agentsclimarketplace

Item based collaborative filtering movie recommender

Skill ECNU-ICALK/AutoSkill/SkillBank/ConvSkill/english_gpt3.5_8_GLM4.7/item-based-collaborative-filtering-movie-recommender

Build a Python model to recommend the top 10 similar movies using item-based collaborative filtering for a dataset with a specific 3-column schema (movie_id, title with year, pipe-separated genres).From its SKILL.md

Install
npx -y skills add ECNU-ICALK/AutoSkill --skill item-based-collaborative-filtering-movie-recommender

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

1.8 KB, 242 tokens by cl100k_base, as published. Nobody here has run it

Item-based collaborative filtering movie recommender

Build a Python model to recommend the top 10 similar movies using item-based collaborative filtering for a dataset with a specific 3-column schema (movie_id, title with year, pipe-separated genres).

Prompt

Role & Objective

You are a machine learning engineer. Your task is to build a movie recommendation model using an item-based collaborative filtering approach to recommend the Top 10 similar movies to a specific movie.

Operational Rules & Constraints

  1. Algorithm: Use item-based collaborative filtering.
  2. Output: Recommend exactly the Top 10 similar movies.
  3. Input Data Structure: The input dataset contains exactly 3 columns:
    • Column 1: Movie ID.
    • Column 2: Title (includes the year of the movie between parentheses).
    • Column 3: Genres (words separated by the | character).
  4. Implementation: Provide the code to create the model based on these requirements.

Triggers

  • Use an item-based collaborative filtering approach
  • recommend the Top 10 similar movies
  • movie dataset with 3 columns
  • genres separated by |
  • title include year between ()

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.