80,000+ Skills to Supercharge Claude
The open directory for GitHub-integrated capabilities, tools, and prompts for your AI workflows.
config
by atrawog
Unified system configuration dispatcher for bazzite-ai. Manages services (Docker, Cockpit, SSH), desktop settings (gamem...
quantization
by atrawog
Model quantization for efficient inference and training. Covers precision types (FP32, FP16, BF16, INT8, INT4), BitsAndB...
inference
by atrawog
Fast inference with Unsloth and vLLM backend. Covers model loading, fast_generate(), thinking model output parsing, and...
test
by atrawog
Runtime verification tests for bazzite-ai installation. Tests GPU detection, CUDA, PyTorch, service health, network conn...
sft
by atrawog
Supervised Fine-Tuning with SFTTrainer and Unsloth. Covers dataset preparation, chat template formatting, training confi...
virtualization
by atrawog
GPU passthrough and virtualization for Bazzite. KVM/VFIO setup, Looking Glass (kvmfr), USB hotplug for VMs, and libvirt...
security
by atrawog
Security configuration for Bazzite. LUKS disk encryption with TPM auto-unlock, secure boot key management, and sudo pass...
fiftyone
by atrawog
FiftyOne dataset visualization and curation tool via Podman Quadlet. Multi-container architecture with MongoDB sidecar f...
storage
by atrawog
Storage management for Bazzite. Automounting drives (BTRFS/EXT4, Framework, SteamOS), BTRFS deduplication, rmlint disk t...
openwebui
by atrawog
Open WebUI AI chat interface management via Podman Quadlet. Provides a web UI for interacting with Ollama models. Use wh...
distrobox
by atrawog
Distrobox container management for Bazzite. Create containers from manifests, custom containers, app-specific containers...
apps
by atrawog
Third-party application installation for Bazzite. CoolerControl, DisplayLink, JetBrains Toolbox, OpenRazer, tablet drive...
api
by atrawog
Direct REST API operations for Ollama using the requests library. Covers all /api/* endpoints for model management, text...
gpu
by atrawog
GPU monitoring and performance metrics for Ollama inference. Check GPU status, VRAM usage, loaded models, and inference...
dpo
by atrawog
Direct Preference Optimization for learning from preference pairs. Covers DPOTrainer, preference dataset preparation, im...
system
by atrawog
System maintenance for Bazzite OS. Updates via topgrade, cleanup of podman/flatpaks, viewing logs and changelogs, diagno...
jellyfin
by atrawog
Jellyfin media server management via Podman Quadlet. Supports multi-instance deployment, hardware transcoding (NVIDIA/AM...
transformers
by atrawog
Transformer architecture fundamentals. Covers self-attention mechanism, multi-head attention, feed-forward networks, lay...
clean
by atrawog
Development: Cleanup and maintenance for the development environment. Removes build artifacts, caches, containers, and r...
runners
by atrawog
Self-hosted GitHub Actions runner management via Podman Quadlet. Supports multi-instance pools with ephemeral storage, a...
rloo
by atrawog
Reinforcement Learning with Leave-One-Out estimation for policy optimization. Covers RLOOTrainer, reward function integr...
rag
by atrawog
Retrieval-Augmented Generation (RAG) for grounding LLM responses with external knowledge. Covers document chunking, embe...
desktop
by atrawog
Desktop customization for Bazzite. GTK theme restoration, terminal transparency, and MOTD settings. Use when users need...
huggingface
by atrawog
Import GGUF models from HuggingFace into Ollama. Pull models directly using the hf.co/ prefix, track download progress,...