stable-diffusion

Text-to-image generation, inpainting, and img2img.

Quality

66%

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

Fix and improve this skill with Tessl

tessl review fix ./optional-skills/mlops/stable-diffusion/SKILL.md

Quality

Content

75%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 body is a comprehensive, highly actionable guide with executable code throughout and well-placed one-level references. Its main weakness is conciseness: conceptual architecture explanations and the sheer length add tokens that largely restate what Claude already knows.

Suggestions

Trim or remove the 'Architecture overview' (three-pillar design, pipeline inference flow ASCII) and the 'Core concepts' explanatory prose, which restate diffusion basics Claude already knows.

Move the bulk of the pipeline/scheduler/ControlNet reference tables into the existing references/ files, keeping only a quick-start snippet and a pointer in SKILL.md.

Consider consolidating the many small standalone code sections (memory optimization, model variants, batch) into the advanced-usage reference to shorten the main file.

Dimension	Reasoning	Score
Conciseness	Mostly efficient with extensive executable code and tables, but the 'Architecture overview' (three-pillar design, pipeline inference flow) and 'Core concepts' sections explain diffusion internals Claude already knows, adding padding to a ~510-line body.	3 / 5
Actionability	Fully executable, copy-paste-ready code covers all common cases (text-to-image, SDXL, img2img, inpainting, ControlNet, LoRA, memory optimization, batch) alongside concrete parameter and scheduler tables.	5 / 5
Workflow Clarity	The 'Common workflows' section gives clearly numbered, sequenced steps (load with optimizations, then generate with specified settings); image generation is not a destructive operation requiring validation feedback loops, so the minor checkpoint gap is acceptable.	4 / 5
Progressive Disclosure	Well-organized sections with clearly signaled, one-level-deep references to existing files (references/advanced-usage.md, references/troubleshooting.md); the body inlines substantial reference-style material that could otherwise be split out, leaving minor organization gaps.	4 / 5
	Total	16 / 20 Passed

Description

58%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.

The description concisely names the skill's core capabilities but omits any 'Use when...' trigger guidance, which caps its completeness. It is specific and distinct but would benefit from natural trigger phrases and synonyms.

Suggestions

Add an explicit 'Use when...' clause, e.g. 'Use when generating images from text prompts, inpainting photos, or doing img2img with Stable Diffusion / SDXL.'

Include common synonyms and model names users actually say, such as 'Stable Diffusion', 'SDXL', 'image generation', and 'AI art'.

Mention outpainting and ControlNet/LoRA to round out capability coverage and further distinguish from generic image skills.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions ('Text-to-image generation, inpainting, and img2img'), matching the anchor that names multiple specific actions with minor coverage gaps (outpainting, ControlNet, LoRA omitted).	4 / 5
Completeness	Provides a clear 'what' but no explicit 'Use when...' trigger clause; per guidelines a missing 'when' caps completeness at 3.	3 / 5
Trigger Term Quality	Contains relevant natural keywords (text-to-image, inpainting, img2img) but misses common variations and synonyms a user might say, such as 'stable diffusion', 'image generation', 'SDXL', or 'AI art'.	3 / 5
Distinctiveness Conflict Risk	Targets a clear niche (diffusion-based image generation) with mostly distinct triggers and only minor overlap risk with closely related image skills.	4 / 5
	Total	14 / 20 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: 6680afb

Reviewed: about 2 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.