Discover tools machine learning skills, compare source repositories and read the instructions for each workflow.
Create, clean, and optimize datasets for LLM fine-tuning. Covers formats (Alpaca, ShareGPT, ChatML), synthetic data generation, quality assessment, and augmentation. Use when preparing data for training.
Algorithm/model development and fine-tuning skill. Use for tasks like dataset design/cleaning, supervised fine-tuning (SFT), preference optimization (DPO/RLHF concepts), LoRA/QLoRA, training configs, evaluation...
This skill should be used when the user asks about "Burn tensors", "tensor operations", "Module derive", "burn config", "autodiff", "backward pass", "gradient", "record serialization", "model weights", or core...
This skill should be used when the user asks about "training loop", "Learner", "metrics", "dataset", "dataloader", "checkpointing", "optimizer", "learning rate scheduler", "custom training", or Burn training wo...
GPU-aware PPO training configuration for A100/H100. Trigger when training is slow or GPU utilization is low.
Add account state (P&L, win rate, drawdown) to RL observations + drawdown penalty in rewards. Trigger when: (1) model needs account awareness, (2) training should penalize drawdowns, (3) upgrading obs_dim 5300→...
Model-trader version compatibility protocol: Embed version metadata in checkpoints, validate at load time. Trigger when: (1) training and live trading versions diverge, (2) models fail to load, (3) action inter...
Training improvements: LR warmup, validation intervals, reward weights. Trigger when: (1) training unstable in early epochs, (2) need more validation visibility, (3) model too conservative.
Post-training model validation workflow: gating, backtesting, walk-forward validation, deployment decisions. Trigger after GPU training completes.
PPO network architecture sizing for trading models. Trigger: (1) model files are unexpectedly small/large, (2) choosing hidden_dims for training, (3) balancing model capacity vs inference speed.
Mandatory training archive with model gating (APPROVED/REVIEW/DROP). Trigger when: (1) training run completes, (2) need to decide which models to deploy, (3) want historical training reference, (4) need checkpo...
Train RL models across multiple timeframes with resampling. Trigger when: (1) multi-timeframe training, (2) resampling data, (3) creating 1Hour/4Hour models.
7-action space with position sizing (25/50/75%) + small account simulation. Trigger when: (1) model needs sizing decisions, (2) training for 5900.
Fix PPO training early-stop issues. Trigger when: (1) impossible drawdown values (>100%), (2) training stops too early, (3) need adaptive recovery instead of hard stop.
Fix phantom MaxDD values in training by calibrating reward_scale. Trigger when: (1) validation MaxDD shows 35-80% values, (2) MaxDD doesn't correlate with training quality, (3) gating thresholds seem too lenien...
Debugging constant Markov regime features in RL observations - when HMM probabilities show uniform values instead of dynamic regime estimates
Explains specialized Synapse action classes for specific workflows. Use when the user mentions "BaseTrainAction", "BaseExportAction", "BaseUploadAction", "BaseInferenceAction", "BaseDeploymentAction", "AddTaskD...
Analyze code performance, detect bottlenecks, suggest optimizations for algorithms, queries, and resource usage. Use when improving application performance or investigating slow code.
Automated CSV data analysis with statistical insights, pattern detection, visualization recommendations, and anomaly detection
fal.aiスキルに新しいモデルを追加するためのスキル
Optimizes AI models for edge deployment through quantization, lazy loading, and memory management. Use when deploying models to resource-constrained environments, mobile devices, or edge computing scenarios. Do...
Provides industry-proven design patterns for effective AI agents based on production systems like Claude Code, Manus, and Cursor. Use when designing agent architectures, optimizing context management, or implem...
Specialized AI assistant for DSPy development with deep knowledge of predictors, optimizers, adapters, and GEPA integration. Provides session management, codebase indexing, and command-based workflows.
Cognitive enhancement toolkit combining non-linear reasoning, mental models, and literate programming. Use for complex analysis, system design, debugging, deep learning, and research workflows.
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.