Skill Claude CodeCodex
Train LoRA/QLoRA adapter "filters" on a local model with the llamero shard (Crystal, Apple Silicon). Use when the user wants to fine-tune a local model, teach a model new facts or documents (manuals, internal docs, domain knowledge), create/train a LoRA or QLoRA adapter, build a golden dataset, or toggle learned…
Skill Claude CodeCodex
Call cloud AI APIs (OpenAI, Anthropic/Claude, Groq, OpenRouter) from Crystal with the llamero shard - chat, streaming, structured JSON output, embeddings, and automatic failover between providers. Use when the user wants to call an LLM API from Crystal, needs provider failover/retries, or wants typed structured…
Skill Claude CodeCodex
Run AI models locally on Apple Silicon from Crystal with the llamero shard (Llamero::Native, MLX/Metal). Use when the user wants on-device or local LLM inference, local chat, token streaming, structured JSON output from a local model, or to load/keep a model resident in memory without cloud APIs like OpenAI. Also…
Instructions file CodexOpenCode
Instructions for crimson-knight/llamero, covering llamero — agent quick reference, cloud chat with failover, structured json output (cloud and local, same pattern), storage root for consuming apps and local inference on apple silicon (no api key).
Instructions file
Instructions for crimson-knight/llamero, covering llamero — guide for ai coding agents, which api do i need?, storage root, working on the llamero repo itself and when llamero is a dependency in another project.