Browse skills

Sundial-org's training-data-curation refines datasets by identifying biases, errors, and gaps for improved AI model performance.

Analyzes GPU utilization and identifies performance bottlenecks during AI model training and inference tasks.

This skill trains large language models like Megatron, accelerating AI development and enabling powerful custom LLM creation for diverse applications.

Analyzes training logs to identify patterns and areas for improvement, boosting performance and efficiency through data-driven insights.

Provides LLMs guidance and assistance for software development workflows.

Provides LLMs guidance and assistance for software development workflows.

Provides LLMs guidance and assistance for building AI and machine learning applications.

Simulates RL environments using UV Miles data for robust agent training and improved performance in realistic scenarios.

Uv Moe Training guides AI models to generate charming, cute (moe) aesthetics and styles for creative content generation.

Dynamically adjusts training parameters based on real-time performance data to maximize model accuracy and efficiency.

Provides LLMs guidance and assistance for building AI and machine learning applications.

This tool automatically adjusts gradients during training to prevent exploding gradients and improve model stability – a crucial aid for deep learning.

Automates model checkpointing, versioning, and retrieval during training, simplifying experiment management and reproducibility.

Provides LLMs guidance and assistance for software development workflows.

This skill analyzes training effectiveness using Kirkpatrick’s levels – assessing if learning led to desired behavior changes and business results.

Grpo RL Training facilitates rapid reinforcement learning model development by automating and optimizing agent training processes for improved performance.

This skill automatically converts documents into vector datasets for efficient semantic search and AI model training.

This AI provides personalized workout plans and fitness advice, helping users achieve their health goals effectively.

Stable Baselines3 provides robust, easy-to-use implementations of reinforcement learning algorithms for training agents to master complex tasks.

Parallel autonomous ML research agents with a Director, git worktrees for per-agent experiment branches, a Skills library for validated technique reuse, a Synthesizer that distills collective knowledge overnight, and circadian rhythm (leisure 03:00–06:00 for paper reading and creative thinking). Uses OpenClaw sessions_spawn, cron, and steer natively. Use when: (1) start or run ML research agents overnight, (2) check agent status or experiment results, (3) view leaderboard or morning digest, (4) steer or stop agents, (5) ask what agents discovered or are exploring, (6) set up Litmus for the first time. NOT for: general coding, non-ML tasks, or machines without a GPU.