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.

1.03x

Quality

66%

Does it follow best practices?

Impact

97%

1.03x

Average score across 3 eval scenarios

Securityby

Passed

No known issues

Optimize this skill with Tessl

npx tessl skill review --optimize ./plugins/nano-banana-prompts/skills/nano-banana-prompts/SKILL.md

Quality

Content

42%

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

The skill provides excellent actionable examples and templates for image prompt generation, but is severely undermined by extreme verbosity and redundancy. The same advice (use sentences not keywords, limit text to 25 chars, edit one change at a time) is repeated 3-4 times across different sections. At 350+ lines with no bundle files for progressive disclosure, this skill consumes far more context window than necessary for the value it provides.

Suggestions

Cut content by at least 50% by eliminating redundant sections: merge 'Common Pitfalls', 'Common Issues & Solutions', and 'Troubleshooting Guide' into a single concise reference table. Remove the 'Prompt Validation' section which duplicates the 'Quick Prompt Checklist'.

Extract detailed category-specific templates (Product Photography, Landscape, Abstract Art) into separate bundle files and reference them from the main SKILL.md with one-line links.

Remove explanations of concepts Claude already knows (what aspect ratios are used for, what different lens focal lengths do, basic photography terminology) and keep only the actionable templates and examples.

Consolidate the 'Testing Your Prompts' and 'Example: Complete Validation' sections into a single brief validation step within the workflow, rather than sprawling across multiple sections.

Dimension	Reasoning	Score
Conciseness	The skill is extremely verbose at ~350+ lines with massive redundancy. The 'Common Issues & Solutions' section repeats guidance already covered (text rendering rules, multi-turn editing advice, keyword vs. sentence advice). The 'Prompt Validation' checklist largely duplicates the 'Quick Prompt Checklist'. The 'Testing Your Prompts' and 'Troubleshooting Guide' sections repeat the same fixes yet again. Claude doesn't need to be taught basic concepts like what aspect ratios mean or that 85mm is a portrait lens.	1 / 3
Actionability	The skill provides numerous concrete, copy-paste-ready prompt templates and fully worked examples across multiple categories (photography, art, product, landscape, abstract). The templates have clear placeholder syntax and the examples show exactly what a finished prompt looks like.	3 / 3
Workflow Clarity	The multi-turn editing workflow is clearly sequenced with good advice (one change at a time), and the refinement workflow has explicit steps. However, there are no real validation checkpoints with feedback loops — the 'Prompt Validation' section is just a static checklist rather than an actionable verify-fix-retry cycle. For a prompt generation task, the workflow is adequate but the validation steps are more aspirational than executable.	2 / 3
Progressive Disclosure	This is a monolithic wall of text with no bundle files or external references. Content that could be split into separate files (e.g., style-specific templates, troubleshooting guide, validation checklists) is all inline, making the skill extremely long. There's no layered structure — everything is dumped at the same level.	1 / 3
	Total	7 / 12 Passed

Description

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 that clearly identifies its niche (prompt optimization for a specific image generation model), includes good trigger terms, and explicitly states both what it does and when to use it. The main weakness is that the specific capabilities could be more granular—listing concrete actions like structured prompt templates, style parameters, or refinement techniques would strengthen specificity.

Suggestions

Add more concrete actions to improve specificity, e.g., 'structure prompt parameters, apply style modifiers, configure aspect ratios, and build iterative refinement chains for Gemini 2.5 Flash Image.'

Dimension	Reasoning	Score
Specificity	Names the domain (prompt generation for Gemini 2.5 Flash Image) and mentions some actions like 'crafting photo prompts', 'art styles', 'multi-turn editing workflows', but these are more categories than concrete specific actions. It doesn't list granular capabilities like 'apply negative prompts', 'set aspect ratios', or 'structure multi-step refinement chains'.	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 an explicit trigger guidance equivalent to 'Use when...'.	3 / 3
Trigger Term Quality	Includes strong natural trigger terms: 'image generation', 'photo prompts', 'art styles', 'Gemini', 'Nano Banana', 'multi-turn editing'. These cover terms users would naturally say when seeking help with Gemini image prompt crafting. The model-specific names ('Gemini 2.5 Flash', 'Nano Banana') are particularly useful triggers.	3 / 3
Distinctiveness Conflict Risk	Highly distinctive due to the specific model target (Gemini 2.5 Flash Image / Nano Banana). This is unlikely to conflict with generic image generation skills or other prompt engineering skills because it's scoped to a particular model and workflow.	3 / 3
	Total	11 / 12 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 — 11 / 11 Passed

Validation for skill structure

No warnings or errors.

Repository: secondsky/claude-skills
Commit: 5e92b71

Reviewed: about 1 month 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.