image-gen
Generate website images with Gemini 3 Native Image Generation. Covers hero banners, service cards, infographics with legible text, and multi-turn editing. Includes Australian-specific imagery patterns. Use when stock photos don't fit, need text in images, or require consistent style across assets. Prevents 5 documented errors.
93
Does it follow best practices?
Validation for skill structure
Discovery
100%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is a strong skill description that excels across all dimensions. It provides specific concrete actions, includes natural trigger terms users would actually say, explicitly states both what the skill does and when to use it, and has a clear distinctive niche that minimizes conflict with other skills.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'hero banners, service cards, infographics with legible text, and multi-turn editing'. Also mentions specific capabilities like 'Australian-specific imagery patterns' and 'Prevents 5 documented errors'. | 3 / 3 |
Completeness | Clearly answers both what ('Generate website images with Gemini 3...hero banners, service cards, infographics') AND when ('Use when stock photos don't fit, need text in images, or require consistent style across assets'). | 3 / 3 |
Trigger Term Quality | Includes natural keywords users would say: 'website images', 'hero banners', 'service cards', 'infographics', 'stock photos', 'text in images', 'consistent style'. These are terms users naturally use when requesting image generation. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with specific niche: Gemini 3 Native Image Generation, website-specific images, Australian imagery patterns. Clear triggers differentiate it from generic image or design skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
87%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a strong, well-structured skill that efficiently covers Gemini image generation with excellent actionability and progressive disclosure. The Known Issues section is particularly valuable, documenting 5 specific problems with prevention patterns. The main weakness is the lack of explicit validation checkpoints in workflows, particularly for multi-turn editing operations which are deferred to reference files.
Suggestions
Add a brief inline workflow for multi-turn editing with validation steps (e.g., verify image loaded, check edit applied, validate output) rather than deferring entirely to references/editing.md
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Content is highly efficient with tables for quick reference, no unnecessary explanations of basic concepts, and every section provides actionable information. The skill assumes Claude's competence and focuses on what's unique to this API. | 3 / 3 |
Actionability | Provides fully executable TypeScript code examples, specific model IDs, exact configuration parameters, and copy-paste ready snippets. The Known Issues section includes both wrong and correct code patterns. | 3 / 3 |
Workflow Clarity | While the Quick Start shows a clear generation workflow, the skill lacks explicit validation checkpoints for multi-step processes like multi-turn editing. The 'When to Use' decision tree is helpful but editing workflows are deferred to reference files without inline validation steps. | 2 / 3 |
Progressive Disclosure | Excellent structure with clear overview, tables for quick scanning, and well-signaled one-level-deep references to detailed files (prompting.md, editing.md, etc.). Content is appropriately split between main skill and reference files. | 3 / 3 |
Total | 11 / 12 Passed |
Validation
87%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 14 / 16 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
metadata_version | 'metadata.version' is missing | Warning |
body_steps | No step-by-step structure detected (no ordered list); consider adding a simple workflow | Warning |
Total | 14 / 16 Passed | |
- Reviewed
Table of Contents
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.