nano-banana-prompts
Generate optimized prompts for Gemini 2.5 Flash Image (Nano Banana). Use for image generation, crafting photo prompts, art styles, or multi-turn editing workflows with best practices.
88
83%
Does it follow best practices?
Impact
97%
1.03xAverage score across 3 eval scenarios
Passed
No known issues
Quality
Discovery
89%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 solid skill description with strong trigger terms and clear distinctiveness due to the specific Gemini model targeting. The main weakness is moderate specificity - while it mentions several use cases, it could be more concrete about what 'optimized prompts' means or what specific capabilities it enables (e.g., style transfer, composition guidance, negative prompts).
Suggestions
Add more concrete actions to improve specificity, such as 'Generate optimized prompts including style modifiers, composition guidance, and negative prompts for Gemini 2.5 Flash Image'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (Gemini 2.5 Flash Image/Nano Banana) and mentions actions like 'generate optimized prompts', 'crafting photo prompts', 'multi-turn editing workflows', but lacks concrete specific actions like what optimization entails or what editing operations are supported. | 2 / 3 |
Completeness | Clearly answers both what ('Generate optimized prompts for Gemini 2.5 Flash Image') and when ('Use for image generation, crafting photo prompts, art styles, or multi-turn editing workflows'). The 'Use for' clause serves as explicit trigger guidance. | 3 / 3 |
Trigger Term Quality | Good coverage of natural terms users would say: 'image generation', 'photo prompts', 'art styles', 'Gemini', 'Nano Banana'. These are terms users would naturally use when seeking this capability. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with specific model name 'Gemini 2.5 Flash Image (Nano Banana)' as a clear niche. Unlikely to conflict with generic image or prompt skills due to the specific platform targeting. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
77%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a highly actionable skill with excellent concrete examples, templates, and troubleshooting guidance for Gemini image prompt generation. The main weakness is its length - at 400+ lines it could benefit from splitting advanced content (troubleshooting, validation checklists, testing workflows) into separate reference files. Some content is redundant, appearing in slightly different forms across sections.
Suggestions
Split troubleshooting, validation checklists, and testing workflows into separate reference files (e.g., TROUBLESHOOTING.md, VALIDATION.md) and link from main skill
Consolidate redundant content - the 'Common Issues & Solutions' section overlaps significantly with the 'Troubleshooting Guide' table at the end
Remove the 'Prompt Validation' checklist section which largely duplicates the 'Quick Prompt Checklist' earlier in the document
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is comprehensive but overly long (~400+ lines). While it avoids explaining basic concepts Claude knows, it includes redundant sections (validation checklist appears twice in different forms, troubleshooting table duplicates earlier content). Could be tightened significantly. | 2 / 3 |
Actionability | Excellent actionability with concrete, copy-paste ready prompt templates, specific examples for each category (photography, art, product, landscape), exact parameter values (lens focal lengths, f-stops), and clear before/after comparisons showing what works vs. what doesn't. | 3 / 3 |
Workflow Clarity | Clear multi-turn editing workflow with explicit step-by-step sequences. Includes validation checklists, troubleshooting tables, and a refinement workflow with numbered steps. The 'Testing Your Prompts' section provides explicit feedback loops for iterative improvement. | 3 / 3 |
Progressive Disclosure | Content is well-organized with clear headers and logical sections, but everything is in one monolithic file. The extensive troubleshooting, validation, and testing sections could be split into separate reference files. No external file references are used despite the length warranting them. | 2 / 3 |
Total | 10 / 12 Passed |
Validation
100%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
- Repository
- secondsky/claude-skills
- Commit
90d6bd7
- 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.