Browse skills

Official huggingface skill for software development workflows.

Automatically synchronizes your local OpenAI documentation with the latest official online versions.

Execute Hugging Face Hub operations using the `hf` CLI. Use when the user needs to download models/datasets/spaces, upload files to Hub repositories, create repos, manage local cache, or run compute j

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.

Provides LLMs guidance and assistance for software development workflows.

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

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

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

Ollama simplifies running large language models locally, enabling experimentation and private use without relying on external APIs.

Ollama Stack streamlines local LLM deployment & management, simplifying setup and enabling efficient experimentation for developers.

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.

Provides LLMs guidance and assistance for software development workflows.

Provides LLMs guidance and assistance for software development workflows.

Local speech-to-text using faster-whisper — 4-6x faster than OpenAI Whisper with identical accuracy. GPU acceleration, SRT/VTT/TTML subtitles, speaker diarization, and chapter detection.

Async deep research via Gemini Interactions API. RAG-ground queries on local files, preview costs with --dry-run, get structured JSON output. Universal skill for 30+ AI agents.

Automates greptime setup using Ollama containers for local time series data analysis and visualization.

Generate or edit raster images by calling the ChatGPT/Codex Responses image_generation tool directly with local Codex or OpenClaw OAuth credentials, then save decoded image files for OpenClaw and other agent workflows.

Generate raster images (PNG/JPEG/WebP) using the user's ChatGPT subscription via a local one-file Python CLI — no OPENAI_API_KEY, no gateway, no daemon. Two backends: web (default) drives the user's logged-in ChatGPT browser so generation runs on the conversation surface and does NOT consume Codex-usage limits; codex is a headless fallback that bills the Codex-usage bucket. Use when an agent needs to create a brand-new bitmap asset for the current project (photos, illustrations, icons, hero banners, mockups, sprites, concept art) and the output should be a bitmap file saved into the workspace. Do not use when the task is better solved by editing existing SVG/vector assets, writing code-native graphics (HTML/CSS/canvas), or extending an established repo icon system.