image-generation

Generate high-quality images via MCP (Gemini models or compatible services) using structured prompts, ratios, and validation for marketing, UI, or presentations.

1.61x

Quality

53%

Does it follow best practices?

Impact

97%

1.61x

Average score across 3 eval scenarios

Securityby

Passed

No known issues

Optimize this skill with Tessl

npx tessl skill review --optimize ./.agent-skills/image-generation/SKILL.md

Quality

Discovery

57%

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 adequately identifies its domain and technical approach (MCP/Gemini image generation) with reasonable distinctiveness. However, it lacks explicit trigger guidance ('Use when...') and could benefit from more natural user-facing keywords and concrete action verbs to improve discoverability.

Suggestions

Add an explicit 'Use when...' clause with trigger terms like 'generate image', 'create picture', 'AI image', 'make a graphic', or 'visual content'

Include more concrete actions such as 'create product mockups, generate social media graphics, design hero images, produce presentation visuals'

Dimension	Reasoning	Score
Specificity	Names the domain (image generation) and mentions some context (marketing, UI, presentations) with methods (structured prompts, ratios, validation), but doesn't list multiple concrete actions like 'create product mockups, generate social media graphics, design UI elements'.	2 / 3
Completeness	Describes what it does (generate images via MCP with structured prompts) and hints at use cases (marketing, UI, presentations), but lacks an explicit 'Use when...' clause with trigger guidance, capping this at 2 per rubric guidelines.	2 / 3
Trigger Term Quality	Includes some relevant terms like 'images', 'MCP', 'Gemini', 'marketing', 'UI', 'presentations', but misses common natural variations users might say like 'generate picture', 'create image', 'AI art', 'image generation', or 'make a graphic'.	2 / 3
Distinctiveness Conflict Risk	The combination of 'MCP', 'Gemini models', and specific use cases (marketing, UI, presentations) creates a clear niche that distinguishes it from generic image or document skills, making conflicts unlikely.	3 / 3
	Total	9 / 12 Passed

Implementation

50%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

This skill provides a reasonable structure for image generation workflows with good examples and templates, but suffers from verbosity and incomplete actionability. The MCP integration—the core technical component—is underspecified, while peripheral content like metadata and multi-agent workflows adds length without clear utility. The workflow lacks explicit validation steps for handling generation failures.

Suggestions

Add concrete MCP tool invocation syntax showing the actual function calls or CLI commands for image generation, not just 'ask-gemini' placeholders

Add a validation/retry loop: what to do when generation fails, how to check if output meets requirements, and how to iterate

Remove or move to separate files: Metadata section, Multi-Agent Workflow (unless made concrete), and Tags—these don't help Claude execute the skill

Trim 'When to use this skill' section—Claude can infer appropriate use cases from the skill description

Dimension	Reasoning	Score
Conciseness	The skill includes some unnecessary sections like 'Metadata', 'Tags', and 'Multi-Agent Workflow' that add bulk without clear value. The core content is reasonably efficient but could be tightened—the 'When to use this skill' section explains obvious use cases Claude would infer.	2 / 3
Actionability	Provides structured prompt templates and example commands, but the MCP integration is vague—'ask-gemini' command is not explained, and the actual MCP tool invocation syntax is missing. The bash examples are incomplete (checking availability without showing actual generation commands).	2 / 3
Workflow Clarity	Steps are clearly numbered and sequenced, and includes a review checklist. However, there's no validation/error recovery for failed generations, no feedback loop for when outputs don't meet criteria, and the 'Multi-Agent Workflow' section is abstract rather than actionable.	2 / 3
Progressive Disclosure	Content is well-organized with clear sections and headers. However, it's somewhat monolithic—the troubleshooting, best practices, and multi-agent workflow sections could be separate files. References to related skills exist but the skill itself is longer than necessary for an overview.	2 / 3
	Total	8 / 12 Passed

Validation

90%

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 — 10 / 11 Passed

Validation for skill structure

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning

	Total	10 / 11 Passed

Repository: supercent-io/skills-template
Commit: fd18296

Reviewed: 26 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.