Browse skills

Use when the user asks to create, scaffold, or edit Jupyter notebooks (`.ipynb`) for experiments, explorations, or tutorials; prefer the bundled templates and run the helper script `new_notebook.py` t

Track and visualize ML training experiments with Trackio. Use when logging metrics during training (Python API), firing alerts for training diagnostics, or retrieving/analyzing logged metrics (CLI). S

Manage and dynamically control feature releases and experiments across your Vercel deployments using flags.

Official posthog skill for software development workflows.

This skill allows you to execute Lua code snippets within your experiments, enabling advanced data manipulation and custom logic for richer insights.

Analyzes CRISPR screen data from ToolUniverse experiments to identify gene essentiality and potential therapeutic targets.

This skill guides you to design and execute reliable experiments by prioritizing factual accuracy and minimizing bias for robust results.

Provides design guidance and assistance for software development workflows.

This skill generates verifiable, reproducible experimental results, enhancing trust and transparency in AI model development & validation.

Google Ads Experiments — provides AI agent assistance for software development workflows.

Automates data ingestion, transformation, and storage within your Comet ML experiments using a robust backend pipeline.

Manages Azure resources, Weights & Biases experiments, and .NET projects using claudedjale's specialized AI agent skill.

Manages Weights & Biases experiments and runs using Azure credentials via the dotnet SDK.

Automatically logs your machine learning experiments to Weights & Biases (W&B), streamlining tracking and analysis for improved model development.

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.