All skills
ollama
Deploys and serves local models with Ollama and exposes an OpenAI-compatible endpoint to apps and agents.
- Part of Prism-Shadow/penguin-harness
- 2 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.
- llamafile1Guides you through building, running, testing and debugging llamafile, including its patch workflow and llama.cpp updates.
Also in this pack
- humanizer2Rewrites or edits prose in any language so it reads like edited human writing rather than default AI output.
- vllm2Deploys and serves language models with vLLM behind an OpenAI-compatible endpoint with tool calling.
- agent-evaluation1Runs one test agent on one benchmark case once, scores it privately and returns a single protocol result.
- agent-optimization1Improves an agent's state using versioned scores and linked traces from a fixed benchmark.