agentsclimarketplace

Alibaba product title builder

Skill tanghongming0/renyi-alibaba-ops/skills/alibaba-product-title-builder

Generate, optimize, and audit Alibaba International Station product titles using a source-backed paper-product component library and strict word-order, truthfulness, application, duplication, and character-length checks. Use when asked to write or improve Alibaba product titles, create 128-character titles, choose title keywords, place for/with/of, generate title variations, or explain why a title is compliant and buyer-readable.From its SKILL.md

Install
npx -y skills add tanghongming0/renyi-alibaba-ops --skill alibaba-product-title-builder

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

2.7 KB, 475 tokens by cl100k_base, as published. Nobody here has run it

Alibaba Product Title Builder

Build buyer-readable titles from verified product facts instead of keyword stuffing.

Workflow

  1. Collect the confirmed product facts:

    • core product
    • material
    • supported certification or environmental attribute
    • specification and process
    • procurement or customization service
    • real application
  2. Mark unsupported or unknown facts. Never place them in a title.

  3. Read title-rules.md.

  4. Read paper-title-components.md when selecting paper-product wording.

  5. Choose the requested mode:

    • Quality mode: one clear core product, concise attributes, one application.
    • Traffic mode: broader buyer-language coverage while preserving natural order and the requested character limit.
    • Variation mode: produce distinct titles for different buyer intents without cosmetic word shuffling.
  6. Generate the title using:

    Procurement/Service + Material/Certification + Spec/Process + Core Product + Function/Form + for Application

  7. Run python scripts/validate_title.py "<title>" --max-length <limit>.

  8. Revise until the checker passes or report the exact unresolved product-fact gap.

Output

Provide:

  • final title
  • character count
  • title mode
  • component breakdown
  • supported versus unverified attributes
  • validation result
  • two alternatives only when they target materially different buyer intent

If the user requests a specific length such as 128 characters, measure it exactly. Do not claim the target is met without counting.

Guardrails

  • Keep the core product in the first half whenever practical.
  • Put the core product before for and with.
  • Use for only for an application, use, buyer industry, or end scenario.
  • Use with only for a real optional feature or service and use it sparingly.
  • Avoid of when a compact noun phrase is natural.
  • Do not repeat the product form merely to fill characters.
  • Do not use certification, compostability, food-grade, material percentage, stock, samples, MOQ, or customization claims without support.
  • Treat library frequency as wording evidence, not proof that the current product has that attribute.
  • Keep title, attributes, main image, and detail page consistent.

What ships with it: 4 files

19.8 KB alongside SKILL.md, 1 of them executable

agents/

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.