — Data-driven iteration

Once ≥2 baselines exist, recommend from observed deltas (what actually moved conversion/rank/reviews), not point-in-time heuristics. Scale what worked; kill what didn't.

Hard-won gotchas

  • Every ASIN may have 2+ SKUs (FBA + FBM offers) — listing-content PATCHes go to the BUYABLE one.
  • Some product types (e.g. ELECTROSHOCK_WEAPON) have attributes REMOVED from the schema (bullet_point!) — live content becomes legacy data no API can edit. Check the Product Type Definitions API before promising a fix.
  • CPR (units needed in 8 days to reach page-1 top half) under ~15 marks a cheap ranking push; surface those explicitly.
  • Empty generic_keyword (backend search terms) is a free, common win — check it via the Catalog Items API on every audit.

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.

Check your setup, free