image-generation

Generate or edit images from text prompts. Use when the user asks to create, draw, design, or edit an image, illustration, photo, icon, poster, or any visual content.

Quality

84%

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

86%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 well-organized, highly actionable single-purpose skill body that keeps implementation in its bundle script and provides concrete copy-paste examples. Minor gains are available from trimming API-key redundancy and adding an explicit output-verification checkpoint.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes Claude's competence with no concept over-explanation, though the API-key list is restated in the Setup section and a few sentences could be tightened, placing it just below fully lean.	4 / 5
Actionability	Copy-paste-ready commands with concrete JSON examples cover the common cases (generate, aspect ratio, single-image edit, multi-image fusion) plus a full parameter table and output/error JSON, matching the fully-executable anchor.	5 / 5
Workflow Clarity	The single action is unambiguous and there is a clear error-recovery feedback loop ('do NOT retry... tell the user to fix it via env_config, then retry'), but there is no explicit validation checkpoint on the generated output, so it sits below the top anchor.	4 / 5
Progressive Disclosure	The body is a clear overview and the heavy implementation is appropriately split into the one-level-deep, well-signaled reference scripts/generate.py, matching the clear-overview anchor.	5 / 5
	Total	18 / 20 Passed

Description

82%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 strong, well-structured description that cleanly states both capability and trigger conditions with rich natural synonyms. It is slightly limited on capability breadth (only generate/edit) and lacks file-extension triggers.

Dimension	Reasoning	Score
Specificity	Names the domain (images from text prompts) and two concrete actions ('Generate or edit images'), but does not enumerate a comprehensive set of capabilities such as variant generation or inpainting, matching the anchor that names the domain with 1-2 actions.	3 / 5
Completeness	It explicitly answers both what it does ('Generate or edit images from text prompts') and when to use it ('Use when the user asks to create, draw, design, or edit...') with concrete trigger phrases, matching the top anchor.	5 / 5
Trigger Term Quality	Strong natural-phrase coverage ('create, draw, design, or edit an image, illustration, photo, icon, poster') with good synonyms and content types, but it omits file-extension terms like .png or .jpg that users sometimes say, so it sits just below comprehensive.	4 / 5
Distinctiveness Conflict Risk	The image-generation niche is clear and the triggers are specific to visual-content creation, keeping overlap risk with unrelated skills minimal and matching the clear-niche anchor.	5 / 5
	Total	17 / 20 Passed

Validation

81%

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 — 13 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning
metadata_field	'metadata' should map string keys to string values	Warning
relative_links	Relative link issues: 1 suspicious	Warning

	Total	13 / 16 Passed

Repository: zhayujie/CowAgent
Path: skills/image-generation/SKILL.md
Commit: ed5bb34

Reviewed: ~15 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.