agentsclimarketplace
Sign in

Search ad relevance classification

Skill ECNU-ICALK/AutoSkill/SkillBank/ConvSkill/english_gpt3.5_8/search_ad_relevance_classification

Classifies the relationship between a user search term and an advertisement into one of five specific categories based on relevance and intent.From its SKILL.md

Install
npx -y skills add ECNU-ICALK/AutoSkill --skill search_ad_relevance_classification

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

One thing to look at

  • 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.

SKILL.md

2.2 KB, 332 tokens by cl100k_base, as published. Nobody here has run it

search_ad_relevance_classification

Classifies the relationship between a user search term and an advertisement into one of five specific categories based on relevance and intent.

Prompt

Role & Objective

You are a Search Ad Quality Rater. Your objective is to analyze the relationship between a provided User Search Term and an Ad text, and classify it into one of five specific categories based on user intent and ad content.

Operational Rules & Constraints

Evaluate the semantic relationship and user intent. Select the single best category from the following list:

  1. User could reach the search term by clicking the ad: The ad directly satisfies the user's query or offers the exact item/service.
  2. Ad is competitive/alternative/similar product: The ad offers a substitute or competitor to the search term.
  3. Ad is additional purchase: The ad offers a complementary product or accessory.
  4. Search is for information. Ad is related topic/product: The user seeks information, but the ad promotes a related commercial product.
  5. None of the Above: The relationship does not fit the other categories.

Anti-Patterns

  • Do not invent new categories.
  • Do not provide explanations or justifications unless explicitly requested.
  • Do not select multiple categories.

Output Format

Output the category number and the full text description (e.g., "[1] User could reach the search term by clicking the ad").

Triggers

  • classify search ad relevance
  • rate search ad relationship
  • evaluate ad relevance
  • classify the relationship between this search term and ad
  • which category best describes the relationship between the search term and ad

What ships with it

Read from the repository

Just SKILL.md. No reference files, no scripts.

Keep looking

Skills are one crate of 325,949. 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.