Skip to content

jeremylongshore/tons-of-skills-marketplace / plugins/ai-ml/recommendation-engine/skills/building-recommendation-systems

building-recommendation-systems

Verified

Execute this skill empowers AI assistant to construct recommendation systems using collaborative filtering, content-based filtering, or hybrid approaches. it analyzes user preferences, item features, and interaction data to generate personalized recommendations... Use when appropriate context detected. Trigger with relevant phrases based on skill purpose.

FileKindSize
SKILL.mdskill md3.8 KB
assets/README.mdmarkdown320 B
assets/configuration_template.yamlconfig2.6 KB
references/README.mdmarkdown64 B
scripts/README.mdmarkdown569 B

assets/configuration_template.yaml

View on GitHub
# Configuration template for the recommendation engine plugin.

# Data source configuration
data_source:
  type: "csv"  # Type of data source: csv, database, api, etc.
  path: "data/user_item_interactions.csv" # Path to the data file or API endpoint
  # Database connection details (if applicable)
  database:
    host: "localhost" # example-value: Database host
    port: 5432       # Database port
    name: "recommendations_db" # example-value: Database name
    user: "recommendations_user" # example-value: Database user
    password: "YOUR_DATABASE_PASSWORD" # example-value: Database password

# Feature engineering configuration
feature_engineering:
  user_features:
    - "age"       # List of user features to use
    - "location"
    - "interests"
  item_features:
    - "category"    # List of item features to use
    - "price"
    - "description"
  interaction_features:
    - "rating"    # List of interaction features to use
    - "timestamp"
  feature_scaling: "standard" # Feature scaling method: standard, minmax, none

# Model configuration
model:
  type: "collaborative_filtering" # Type of recommendation model: collaborative_filtering, content_based, hybrid
  algorithm: "als" # Algorithm to use for the model: als, sgd, knn, etc.
  hyperparameters:
    n_factors: 50  # Number of latent factors in collaborative filtering
    reg_param: 0.01 # Regularization parameter
    epochs: 10      # Number of training epochs
  cold_start_strategy: "popularity" # Strategy for handling cold start problems: popularity, average, etc.

# Evaluation configuration
evaluation:
  metrics:
    - "precision"   # List of evaluation metrics to use
    - "recall"
    - "ndcg"
  split_ratio: 0.8  # Ratio of data to use for training (remaining for testing)
  k: 10           # Number of recommendations to consider for evaluation

# Deployment configuration
deployment:
  model_path: "models/recommendation_model.pkl" # Path to save the trained model
  api_endpoint: "/recommendations" # API endpoint for serving recommendations
  num_recommendations: 5  # Default number of recommendations to return

# Logging configuration
logging:
  level: "INFO"   # Logging level: DEBUG, INFO, WARNING, ERROR, CRITICAL
  file: "logs/recommendation_engine.log" # Path to the log file

# Performance optimization configuration
optimization:
  enable_caching: true # Enable caching of recommendations
  cache_expiry: 3600  # Cache expiry time in seconds (1 hour)

# Error handling configuration
error_handling:
  retries: 3       # Number of retries for failed requests
  retry_delay: 60   # Delay between retries in seconds
reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis.Stars: 472kUpdated Claude CodeCodexVerifiedInstall
diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness.Stars: 323kUpdated Claude CodeCodexVerifiedInstall
dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependenciesStars: 323kUpdated Claude CodeCodexVerifiedInstall
executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is availableStars: 323kUpdated Claude CodeCodexVerifiedInstall