cowart-image-gen

Generate a final AI bitmap for the Cowart canvas, including any requested in-image text by default. Use when the user asks Codex to create, fill, replace, or place an AI-generated image on a Cowart canvas. If an AI 图片 holder is selected, use it as the size target and replace it with the generated image by default; otherwise generate the image and insert it into the current Cowart page.

Quality

83%

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

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.

A detailed, highly actionable workflow with concrete tool calls and verification steps; its main weakness is mild verbosity from restated holder geometry and prose that could be trimmed. No external bundle files exist, which is appropriate for this single-purpose skill.

Suggestions

De-duplicate the holder geometry (parentId/x/y/rotation/w/h) between step 3 and step 5 — define it once and reference it.

Tighten the output-image resolution section into a prioritized checklist rather than narrative prose.

Add an explicit validate-fix-retry loop for the destructive holder replacement (e.g., if the inserted image fails the visual inspection, regenerate rather than proceed).

Dimension	Reasoning	Score
Conciseness	Mostly efficient domain-specific detail, but the holder geometry (parentId/x/y/w/h) is restated across steps 3 and 5 and the output-image resolution prose could be tightened without losing the safety guidance.	3 / 5
Actionability	Concrete MCP tool names (get_cowart_selection, insert_cowart_image), explicit JSON/meta specs, asset-path patterns, and a copy-ready generation prompt example give fully actionable, parameter-level guidance.	5 / 5
Workflow Clarity	A clear 8-step sequence with verification checkpoints (visual image inspection in step 4, final confirmation in step 8); lacks an explicit validate-fix-retry feedback loop for the destructive holder replacement.	4 / 5
Progressive Disclosure	Well-organized into Preconditions, Workflow, and Notes with no nested references, but the file is self-contained at ~135 lines with no content split into bundle files, so it sits just below the well-signaled-reference ideal.	4 / 5
	Total	16 / 20 Passed

Description

92%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, specific description that clearly states what the skill does and when to use it, anchored to a distinct niche with concrete trigger verbs. Trigger-term coverage is good but could add a few more natural synonyms.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'create, fill, replace, or place an AI-generated image', 'use it as the size target and replace it', 'generate the image and insert it into the current Cowart page' — with comprehensive coverage of both holder and standalone paths.	5 / 5
Completeness	Explicitly answers both 'what' ('Generate a final AI bitmap for the Cowart canvas, including any requested in-image text by default') and 'when' ('Use when the user asks Codex to create, fill, replace, or place an AI-generated image').	5 / 5
Trigger Term Quality	Natural trigger phrases like 'create, fill, replace, or place an AI-generated image on a Cowart canvas' map to what a user would say, though common synonyms like 'draw' or 'add a picture' are absent.	4 / 5
Distinctiveness Conflict Risk	The 'Cowart canvas' niche and 'AI 图片 holder' trigger are highly specific with minimal overlap risk against generic image skills.	5 / 5
	Total	19 / 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: zhongerxin/Cowart
Path: skills/cowart-image-gen/SKILL.md
Commit: c40d254

Reviewed: 7 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.