Total 57,837 skills, AI & Machine Learning has 9618 skills
Showing 12 of 9618 skills
Task management for AI agents across context windows. Use when agents need to track work, log progress, hand off state, and maintain context across sessions. Includes workflows for single-issue focus, multi-issue work sessions, and structured handoffs. Essential for AI-assisted development where context windows reset between sessions.
AI-driven browser automation via Model Context Protocol
This skill should be used when the user asks to "create a ReAct agent", "build an agent with tools", "implement tool-calling agent", "use dspy.ReAct", mentions "agent with tools", "reasoning and acting", "multi-step agent", "agent optimization with GEPA", or needs to build production agents that use tools to solve complex tasks.
Upload and manage files using Google Gemini File API via scripts/. Use for uploading images, audio, video, PDFs, and other files for use with Gemini models. Supports file upload, status checking, and file management. Triggers on "upload file", "file API", "upload image", "upload PDF", "upload video", "file management".
Build and train neural networks with TensorFlow
Structured messaging protocols for agent team communication including message type selection, plan approval, shutdown procedures, and anti-patterns to avoid. Use this skill when establishing team communication norms, handling plan approvals, or managing team shutdown.
Use when working with error debugging multi agent review
Adaptive epoch selection for Walk-Forward Optimization. TRIGGERS - WFO epoch, epoch selection, WFE optimization, overfitting epochs.
Google Gemini File Search for managed RAG with 100+ file formats. Use for document Q&A, knowledge bases, or encountering immutability errors, quota issues, polling failures. Supports Gemini 3 Pro/Flash (Gemini 2.5 legacy).
Interactive reading teacher that instantly generates playful, engaging learning experiences for children ages 1-10. Creates visual playgrounds, phonics games, and interactive stories to build reading skills from letter recognition to comprehension.
Fully autonomous epic execution. Runs until ALL children are CLOSED. Local mode uses /swarm with runtime-native spawning (Codex sub-agents or Claude teams). Distributed mode uses /swarm --mode=distributed (tmux + Agent Mail) for persistence and coordination. NO human prompts, NO stopping.
Lab environment for Claude superpowers