ov-layers/skills/llama-cpp/SKILL.md
llama.cpp prebuilt binaries and GGUF conversion tools. Use when working with llama.cpp, GGUF model conversion, or llama-quantize/llama-cli.
npx skillsauth add overthinkos/overthink-plugins llama-cppInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
| Property | Value |
|----------|-------|
| Dependencies | None |
| Ports | — |
| Service | — |
| Install files | layer.yml, tasks: |
Downloads the latest llama.cpp release from GitHub into ~/llama.cpp:
Binaries: llama-quantize, llama-cli, shared libraries (lib*.so*)
Python tools: convert_hf_to_gguf.py, gguf-py package (from source tarball)
| Variable | Value | Purpose |
|----------|-------|---------|
| LLAMA_CPP_PATH | ~/llama.cpp | Location of llama.cpp binaries |
| PATH (appended) | ~/llama.cpp | Makes llama-quantize/llama-cli available |
This layer has no pixi.toml and no depends. It downloads prebuilt binaries and sets environment variables. It is designed to be composed into environment-owning layers (Tier 2) via the layers: field.
The user-phase tasks run after the pixi environment is established by the parent layer. The gguf Python package (for programmatic GGUF access) is declared in the parent layer's pixi.toml, not here.
/ov-layers:python-ml — via layers: [llama-cpp]/ov-layers:jupyter-ml — via layers: [llama-cpp, unsloth]/ov-layers:unsloth-studio — via layers: [llama-cpp, unsloth]/ov-layers:unsloth — Fine-tuning (depends on llama.cpp for GGUF conversion)/ov-images:python-ml (via python-ml metalayer)/ov-images:immich-ml (via python-ml metalayer)/ov-images:jupyter-ml (via jupyter-ml metalayer)/ov-images:jupyter-ml-notebook (via jupyter-ml metalayer)/ov-images:unsloth-studio (via unsloth-studio metalayer)Use when the user asks about:
LLAMA_CPP_PATH environment variable/ov:layer — layer authoring reference (layer.yml schema, task verbs, service declarations)/ov:test — declarative testing (tests: block, ov image test, ov test)tools
Use when authoring or modifying a charly PLUGIN — a candy with a `plugin:` block that contributes Providers (verbs/kinds/deploy-targets/steps/builders/commands), its own CUE schema, builtin (compiled-in) or external (out-of-tree git repo). Covers the unified Provider model, the per-plugin CUE-schema contract (single source → Go params for dev + schema-over-Describe RPC for runtime), the SDK, and the loader.
tools
The CUE data-validation / configuration CLI (cue), pinned to v0.16.1. Use when working with the cue candy, installing the cue binary into a box or onto a target:local dev host, or running the offline schema-vendoring pipeline that feeds charly's egress validation.
tools
CUE EGRESS validation — validating (and, where it adds value, generating) the config files charly WRITES to a system BEFORE the bytes hit disk. MUST be invoked before working on charly/egress.go, the vendored schemas under candy/plugin-egress/egress-schemas/vendor/, the ValidateEgress / registerVendoredEgressKind path, the offline `task cue:vendor` pipeline, or adding an egress schema for any written artifact (cloud-init, k8s manifests, traefik routes, runtime config, install ledger, systemd/quadlet units, ssh_config, libvirt XML).
tools
Kubernetes cluster-probe declarative check verb — the `kube:` check verb (nodes, pods, ingress, storage class, addon health, apply/delete, and arbitrary resource GETs) served out-of-process by the candy/plugin-kube plugin (vendored client-go; no external kubectl required).