yao-image

Image expert. ALWAYS invoke this skill when you need to read, analyze, describe, or generate images. Use for screenshots, photos, charts, diagrams, AI-generated images, or any visual content.

Quality

82%

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

82%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 content is highly actionable with executable commands and complete parameter tables, well-organized by tool, and respects token budget. Its main weakness is the absence of validation checkpoints for generation/edit operations that produce output files.

Suggestions

Add a brief validation step after image_generate/image_edit (e.g., confirm the output file was created and is non-empty) to satisfy the batch/destructive-operation feedback-loop expectation.

Tighten the prose around default parameter behavior to avoid restating what the parameter tables already specify.

Consider extracting the shared parameter tables or provider-listing detail into a reference file so SKILL.md stays a lean overview.

Dimension	Reasoning	Score
Conciseness	The body is efficiently organized into tool sections with executable commands and compact parameter tables, with only minor instances (e.g., restating default-parameter behavior in prose) that could be trimmed.	4 / 5
Actionability	Every tool provides copy-paste-ready bash commands covering common cases (local file, URL, provider override, mask, transparent background), plus complete parameter tables — fully executable guidance.	5 / 5
Workflow Clarity	Tools are clearly delineated with when-to-use guidance and a Constraints section enumerating supported/unsupported parameters, but image generation and editing are batch-like operations with no validation step (e.g., confirming the output file exists or is non-empty), leaving a minor checkpoint gap.	4 / 5
Progressive Disclosure	Content is well-structured into per-tool sections with clear headers and a single overview, and no bundle files are referenced so there is no nested-reference risk; it stays just below 5 because all reference material is inlined in one file rather than split for depth.	4 / 5
	Total	17 / 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.

The description is specific, well-triggered, and clearly scoped to image operations, with strong natural keyword coverage. It could be marginally stronger by phrasing the 'when' as a concrete user-side trigger rather than an imperative command.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions ('read, analyze, describe, or generate images') tied to a clear domain, though the actions are general verbs rather than tool-specific operations, leaving minor gaps in coverage compared to a fully comprehensive list.	4 / 5
Completeness	Clearly answers both what (read/analyze/describe/generate images) and when ('ALWAYS invoke this skill when you need... Use for...'), but the 'when' is slightly directive/imperative rather than a cleanly explicit natural trigger phrase, so it sits just below the top anchor.	4 / 5
Trigger Term Quality	Comprehensive coverage of natural terms users would say — 'screenshots, photos, charts, diagrams, AI-generated images, or any visual content' — including common synonyms and concrete content types.	5 / 5
Distinctiveness Conflict Risk	Scoped specifically to image operations with distinct triggers (screenshots, photos, charts), giving a clear niche with only minor overlap risk against a broader multimodal or document skill.	4 / 5
	Total	17 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: YaoApp/yao
Path: tools/skills/yao-image/SKILL.md
Commit: d90d41d

Reviewed: 22 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.