agentsclimarketplace
Sign in

Alibaba keyword evidence audit

Skill tanghongming0/renyi-alibaba-ops/skills/alibaba-keyword-evidence-audit

Audit Alibaba International Station keyword, search-term, P4P, product, and title data while separating verified performance evidence from relevance-only candidates and missing data. Use when asked for high-conversion keywords, keyword screening, P4P grouping, title keyword sources, search-term analysis, or proof of where a keyword conclusion came from.From its SKILL.md

Install
npx -y skills add tanghongming0/renyi-alibaba-ops --skill alibaba-keyword-evidence-audit

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

3 things to look at

  • 21 days oldThe repository was created 21 days ago. New is not bad, but a brand new repository carrying a familiar-sounding name is the shape a typosquat arrives in, and there has been no time for anyone else to find a problem with it.
  • no licenseNo license file was found in the repository. Code published without one is not open source by default, so using it at work is a question for whoever answers licensing questions where you are.
  • 0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

SKILL.md

1.7 KB, 272 tokens by cl100k_base, as published. Nobody here has run it

Alibaba Keyword Evidence Audit

Produce an action-ready keyword audit without overstating the evidence.

Workflow

  1. Inspect every relevant sheet or source and locate the real header row.
  2. Record source file, worksheet or dataset, column names, reporting period, and row-level matching logic.
  3. Classify each keyword with evidence-levels.md.
  4. When a clean CSV or JSON export is available, run python scripts/audit_keywords.py <input> <output.csv>.
  5. Rank verified performance rows first. Keep relevance candidates in a separate section.
  6. Deliver a backend-copyable table plus a source-and-method sheet or section.

Guardrails

  • Never call a title match, product-name match, or Top 200 search term a verified high-conversion keyword by itself.
  • Require word-level clicks and conversion or opportunity evidence before using a high-conversion label.
  • State thresholds explicitly.
  • Preserve zero values; do not treat zero as missing.
  • Do not combine periods silently.
  • Mark unavailable spend, click, inquiry, order, and conversion data as missing.

Required fields

Include keyword, classification, source, sheet or dataset, matched column, period, clicks, spend, inquiries or orders, conversion rate when available, threshold result, and recommended action.

What ships with it: 3 files

3.9 KB alongside SKILL.md, 1 of them executable

agents/

references/

scripts/

Keep looking

Skills are one crate of 326,401. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.