cowart-image-gen

Generate and place a final AI bitmap on the Cowart canvas, replacing a selected AI 图片 holder or inserting the image into the current page.

Quality

70%

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

Fix and improve this skill with Tessl

tessl review fix ./skills/cowart-image-gen/SKILL.md

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 and well-structured, giving concrete MCP tool calls and exact field mappings for a clear 8-step workflow; its main weakness is minor verbosity from restating the size contract and the absence of an explicit error-recovery feedback loop.

Suggestions

Add an explicit validate-then-retry feedback loop for the destructive steps (e.g., if visual inspection finds a stale/wrong bitmap, regenerate or re-resolve the path before inserting).

Consolidate the target size/aspect-ratio contract so it is derived once and referenced, rather than restated in both step 3 and step 4.

Consider extracting the detailed shape field-mapping tables into a short reference section or file to keep the core workflow leaner.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient domain-specific operational detail Claude would not already know, with only minor repetition (the size contract is restated across steps 3 and 4) that could be trimmed.	4 / 5
Actionability	Provides fully executable guidance: named MCP tools (get_cowart_selection, insert_cowart_image), exact tldraw shape field mappings, concrete asset paths, and a copy-paste example generation prompt.	5 / 5
Workflow Clarity	A clearly sequenced 8-step workflow with a visual-inspection checkpoint (step 4) and a final confirmation (step 8), plus path-resolution fallbacks; it lacks an explicit validate-then-retry error-recovery loop, leaving a minor validation gap.	4 / 5
Progressive Disclosure	Well-organized into Preconditions, numbered Workflow, and Notes sections with easy navigation; all content is inline with no external references, which is appropriate for this cohesive single workflow though it exceeds 50 lines.	4 / 5
	Total	17 / 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 states concrete actions and a distinct Cowart-specific niche clearly, but omits any explicit "Use when..." trigger guidance, which limits its completeness and trigger-term quality.

Suggestions

Add an explicit "Use when..." clause naming natural trigger phrases (e.g., "Use when the user wants an AI image placed on the Cowart canvas, or mentions an AI 图片 holder").

Include common synonyms and file/shape terms users might say ("AI image", "canvas image", "image holder") to broaden trigger coverage.

Keep the existing concrete action list but ensure the "when" half is as explicit as the "what" half.

Dimension	Reasoning	Score
Specificity	Names concrete actions — "Generate and place a final AI bitmap", "replacing a selected AI 图片 holder", "inserting the image into the current page" — giving several specific actions with only minor coverage gaps.	4 / 5
Completeness	The "what" is clear, but there is no "Use when..." clause or equivalent explicit trigger guidance, which caps completeness at 3 per the rubric guideline.	3 / 5
Trigger Term Quality	Relevant domain terms ("AI bitmap", "Cowart canvas", "AI 图片 holder", "image") are present but common variations and synonyms a user might naturally say are missing.	3 / 5
Distinctiveness Conflict Risk	The Cowart-specific niche ("Cowart canvas", "AI 图片 holder") is mostly distinct with minimal overlap risk against other skills.	4 / 5
	Total	14 / 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: 43fc888

Reviewed: 5 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.