Total 50,737 skills, AI & Machine Learning has 8499 skills
Showing 12 of 8499 skills
Interactively onboard a project to agent-driven development by running a structured interview and generating a complete AGENTS.md (or CLAUDE.md). Use this skill whenever a user mentions "AGENTS.md", "CLAUDE.md", "agent behavior", "agent instructions", "agent config", "set up agent rules", "onboard agent", "configure claude code", "agent guardrails", "agent workflow", or asks how to tell an AI agent how to behave in their project — even if they just say "help me write AGENTS.md" or "what should go in CLAUDE.md". Always prefer this skill over ad-hoc agent instruction generation.
Expert skill for OmniVoice, a massively multilingual zero-shot TTS model supporting 600+ languages with voice cloning and voice design capabilities.
Build and use free-code, the open-source fork of Claude Code CLI with telemetry removed, guardrails stripped, and all experimental features unlocked.
On-device, real-time multimodal AI voice and vision assistant powered by Gemma 4 E2B and Kokoro TTS, running entirely locally via FastAPI WebSocket server.
Autonomous LLM training optimization with GPU support. Runs 5-minute training experiments, measures val_bpb, keeps improvements or reverts — repeat forever. Use this skill when the user asks to "train a model autonomously", "optimize LLM training", "run ML experiments", "autoresearch with GPU", "optimize val_bpb", "autonomous ML training", "LLM pretraining loop", "setup ML autoresearch", "GPU training experiments", "pretrain from scratch", "speed up training", "lower my loss", "GPU optimization", "CUDA training", or mentions "train.py", "prepare.py", "bits per byte", "val_bpb", "NVIDIA GPU training", "RTX training", "H100 training", "autonomous model training", "consumer GPU training", "low VRAM training". Always use this skill when the user wants to autonomously optimize any ML training metric.
Use when generating videos with Model Studio DashScope SDK using Wan video generation models (wan2.6-t2v, wan2.6-i2v-flash, wan2.6-i2v and regional variants). Use when implementing or documenting video.generate requests/responses, mapping prompt/negative_prompt/duration/fps/size/seed/reference_image/motion_strength, or integrating video generation into the video-agent pipeline.
Triggered automatically at the start of each new top-level conversation to establish the general principle of "seeking truth from facts", and select downstream skills for subsequent tasks only when clearly applicable. Skip this skill if you are a delegated sub-agent performing a single specific task. English: Trigger at the start of each new top-level conversation to establish the core methodology and select downstream skills only when clearly useful. Skip this skill when you are a delegated sub-agent handling a narrow, concrete task.
Agent skill for agentic-payments - invoke with $agent-agentic-payments
Set up and maintain a persistent, LLM-managed knowledge base for a digital health project — turning clinical observations, papers, interviews, and planning docs into a compounding, interlinked wiki.
Continuous self-improvement through structured reflection and memory
Datumbox integration. Manage Organizations, Users, Goals, Filters. Use when the user wants to interact with Datumbox data.
Use skill if you are building or maintaining MCP servers with @modelcontextprotocol/sdk v1.x — single-package TypeScript SDK with Zod, RequestHandlerExtra, and built-in OAuth.