llama-cpp SKILL.md skillA
llama-cpp from magnus919/agent-skills is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add magnus919/agent-skills/llama-cpp@git:20261012.8794814Pins git:20261012.8794814 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- magnus919/agent-skills
- Path
llama-cpp/SKILL.md- Versions recorded
- 3
- Latest version
- git:20261012.8794814, committed Oct 12, 2026
- First version recorded
- Jul 25, 2026
- Size
- 10,327 bytes
- Repository stars
- 166
- License
- MIT
Operate, configure, benchmark, and troubleshoot llama.cpp across CPU, Metal, CUDA, HIP/ROCm, Vulkan, SYCL, and hybrid or multi-GPU systems. Use when installing or building llama.cpp, selecting or inspecting GGUF models, running llama-cli or bounded llama-completion, serving an OpenAI-compatible API with llama-server, tuning memory and performance, or diagnosing backend, context, template, and API failures. Do not use for model training or fine-tuning, general inference-framework selection…
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
# llama.cpp Operations Treat every launch recipe as a hypothesis about a specific build, model, host, and workload. Discover capabilities from the installed binary, inspect the model and startup logs, then measure the requested boundary. ## Operating contract 1. Record the exact llama.cpp version or commit, installation method, OS and architecture, CPU and RAM, accelerator and memory, driver/toolkit, available devices, model provenance and quantization, intended context, concurrency, and workload. 2. Read the installed command's `--help` before using a flag from documentation. llama.cpp flags, defaults, binary names, and REST behavior change frequently. 3. Confirm the target, scope, and rollback path before acting. Read-only discovery may proceed without confirmation. 4. Verify the backend from `--list-devices` and model-load logs. A successful build or an accepted GPU flag does not prove acceleration is active. 5. Start with a bounded CLI smoke test on loopback or local input. Establish a measured baseline before changing threads, batches, context, cache types, offload, or split mode. …
Read the whole file at its exact version.
How to install
mdr add magnus919/agent-skills/llama-cpp@sha256:c6f4431e0b543ad9The line at the top of this page pins the label git:20261012.8794814, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
[](https://markdownregistry.com/a/art_orwpi24eavxz2gc7)
6 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 3 versions of this file, between Jul 25, 2026 and Oct 12, 2026, about one every 40 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20261012.8794814 latest | 2026-10-12 | 8794814 | 10,327 B | A | view · diff |
| git:20260725.86ac280 | 2026-07-25 | 86ac280 | 9,150 B | A | view · diff |
| git:20260725.58457b4 | 2026-07-25 | 58457b4 | 7,964 B | A | view |
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (10327 bytes)
- pass: No zero-width or bidi control characters
- pass: No instruction hidden inside an HTML comment
- pass: No link to an exfiltration or paste host
- pass: No credential-shaped string
- pass: No instruction to send local credentials anywhere
- pass: No text hidden with inline styles
- pass: No prompt-injection phrasing
- pass: No curl or wget piped into a shell
- pass: No recursive delete of root, home or parent
- pass: No instruction to read or print local credentials
- pass: No base64 blob over 200 characters
- pass: No link to a raw IP address
- pass: No script tag
Source
magnus919/agent-skills · 166 stars · license MIT · pushed 2026-11-04 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_orwpi24eavxz2gc7 GET https://markdownregistry.com/api/v1/resolve?ref=magnus919/agent-skills/llama-cpp GET https://markdownregistry.com/api/v1/blob/c6f4431e0b543ad91f7d24e09bf632f5b0ea92d22b7326ccc4092491875f3da1
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.
More from magnus919/agent-skills
Every file in magnus919/agent-skills