llama-cpp

llama.cpp local GGUF inference + HF Hub model discovery.

Quality

75%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./skills/mlops/inference/llama-cpp/SKILL.md

Quality

Content

92%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The content is strong: executable code, a well-sequenced discovery workflow with fallback checkpoints, and clean progressive disclosure to six existing reference files. The only weakness is minor verbosity in a couple of peripheral sections.

Dimension	Reasoning	Score
Conciseness	The body is efficient with direct code and minimal prose, assuming Claude's competence, though the OpenAI-compatible curl section and some URL repetition across sections could be trimmed; minor over-explanation keeps it below a 5.	4 / 5
Actionability	Fully executable, copy-paste-ready guidance throughout: brew/winget/build install commands, llama-cli/llama-server -hf invocations, complete Python binding examples, and concrete tree API URLs covering the common cases.	5 / 5
Workflow Clarity	The Model Discovery workflow is a clear 7-step sequence with explicit validation and fallback checkpoints (steps 4, 6, 7) providing feedback loops for when the local-app snippet is not visible.	5 / 5
Progressive Disclosure	SKILL.md is a clear overview with well-signaled, one-level-deep references to six real bundle files (all present in references/), each described in the References section, with content appropriately split between the overview and detail files.	5 / 5
	Total	19 / 20 Passed

Description

57%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description is concise and distinct with a clear niche, but it is too terse: it names only two actions and lacks an explicit 'Use when...' trigger clause. Adding concrete trigger phrases and a few more actions would lift specificity and completeness.

Suggestions

Add an explicit 'Use when...' clause listing natural triggers, e.g. 'Use when running local models with llama.cpp, finding GGUF files on the Hugging Face Hub, or building llama-server/llama-cli commands.'

Expand the action list beyond the two named ('inference', 'model discovery') to include quant selection and command building, which the body already supports.

Surface natural user phrasings and the .gguf extension (e.g. 'GGUF files', '.gguf', 'local model server') so the description matches what users actually say.

Dimension	Reasoning	Score
Specificity	Names the domain ('local GGUF inference') and one concrete action ('HF Hub model discovery') via the '+', but coverage is not comprehensive, matching the anchor for 1-2 concrete actions.	3 / 5
Completeness	Provides a clear 'what' (inference + discovery) but has no 'Use when...' clause or equivalent trigger guidance, which caps completeness at 3 per the guidelines.	3 / 5
Trigger Term Quality	Includes relevant technical terms ('llama.cpp', 'GGUF', 'HF Hub') but omits natural user phrasings and the .gguf file extension, missing common synonyms per the anchor.	3 / 5
Distinctiveness Conflict Risk	The llama.cpp + GGUF + HF Hub combination is a clear niche with distinct triggers and minimal overlap with other skills.	5 / 5
	Total	14 / 20 Passed

Validation

81%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 13 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning
metadata_field	'metadata' should map string keys to string values	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	13 / 16 Passed

Repository: NousResearch/hermes-agent
Path: skills/mlops/inference/llama-cpp/SKILL.md
Commit: 2635035

Reviewed: 8 days ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.