Browse skills

Quickly query and retrieve relevant information from your local documents using davila7's llamaindex integration.

LlamaCpp enables running Meta’s LLaMA language model locally using C++, offering privacy and offline capabilities for developers.

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

LlamaCpp enables running Meta’s LLaMA language model locally using C++, offering efficient inference and privacy without internet dependency.

Serves LLMs like VLLM efficiently for local experimentation and development, accelerating AI workflows.

Use CodexBar CLI local cost usage to summarize per-model usage for Codex or Claude, including the current (most recent) model or a full model breakdown. Trigger when asked for model-level usage/cost data from codexbar, or when you need a scriptable per-model summary from codexbar cost JSON.

Local speech-to-text with the Whisper CLI (no API key).

Local text-to-speech via sherpa-onnx (offline, no cloud)

Z-Image Manga/Illustration Generation using local ComfyUI. High-quality anime/manga art with quick preview and high-res upscale modes. No cloud API needed.

Semantic memory search using Qdrant + Ollama embeddings (QRAS). Use as primary method for recalling workspace files, notes, decisions, and prior work before falling back to built-in search.