stable-diffusion-image-generation

State-of-the-art text-to-image generation with Stable Diffusion models via HuggingFace Diffusers. Use when generating images from text prompts, performing image-to-image translation, inpainting, or building custom diffusion pipelines.

Quality

82%

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

Quality

Content

65%

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

A highly actionable reference rich in executable examples, but it is verbose for a SKILL.md body — explaining concepts Claude already knows and keeping most detail inline rather than deferring to the provided reference files. Workflows lack validation checkpoints and the inline troubleshooting overlaps with its own reference file.

Suggestions

Trim the 'Architecture overview' and 'Core concepts' explanatory sections plus the 'Use alternatives' list; Claude already knows how Diffusers is structured.

Move the inline 'Common issues' section into the existing troubleshooting.md reference (or vice versa) to remove overlap and slim the body into a true overview.

Add explicit validation/checkpoint steps to the batch-generation and workflow recipes (e.g., verify the output image is not blank/noise before proceeding).

Dimension	Reasoning	Score
Conciseness	The ~510-line body is mostly efficient executable code, but includes architecture/concept explanations ('Three-pillar design', 'Pipeline inference flow') and a 'Use alternatives' marketing list that Claude largely already knows and could be trimmed. Not a 3 because not every token earns its place; not a 1 because the bulk is concrete code rather than padded prose.	2 / 3
Actionability	Packed with concrete, copy-paste-ready executable Python covering text-to-image, SDXL, scheduler swapping, reproducible generation, negative prompts, img2img, inpainting, ControlNet, LoRA, and memory optimization. The single undefined helper get_canny_image() is a minor blemish amid overwhelmingly complete examples.	3 / 3
Workflow Clarity	The 'Common workflows' recipes are sequenced with numbered steps, but lack explicit validation checkpoints or validate→fix→retry feedback loops; batch generation has no verification step, which caps clarity at 2 per the batch-operations guideline.	2 / 3
Progressive Disclosure	Two references (advanced-usage.md, troubleshooting.md) are clearly signaled and one-level deep, but the body is a monolithic ~510-line guide keeping full technique sections and an inline 'Common issues' block (overlapping troubleshooting.md) that should be split out, matching the 'content that should be separate is inline' anchor.	2 / 3
	Total	9 / 12 Passed

Description

100%

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 strong, complete description that names concrete actions, includes natural trigger terms, and explicitly covers both what the skill does and when to use it. The only minor blemish is the 'State-of-the-art' buzzword, which does not undermine the otherwise precise triggers.

Dimension	Reasoning	Score
Specificity	Lists multiple specific concrete actions — 'text-to-image generation', 'image-to-image translation', 'inpainting', 'building custom diffusion pipelines' — matching the multiple-specific-actions anchor; the lone 'State-of-the-art' buzzword does not displace the concrete verbs.	3 / 3
Completeness	Explicitly answers what ('text-to-image generation with Stable Diffusion models via HuggingFace Diffusers') and when ('Use when generating images from text prompts...'), with an explicit Use-when trigger clause, so no completeness cap applies.	3 / 3
Trigger Term Quality	Includes natural terms a user would actually say — 'generating images from text prompts', 'image-to-image translation', 'inpainting' — with good coverage rather than technical jargon.	3 / 3
Distinctiveness Conflict Risk	Names a clear niche — Stable Diffusion via HuggingFace Diffusers — with distinct triggers unlikely to overlap with unrelated skills.	3 / 3
	Total	12 / 12 Passed

Validation

75%

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 — 12 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (524 lines); consider splitting into references/ and linking	Warning
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	12 / 16 Passed

Repository: NousResearch/hermes-agent
Path: optional-skills/mlops/stable-diffusion/SKILL.md
Commit: 4c9628e

Reviewed: about 13 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.