All skills
cli-anything-ollama
Manages local Ollama models and runs text generation, chat and embeddings from the terminal.
- Part of HKUDS/CLI-Anything
- 627 installs
- Machine Learning · Local inference
More Local inference skills
See all- llama-cpp86Runs local GGUF models with llama.cpp and finds models on Hugging Face.
- llmfit-advisor28Detects your RAM, CPU and GPU, then recommends local LLM models with quantization and speed estimates.
- kermt-infer12Runs predictions on a SMILES CSV using a fine-tuned KERMT checkpoint.
- code-review10Reviews llama.cpp changes against project conventions and common reviewer pitfalls before you open a PR.
Also in this pack
- cli-anything2.3kBuilds, tests and validates command-line harnesses that let agents drive GUI applications.
- cli-anything-blender1.1kEdits 3D scenes and objects in Blender from the command line.
- cli-anything-obsidian1.1kManages and searches your Obsidian notes and runs vault commands without the app.
- cli-anything-notebooklm933Lists NotebookLM notebooks, manages sources, asks questions and downloads generated outputs.