GitHub
reward-function-v330
Use when tuning RL reward function weights, fixing reward hacking, or addressing P&L gradient issues
Skills IA tools machine learning
Découvrez les skills tools machine learning, comparez leurs dépôts et consultez leurs instructions.
Catégories: tools machine learning
tools machine learning Effacer les filtres
Explorer
GitHub
readiness
Evaluate repository readiness for AI agents. Analyzes 81 criteria across 8 pillars, assigns maturity level 1-5, generates visual report.
GitHub
scale-adaptive
Adjust planning depth and agent behavior based on PRD complexity level
GitHub
eval-recipes-runner
Run Microsoft's eval-recipes benchmarks to validate amplihack improvements against baseline agents. Activates when testing with eval-recipes, running evals, or benchmarking changes.
GitHub
explainability
See the main Model Explainability skill for comprehensive XAI coverage.
GitHub
ground-truth-management
Comprehensive guide to creating, managing, and maintaining ground truth datasets for AI evaluation including annotation, quality control, and versioning
GitHub
ai-model-registry
Centralized management of machine learning models throughout their lifecycle, including versioning, metadata, and production deployment.
GitHub
model-serving-inference
Comprehensive guide to deploying and serving LLM models including optimization, batching, caching, and production infrastructure
GitHub
model-explainability-and-interpretability
Techniques and tools for understanding how machine learning models make decisions and explaining those decisions to stakeholders.
GitHub
confidence-scoring
See the main Model Explainability skill for comprehensive coverage of confidence scoring and calibration.
GitHub
ai-data-privacy
Protecting personal and sensitive data throughout the machine learning lifecycle, from training to inference.
GitHub
model-bias-and-fairness
Identifying, measuring, and mitigating algorithmic bias to ensure equitable outcomes in AI systems.
GitHub
ai-feature-template
Create new AI-powered features using xAI Grok. Use when user mentions "new AI feature", "add Grok", "create prompt", "AI analysis", or "generate with AI".
GitHub
python-ml-workflow
Expert guidelines for Python ML and LLM workflows. Covers code quality, experiment tracking, and data handling. Use when working on AI/ML components or data pipelines.
GitHub
outer-review
Commission and process external AI analysis to reduce blind spots. Manual invocation only.
GitHub
ai-engineer
Expert AI Engineer role (10+ Years Exp). Focuses on production-grade GenAI, Agentic Systems, Advanced RAG, and rigorous Evaluation.
GitHub
tensorflow-lite
TensorFlow Lite integration for on-device ML in React Native. Trigger: When working with object detection, image classification, or ML models.
GitHub
magic-model-review
Evaluates Magic Model (Triangle) frameworks for BlackBelt coaches using Ed Dale's frameworks. Produces Facebook-ready feedback comments.
GitHub
ai-orchestration
Multi-model AI collaboration via orchestrator MCP. Use when seeking second opinions, debugging complex issues, building consensus on architectural decisions, conducting code reviews, or needing external validat...
GitHub
tinker-from-docs
Fine-tune LLMs using the Tinker API. Covers supervised fine-tuning, reinforcement learning, LoRA training, vision-language models, and both high-level Cookbook patterns and low-level API usage.
GitHub
orchestrate
Multi-Model Orchestration - Guide for orchestrating multi-model agents
GitHub
readiness-check
Classifies pre-run readiness (proceed/modify/skip) using recent load, recovery, and self-reported signals.
GitHub
load-anomaly-guard
Detects unsafe training load spikes (>20-30% week-over-week) and emits safety flags. Use in nightly background jobs or when reviewing weekly training volume with conservative adjustment recommendations.
GitHub
game-scoring
Use when working with candidate scoring, confidence calculation, softmax aggregation, or guess decision logic. Load for understanding how candidates are ranked, when the system decides to guess, and how semanti...
Le classement utilise les étoiles du dépôt GitHub indexé. Plusieurs skills peuvent partager ce nombre : ce n’est ni un nombre d’installations ni une note de qualité.