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

81%

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

76%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.

The skill body is highly actionable with executable examples throughout and reasonable progressive-disclosure structure. Its chief weakness is missing validation/feedback checkpoints in batch and model-loading workflows, which caps workflow clarity.

Suggestions

Add explicit validation steps to batch generation and model-loading workflows (e.g., assert GPU availability and that the pipeline loaded before generating), with a fix-and-retry loop on failure, to lift workflow clarity above 3.

Move the ControlNet type table, LoRA multi-adapter detail, and memory-optimization sections into a referenced file to sharpen progressive disclosure and reduce inline bulk.

Trim the 'When to use'/'Key features' bullet lists, which restate concepts Claude already knows, to improve conciseness.

Dimension	Reasoning	Score
Conciseness	Content is largely code-driven and efficient, but feature-list sections like 'Key features' and 'When to use' re-state concepts (ControlNet, LoRA) Claude already knows, making it 'efficient with minor over-explanation' rather than the fully lean level-5 anchor.	4 / 5
Actionability	Examples are fully executable and copy-paste ready across text-to-image, img2img, inpainting, ControlNet, and LoRA, with specific parameters and model IDs covering common cases per the level-5 anchor.	5 / 5
Workflow Clarity	Multi-step workflows (batch generation, model loading) lack explicit validation checkpoints or feedback loops; per the batch/destructive cap, a batch skill without validation cannot score above 3 even though sequences are listed.	3 / 5
Progressive Disclosure	Two real reference files (advanced-usage.md, troubleshooting.md) are clearly signaled, but substantial reference-worthy material (ControlNet tables, LoRA detail, memory optimization) is inlined in SKILL.md, leaving minor organization gaps versus the ideal level-5 split.	4 / 5
	Total	16 / 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.

This is a strong, well-structured description that explicitly states both capabilities and use-when triggers with concrete actions. The main weakness is the 'State-of-the-art' buzzword opener and slightly less comprehensive natural-term coverage.

Dimension	Reasoning	Score
Specificity	The description names the domain and lists several concrete actions ('generating images from text prompts, performing image-to-image translation, inpainting, or building custom diffusion pipelines'), matching the 'several specific actions; minor gaps' anchor rather than the fully comprehensive level above.	4 / 5
Completeness	It clearly answers both what ('text-to-image generation with Stable Diffusion models via HuggingFace Diffusers') and when ('Use when generating images from text prompts, performing image-to-image translation, inpainting...') with concrete trigger phrases, matching the level-5 anchor.	5 / 5
Trigger Term Quality	Natural user-facing terms are present ('text prompts', 'image-to-image', 'inpainting'), but the opening 'State-of-the-art' buzzword and lack of synonyms/file extensions keep it below the comprehensive level-5 anchor.	4 / 5
Distinctiveness Conflict Risk	The Stable Diffusion / Diffusers niche is clearly delimited with distinct triggers (text-to-image, image-to-image, inpainting), giving minimal conflict risk with other skills.	5 / 5
	Total	18 / 20 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 (521 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: synthetic-sciences/openscience
Path: backend/cli/skills/llm-tools/stable-diffusion/SKILL.md
Commit: fcd2e11

Reviewed: 2 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.