ml-experiment
Track ML experiments with proper logging and reproducibility. Use when training models or running experiments.
Discover Research skills, compare source repositories and read the instructions for each workflow.
Track ML experiments with proper logging and reproducibility. Use when training models or running experiments.
Manage Python virtual environments and dependencies. Use when setting up projects or installing packages.
Create conventional commit messages. Use when committing changes or writing commit messages.
Triage and manage GitHub issues. Use when reviewing issues or planning work.
Use when writing Python code for clean, performant, and idiomatic implementations
Use when designing test strategies, implementing test automation, or establishing QA processes
Use before marking any task complete to ensure all requirements are met
Use when managing Git branches, creating commits, or preparing pull requests
Use before invoking Oracle to ensure appropriate usage of this expensive reasoning resource
Use when encountering any bug, test failure, or unexpected behavior before proposing fixes
Use when designing multi-cloud infrastructure, CI/CD pipelines, or Kubernetes deployment strategies
Use when developing applications for AWS cloud platform with best practices and cost optimization
Use when researching unfamiliar code, multiple modules involved, or external libraries referenced
Use when writing Nix code for flakes, modules, or packages
Use when touching frontend files to classify visual vs logic changes before acting
Use when writing Rust code for memory safety, performance, and systems programming
Use when reviewing code for architectural consistency, designing backend systems, or evaluating structural changes
Use when starting open-ended tasks in unfamiliar codebases, before following existing patterns
Use when optimizing performance, profiling bottlenecks, or architecting for scale
Use when implementing any feature or bugfix before writing implementation code
Use when reviewing code for quality, security vulnerabilities, and best practices
Use when writing SQL queries, optimizing database performance, or analyzing data
Security patterns for the 3SC widget host. Covers credential storage, input validation, secure coding practices, and protecting user data.
Global error handling for the 3SC widget host. Covers exception handling, crash reporting, user-friendly error surfaces, and recovery strategies.
The default order uses GitHub repository stars from our indexed data. Stars belong to the source repository and may be shared by multiple skills. They indicate repository interest, not skill installs or an independent quality score.