discover-ml

rand's avatarfrom rand

Automatically discover machine learning and AI skills when working with machine learning. Activates for ml development tasks.

⭐33stars🔀2forks📁View on GitHub🕐Updated Nov 25, 2025
[Developer Tools]

When & Why to Use This Skill

The discover-ml skill acts as an intelligent gateway for machine learning and AI development within Claude. It automatically detects ML-related tasks—such as model training, inference, or framework-specific coding with PyTorch and TensorFlow—and provides instant access to a comprehensive suite of 25 specialized sub-skills. By enabling progressive loading of advanced techniques like RAG evaluation, LoRA fine-tuning, and DSPy optimization, it streamlines the development workflow and ensures the most relevant AI tools are always at the developer's fingertips.

Use Cases

  • LLM Fine-tuning & Optimization: Quickly activate specialized skills for LoRA, PEFT, and Unsloth to enhance model performance and efficiency.
  • RAG System Implementation: Access advanced modules for Retrieval-Augmented Generation, including hybrid search, reranking techniques, and hierarchical RAG architectures.
  • AI Framework Integration: Seamlessly manage development tasks involving PyTorch, TensorFlow, and DSPy through context-aware skill discovery.
  • Model Evaluation & Benchmarking: Utilize 'LLM-as-a-judge' frameworks and automated evaluation metrics to validate model accuracy and output quality.
namediscover-ml
descriptionAutomatically discover machine learning and AI skills when working with machine learning. Activates for ml development tasks.

Ml Skills Discovery

Provides automatic access to comprehensive ml skills.

When This Skill Activates

This skill auto-activates when you're working with:

  • machine learning
  • ML
  • AI
  • models
  • training
  • inference
  • PyTorch
  • TensorFlow

Available Skills

Quick Reference

The Ml category contains 25 skills:

  1. custom-llm-evaluation
  2. diffusion-finetuning
  3. diffusion-model-basics
  4. dspy-assertions
  5. dspy-evaluation
  6. dspy-modules
  7. dspy-optimizers
  8. dspy-rag
  9. dspy-setup
  10. dspy-signatures
  11. graph-rag
  12. hierarchical-rag
  13. hybrid-search-rag
  14. llm-as-judge
  15. llm-benchmarks-evaluation
  16. llm-dataset-preparation
  17. llm-evaluation-frameworks
  18. llm-model-routing
  19. llm-model-selection
  20. lora-peft-techniques
  21. multi-model-orchestration
  22. rag-evaluation-metrics
  23. rag-reranking-techniques
  24. stable-diffusion-deployment
  25. unsloth-finetuning

Load Full Category Details

For complete descriptions and workflows:

cat ~/.claude/skills/ml/INDEX.md

This loads the full Ml category index with:

  • Detailed skill descriptions
  • Usage triggers for each skill
  • Common workflow combinations
  • Cross-references to related skills

Load Specific Skills

Load individual skills as needed:

cat ~/.claude/skills/ml/custom-llm-evaluation.md
cat ~/.claude/skills/ml/diffusion-finetuning.md
cat ~/.claude/skills/ml/diffusion-model-basics.md
cat ~/.claude/skills/ml/dspy-assertions.md
cat ~/.claude/skills/ml/dspy-evaluation.md

Progressive Loading

This gateway skill enables progressive loading:

  • Level 1: Gateway loads automatically (you're here now)
  • Level 2: Load category INDEX.md for full overview
  • Level 3: Load specific skills as needed

Usage Instructions

  1. Auto-activation: This skill loads automatically when Claude Code detects ml work
  2. Browse skills: Run cat ~/.claude/skills/ml/INDEX.md for full category overview
  3. Load specific skills: Use bash commands above to load individual skills

Next Steps: Run cat ~/.claude/skills/ml/INDEX.md to see full category details.