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

Critical

Do not install without reviewing

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 thorough, highly actionable reference dominated by executable code and useful tables, but it is verbose and monolithic — conceptual padding and inline detail that belongs in the existing reference files keep conciseness, workflow clarity, and progressive disclosure at the mid-level.

Suggestions

Trim the intro and Architecture overview (three-pillar design, inference-flow diagram) — Claude knows diffusion basics; keep only model/scheduler/pipeline specifics.

Move ControlNet, LoRA, and memory-optimization sections into references/advanced-usage.md, leaving a brief overview plus a clearly signaled link so SKILL.md stays a lean entry point.

Add a validation checkpoint to the workflow recipes (e.g., verify output image dimensions/dtype and check for black-frame warnings before accepting a generation).

Dimension	Reasoning	Score
Conciseness	Mostly efficient code and reference tables, but padded with a redundant 'Comprehensive guide' intro and an Architecture overview (three-pillar design, inference-flow ASCII diagram) that explains diffusion concepts Claude already knows; could be tightened.	2 / 3
Actionability	Numerous complete, copy-paste-ready code blocks (basic generation, img2img, inpainting, LoRA, memory opts) plus concrete parameter and scheduler tables; the lone undefined helper get_canny_image() is a minor exception in an otherwise executable body.	3 / 3
Workflow Clarity	Workflow 1/2 are sequenced with numbered comments, but neither includes validation or feedback checkpoints; while image generation is not destructive, the rubric rewards explicit validation steps that are absent here.	2 / 3
Progressive Disclosure	Two real, clearly-signaled one-level-deep references exist (advanced-usage.md, troubleshooting.md), but the SKILL.md itself is a ~510-line monolith with ControlNet, LoRA, and memory-optimization detail inline that could live in those reference files.	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 description: third-person, concise, with an explicit 'Use when' trigger and several concrete capabilities. The only weakness is the 'State-of-the-art' buzzword opener, which adds no triggering value.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — "text-to-image generation", "image-to-image translation", "inpainting", "building custom diffusion pipelines" — matching the 'lists multiple specific concrete actions' anchor, though the opening 'State-of-the-art' is mild buzzword over-claim.	3 / 3
Completeness	Explicitly answers both what ("text-to-image generation with Stable Diffusion models via HuggingFace Diffusers") and when ("Use when generating images from text prompts..."), with an explicit trigger clause.	3 / 3
Trigger Term Quality	Covers natural terms users would say — "text-to-image", "image-to-image translation", "inpainting", "text prompts", "images" — giving good coverage rather than only technical jargon.	3 / 3
Distinctiveness Conflict Risk	Scoped to Stable Diffusion via HuggingFace Diffusers with distinct triggers, making it unlikely to fire for unrelated image-generation skills.	3 / 3
	Total	12 / 12 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (520 lines); consider splitting into references/ and linking	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	14 / 16 Passed

Repository: Orchestra-Research/AI-Research-SKILLs
Path: 18-multimodal/stable-diffusion/SKILL.md
Commit: 773a529

Reviewed: about 11 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.