minicpm5-finetune-llamafactory

Fine-tune MiniCPM5-1B with LLaMA-Factory (YAML-driven SFT / DPO / WebUI). Use when the user wants to fine-tune via LLaMA-Factory, llamafactory-cli, mentions YAML configs, WebUI, or asks for the most-documented community framework.

Quality

88%

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

Quality

Content

88%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.

A concise, highly actionable skill body with executable code/configs at every step, a clear numbered workflow, and a built-in validation checkpoint with an error-recovery hint. Minor conciseness and disclosure polish only.

Dimension	Reasoning	Score
Conciseness	Lean body that assumes competence and foregrounds genuine gotchas (transformers pin, template: empty); the opening two-line summary slightly duplicates the frontmatter description.	4 / 5
Actionability	Fully executable, copy-paste-ready guidance across install, dataset_info.json, the training YAML, train command, inference sanity-check code, and merge flow, covering the common cases.	5 / 5
Workflow Clarity	Clear numbered sequence (1 Install, 2 Register dataset, 3 Write YAML, 4 Train, 5 Validate) with an explicit validation step and an error-recovery hint ("Gibberish ⇒ check template: empty").	5 / 5
Progressive Disclosure	Well-organized sections with a single clearly-signaled one-level reference (docs/finetune/llamafactory.md); the inline training YAML is appropriately kept in the main file rather than split off.	4 / 5
	Total	18 / 20 Passed

Description

87%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.

A precise, well-scoped description that names a concrete model and framework, lists multiple capabilities, and provides explicit 'Use when...' trigger guidance with natural keywords. Strong on completeness and distinctiveness; only minor room for added synonyms.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions ("Fine-tune", "SFT", "DPO", "WebUI") tied to a named model/framework; not quite comprehensive (inference/eval omitted) so below a 5.	4 / 5
Completeness	Explicitly states both what ("Fine-tune MiniCPM5-1B with LLaMA-Factory (YAML-driven SFT / DPO / WebUI)") and when ("Use when the user wants to fine-tune via...") with concrete trigger phrases.	5 / 5
Trigger Term Quality	Good natural trigger coverage ("fine-tune via LLaMA-Factory", "llamafactory-cli", "YAML configs", "WebUI") that users would actually say; missing some synonyms (LoRA, training).	4 / 5
Distinctiveness Conflict Risk	Pinpoints a clear niche (MiniCPM5-1B + LLaMA-Factory) with distinct triggers; minimal overlap risk with other fine-tuning skills.	5 / 5
	Total	18 / 20 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
relative_links	Relative link issues: 1 suspicious	Warning

	Total	15 / 16 Passed

Repository: OpenBMB/MiniCPM
Path: skills/minicpm5-finetune-llamafactory/SKILL.md
Commit: 719e4fc

Reviewed: 17 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.