533 skills ・ Works with: Discord · sorted by popularity
Use Outlines to make language models produce data in a defined format. The skill covers extracting information into JSON, restricting classification labels, and applying Pydantic models, which define fields and data types, with local model backends.
Reduce the memory needed to run large language models with GPTQ quantization, which stores model weights at lower precision. Covers loading compressed models, quantizing your own models, choosing execution backends, and connecting to memory-efficient fine-tuning.
Set up model training with torchforge for reinforcement learning, where rewards guide improvement. Covers training configurations, custom reward and loss functions, and distributed execution with Monarch and TorchTitan, keeping algorithm experiments separate from infrastructure concerns.
Set up LLM serving with structured responses, including JSON and outputs restricted to specified patterns. Covers reusing shared prompt calculations, tool calling, and multi-turn conversations through SGLang, with examples for server setup and application integration.
Use W&B to record machine learning experiments, visualize training, and compare results. The skill also covers automated searches for training settings and version tracking for datasets and models, helping teams share experiments and trace their inputs.
Build image generation workflows in Python with Stable Diffusion and HuggingFace Diffusers. The guide covers text prompts, transforming existing images, replacing selected regions, controlling composition, applying learned styles, and adjusting memory use during generation.
Run machine learning workloads on Modal's cloud GPUs without managing servers. Guides Python configuration for training, inference, batch processing, and API deployment, including automatic scaling, persistent storage, scheduled jobs, and troubleshooting.
Run language models locally with llama.cpp on CPUs, Apple Silicon, or AMD and Intel GPUs. The skill guides model setup, memory-saving GGUF format choices, interactive chat, and serving models through an OpenAI-compatible API.
Organize PyTorch training code with LightningModule and Trainer. Follow examples for validation, logging, model saving, and distributed training across multiple GPUs, with callbacks that add monitoring or stop training when progress stalls.
Build LlamaIndex applications that retrieve relevant material before generating answers, a method called RAG. Connect documents, websites, and databases to support document questions, conversational search, structured summaries, and checks of answer relevance and source consistency.
Build and operate AutoGPT agents that carry out multi-step workflows. Covers a visual editor for connecting processing blocks, scheduled and webhook triggers, deployment, execution monitoring, and benchmarks for evaluating agent performance.
Present clear choices when a task needs a human decision, then pause execution until the user replies. This reusable interaction pattern supports filing decisions, priority selection, and confirmation before destructive actions, with an option to decline.
Move an existing OpenClaw setup to NanoClaw v2 through a guided conversation. Review identity, memory, credentials, groups, and scheduled tasks, then decide what to transfer and preview changes before applying them.
Set up the first NanoClaw agent on a configured messaging channel. The skill identifies the operator and DM destination, selects or creates an agent group, and sends a welcome message to verify delivery through the service.
Adapt NanoClaw by adding messaging channels, connecting services, changing response instructions, or adjusting message routing. The skill clarifies the request, selects dedicated skills where available, applies changes, and explains how to verify them.
Add Discord bot support to NanoClaw for conversations in server channels or direct messages. The skill installs and tests the integration, guides bot setup, checks credentials, and finds the owner's DM channel for subsequent agent connection.
Finish a NanoClaw v1-to-v2 migration after the migration script completes. The skill checks real message routing, assigns owner access, coordinates legacy memory migration, reviews container settings, and helps decide how to carry over customizations.
Design AI agents and chatbots in n8n, choosing suitable nodes and connecting models, tools, conversation memory, and structured JSON output. Includes guidance on document retrieval and human approval before tool execution.
Build Python applications that collect live cryptocurrency prices, trades, and order books with Cryptofeed. Covers consistent data formats across exchanges, price comparisons, and writing incoming data to storage systems for monitoring and analysis.
Develop applications with the Claude API using examples from Anthropic's official cookbooks. Explore document summarization, image analysis, document retrieval, external tool calls, and prompt caching through practical Python code and implementation guidance.
Create and manage scheduled AI automations in screenpipe from the command line. Enable or disable jobs, test runs, inspect logs, and configure service connections such as Telegram and Slack, including connection status checks.
Use Screenpipe’s local REST API, an interface for programmatic requests, to search screen and meeting history, review app activity and active time, retrieve synced-device records, export recordings, and rerun audio transcription.
Operate Screenpipe from the terminal to set up continuous recording, check capture health, and search local history. Manage Pipes, scheduled AI automations, and configure and test connections to external services.
Search Screenpipe recordings, screen text, audio transcripts, and synced-device history through its local API. Use the evidence to review activity, find meeting details, and inspect saved workflows, including recorded steps that can inform automation.