llama-cpp

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

Quality

78%

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

100%

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

The body is lean, highly actionable, and well-organized: core workflows are inline with validation checkpoints, and deeper material is split across six clearly signaled reference files.

Dimension	Reasoning	Score
Conciseness	The body is dense with executable commands, code, and URL patterns and assumes Claude's competence without explaining what GGUF is or how libraries work; every section earns its place, matching the lean score-3 anchor.	3 / 3
Actionability	It provides copy-paste-ready commands (brew install, llama-cli/llama-server, curl) and complete executable Python examples with real flags, matching the 'fully executable code/commands; copy-paste ready' anchor.	3 / 3
Workflow Clarity	The Model Discovery workflow is a clearly numbered 7-step sequence with explicit validation (tree API to 'confirm what actually exists') and fallback/feedback loops ('if that section is not visible ... fall back'), matching the score-3 anchor.	3 / 3
Progressive Disclosure	SKILL.md is a well-signaled overview pointing to six real one-level-deep reference files (verified to exist) with one-line descriptions, keeping core workflows inline and splitting detail appropriately, matching the score-3 anchor.	3 / 3
	Total	12 / 12 Passed

Description

57%

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 specific and distinctive but relies on noun phrases, abbreviates Hugging Face, and lacks an explicit 'when to use' trigger clause, capping several dimensions at 2.

Suggestions

Add an explicit 'Use when ...' trigger clause naming natural user phrases (e.g. 'Use when running local GGUF models, finding GGUFs on Hugging Face, or picking a quant for your RAM/VRAM').

Spell out 'Hugging Face' (or add 'Hub') and include 'quantization'/'quant' as trigger terms alongside 'llama.cpp' and 'GGUF'.

Lead with concrete verb actions ('Run local GGUF models, discover GGUFs on Hugging Face, pick a quant') instead of noun phrases.

Dimension	Reasoning	Score
Specificity	Names the domain ('local GGUF inference' and 'HF Hub model discovery') but uses noun phrases rather than concrete verb actions and is not comprehensive, matching the score-2 anchor while clearly above the vague score-1 example.	2 / 3
Completeness	It states what the skill does but has no 'Use when...' clause or equivalent explicit trigger guidance, so per the judging guideline completeness is capped at 2 (has what, when is missing or only implied).	2 / 3
Trigger Term Quality	Includes relevant terms users would say ('llama.cpp', 'GGUF') but abbreviates 'HF Hub' instead of 'Hugging Face' and omits common variations like 'quantization'/'quant', so it matches 'some relevant keywords but missing common variations' rather than full score-3 coverage.	2 / 3
Distinctiveness Conflict Risk	Naming a specific tool (llama.cpp) and format (GGUF) gives it a clear niche unlikely to conflict with other skills, matching the score-3 'clear niche with distinct triggers' anchor.	3 / 3
	Total	9 / 12 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: b7a05b6

Reviewed: about 14 hours 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.