nano-banana-pro
Generate and edit images using Google's Nano Banana Pro (Gemini 3 Pro Image) API. Use when the user asks to generate, create, edit, modify, change, alter, or update images. Also use when user references an existing image file and asks to modify it in any way (e.g., "modify this image", "change the background", "replace X with Y"). Supports both text-to-image generation and image-to-image editing with configurable resolution (1K default, 2K, or 4K for high resolution). DO NOT read the image file first - use this skill directly with the --input-image parameter.
Install with Tessl CLI
npx tessl i github:intellectronica/agent-skills --skill nano-banana-pro82
Does it follow best practices?
If you maintain this skill, you can automatically optimize it using the tessl CLI to improve its score:
npx tessl skill review --optimize ./path/to/skillValidation 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 an excellent skill description that hits all the key criteria. It provides specific capabilities, comprehensive trigger terms covering multiple natural phrasings, explicit 'Use when' guidance with concrete examples, and clear distinctiveness through API-specific details and usage instructions.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'generate and edit images', 'text-to-image generation', 'image-to-image editing', with configurable resolution options (1K, 2K, 4K). Uses third person voice correctly. | 3 / 3 |
Completeness | Clearly answers both what (generate/edit images via Gemini API with resolution options) and when (explicit 'Use when' clause with comprehensive trigger scenarios including both new generation and existing image modification). | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural terms users would say: 'generate', 'create', 'edit', 'modify', 'change', 'alter', 'update images', 'change the background', 'replace X with Y'. Includes both action verbs and example phrases. | 3 / 3 |
Distinctiveness Conflict Risk | Clear niche focused specifically on image generation/editing via a specific API. The mention of the specific tool (Nano Banana Pro/Gemini 3 Pro), the --input-image parameter, and the explicit instruction not to read image files first creates distinct boundaries. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
64%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill provides clear, actionable commands for image generation and editing with good examples. However, it's somewhat verbose in places (filename generation, resolution mapping) and lacks error handling guidance or validation steps. The workflow assumes success without addressing failure scenarios.
Suggestions
Add a brief troubleshooting section or validation step (e.g., 'If script exits with error, check API key validity' or 'Verify output file exists before confirming to user')
Condense the filename generation section - one example pattern plus 1-2 examples is sufficient; Claude can extrapolate
Compress the resolution mapping into a single line or compact table (e.g., 'Map: default/1080p→1K, 2K/medium→2K, high-res/4K/ultra→4K')
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Generally efficient but includes some unnecessary explanation. The filename generation section is overly detailed with multiple examples when one or two would suffice. The resolution mapping table, while useful, could be more compact. | 2 / 3 |
Actionability | Provides fully executable bash commands with clear parameter syntax. Examples are copy-paste ready with realistic values. Both generation and editing workflows have concrete, runnable commands. | 3 / 3 |
Workflow Clarity | Steps for image editing are listed but lack validation checkpoints. No guidance on what to do if the script fails, if the API key is invalid, or how to verify the output was successful beyond checking the file exists. | 2 / 3 |
Progressive Disclosure | Content is reasonably organized with clear sections, but everything is inline in one file. The resolution mapping table and filename generation rules could potentially be separate references. For a skill of this length (~100 lines), the structure is acceptable but not optimal. | 2 / 3 |
Total | 9 / 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' field is not a dictionary | Warning |
license_field | 'license' field is missing | 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.