llama-factory

Expert guidance for fine-tuning LLMs with LLaMA-Factory - WebUI no-code, 100+ models, 2/3/4/5/6/8-bit QLoRA, multimodal support

Quality

58%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./backend/cli/skills/ml-training/llama-factory/SKILL.md

Quality

Content

35%

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

The body is a lean but generic auto-generated skeleton that defers all substance to reference files while offering no concrete examples, commands, or a real fine-tuning workflow. Reference navigation exists but is weakly signaled and incomplete.

Suggestions

Replace the empty Quick Reference with 1-2 concrete, copy-pasteable fine-tuning commands (e.g., a minimal WebUI launch and a QLoRA CLI example) to lift actionability.

Add a brief ordered fine-tuning workflow with a validation/checkpoint step (e.g., verify training loss / test inference after fine-tuning) so workflow_clarity reflects the real multi-step process.

Improve the Reference Files listing with specific one-line descriptions of each file's contents and include the existing index.md, and remove the generic 'Add helper scripts / templates here' placeholders.

Dimension	Reasoning	Score
Conciseness	The body is short and avoids explaining concepts Claude already knows, but it is padded with generic boilerplate and placeholders ('Quick reference patterns will be added as you use the skill.', 'Add helper scripts here for common automation tasks.') that don't earn their tokens.	2 / 3
Actionability	It provides no concrete code or commands — guidance like 'Use `view` to read specific reference files' and 'Start with the getting_started ... reference files' describes rather than instructs, and the Quick Reference section is explicitly empty.	1 / 3
Workflow Clarity	Only a trivial two-step 'Updating' list is sequenced; the actual fine-tuning workflow is deferred to reference files with no checkpoints or validation feedback loops in the body.	2 / 3
Progressive Disclosure	An overview points to one-level-deep reference files (verified present: advanced.md, getting_started.md, other.md, _images.md), but the file descriptions are generic, the existing index.md is omitted from the listing, and the Quick Reference section is an empty placeholder.	2 / 3
	Total	7 / 12 Passed

Description

82%

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, uses natural trigger terms, and is clearly distinct thanks to the named tool, but it omits an explicit 'Use when...' trigger clause, capping completeness at 2. Adding a when-to-use clause would round it out.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete capabilities — 'fine-tuning LLMs', 'WebUI no-code', '2/3/4/5/6/8-bit QLoRA', 'multimodal support' — rather than vague language, matching the 'lists multiple specific concrete actions' anchor.	3 / 3
Completeness	Clearly states what the skill does but lacks any 'Use when...' clause or equivalent explicit trigger, so per the guideline the missing 'when' caps completeness at 2.	2 / 3
Trigger Term Quality	Includes natural terms an ML user would actually say — 'fine-tuning LLMs', 'LLaMA-Factory', 'QLoRA', 'multimodal', 'WebUI' — giving good coverage rather than jargon-only or sparse keywords.	3 / 3
Distinctiveness Conflict Risk	Naming the specific tool 'LLaMA-Factory' carves out a clear niche with distinct triggers unlikely to conflict with other skills.	3 / 3
	Total	11 / 12 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: synthetic-sciences/openscience
Path: backend/cli/skills/ml-training/llama-factory/SKILL.md
Commit: 52845c3

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.