GitHub
google-adk
Agent Development Kit from Google
☆ 4查看技能
tools machine learning AI 技能
发现 tools machine learning 相关 Skills，比较来源仓库和用途，查看适合你工作流的技能说明。
分类目录: tools machine learning
tools machine learning 清除筛选
全部技能
GitHub
base-model-selector
Use when starting a fine-tuning project to determine if fine-tuning is needed, or when evaluating whether a base model meets quality thresholds for a specific domain task
☆ 4查看技能
GitHub
finetune-train
Use when training a fine-tuned model and evaluating improvement over base model. Triggers - have filtered training data, ready to submit training job, need to convert to GGUF. Requires finetune-generate first.
☆ 4查看技能
GitHub
qwen-training-data-miner-prototype
Qwen Training Data Miner (Prototype)
☆ 4查看技能
GitHub
bedrock-fine-tuning
Amazon Bedrock Model Customization with fine-tuning, continued pre-training, reinforcement fine-tuning (NEW 2025 - 66% accuracy gains), and distillation. Create customization jobs, monitor training, deploy cust...
☆ 4查看技能
GitHub
bedrock-flows
Build visual AI workflows with Amazon Bedrock Flows. Create flows with prompt nodes, knowledge bases, Lambda, inline code, condition branching, iterators, collectors, and DoWhile loops. Version management, alia...
☆ 4查看技能
GitHub
agent-cost-optimizer
Real-time cost tracking, budget enforcement, and ROI measurement for AI agent operations. Track token usage, predict costs, enforce budget caps ($50-70/month typical), optimize model selection, cache results, m...
☆ 4查看技能
GitHub
claude-opus-4-5-guide
Comprehensive guide to Claude Opus 4.5, Anthropic's most intelligent model with effort parameter for reasoning control. Covers model capabilities, benchmarks, effort levels (high/medium/low), hybrid reasoning,...
☆ 4查看技能
GitHub
xai-models
xAI Grok model selection and capabilities guide. Use when choosing the right Grok model for your task, comparing model features, or optimizing costs.
☆ 4查看技能
GitHub
skill-improvement-from-observability
Complete feedback loop from observability insights to skill updates. Use when analyzing enhanced telemetry patterns and automatically improving skills.
☆ 4查看技能
GitHub
improvement-workflow
Complete continuous improvement cycle orchestrating review, analysis, learning extraction, systematic updates, and validation. Sequential workflow from comprehensive review through pattern analysis and learning...
☆ 4查看技能
GitHub
bedrock-agentcore-evaluations
Amazon Bedrock AgentCore Evaluations for testing and monitoring AI agent quality. 13 built-in evaluators plus custom LLM-as-Judge patterns. Use when testing agents, monitoring production quality, setting up ale...
☆ 4查看技能
GitHub
hugging-face-evaluation-manager
Add and manage evaluation results in Hugging Face model cards. Supports extracting eval tables from README content, importing scores from Artificial Analysis API, and running custom model evaluations with vLLM/...
☆ 4查看技能
GitHub
model-trainer
This skill should be used when users want to train or fine-tune language models using TRL (Transformer Reinforcement Learning) on Hugging Face Jobs infrastructure. Covers SFT, DPO, GRPO and reward modeling trai...
☆ 4查看技能
GitHub
machine-learning
Supervised & unsupervised learning, scikit-learn, XGBoost, model evaluation, feature engineering for production ML
☆ 4查看技能
GitHub
mlops
MLflow, model versioning, experiment tracking, model registry, and production ML systems
☆ 4查看技能
GitHub
deep-learning
PyTorch, TensorFlow, neural networks, CNNs, transformers, and deep learning for production
☆ 4查看技能
GitHub
advanced-evaluation
Master LLM-as-a-Judge evaluation techniques including direct scoring, pairwise comparison, rubric generation, and bias mitigation. Use when building evaluation systems, comparing model outputs, or establishing...
☆ 4查看技能
GitHub
funsloth-local
Training manager for local GPU training - validate CUDA, manage GPU selection, monitor progress, handle checkpoints
☆ 4查看技能
GitHub
funsloth-check
Validate datasets for Unsloth fine-tuning. Use when the user wants to check a dataset, analyze tokens, calculate Chinchilla optimality, or prepare data for training.
☆ 4查看技能
GitHub
funsloth-hfjobs
Training manager for Hugging Face Jobs - launch fine-tuning on HF cloud GPUs with optional WandB monitoring
☆ 4查看技能
GitHub
funsloth-runpod
Training manager for RunPod GPU instances - configure pods, launch training, monitor progress, retrieve checkpoints
☆ 4查看技能
GitHub
funsloth-upload
Generate comprehensive model cards and upload fine-tuned models to Hugging Face Hub with professional documentation
☆ 4查看技能
GitHub
funsloth-train
Generate Unsloth training notebooks and scripts. Use when the user wants to create a training notebook, configure fine-tuning parameters, or set up SFT/DPO/GRPO training.
☆ 4查看技能
默认按已收录数据中的 GitHub 仓库 Stars 排序。Stars 属于来源仓库，同一仓库的多个技能可能共享相同数值；它反映仓库关注度，不代表单个技能的安装量或质量评分。