Generate or edit images via Gemini 3 Pro Image (Nano Banana Pro).
70
66%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./skills/nano-banana-pro/SKILL.mdQuality
Discovery
32%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 is minimal and functional but incomplete. It identifies the core capability (image generation/editing) and the specific tool, but lacks explicit trigger guidance and comprehensive action details. The absence of a 'Use when...' clause significantly limits Claude's ability to correctly select this skill from a larger skill set.
Suggestions
Add a 'Use when...' clause with trigger terms like 'generate image', 'create picture', 'edit photo', 'AI image', 'Gemini image'
Expand specific capabilities beyond just 'generate or edit' - include details like supported styles, editing operations (resize, remove background, style transfer), or output formats
Include natural language variations users might say: 'make me an image', 'create artwork', 'modify this picture', 'photo editing'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (images) and two actions (generate, edit), but lacks comprehensive detail about specific capabilities like style transfer, inpainting, resolution options, or format support. | 2 / 3 |
Completeness | Describes what it does (generate/edit images) but completely lacks a 'Use when...' clause or any explicit trigger guidance for when Claude should select this skill. | 1 / 3 |
Trigger Term Quality | Includes 'images', 'generate', and 'edit' which are natural terms, but missing common variations like 'picture', 'photo', 'create image', 'modify image', 'AI art', or file extensions. | 2 / 3 |
Distinctiveness Conflict Risk | The specific model name 'Gemini 3 Pro Image (Nano Banana Pro)' adds some distinctiveness, but 'generate or edit images' is generic enough to potentially conflict with other image generation skills like DALL-E or Midjourney integrations. | 2 / 3 |
Total | 7 / 12 Passed |
Implementation
100%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is an excellent skill file that exemplifies token efficiency and actionability. It provides complete, executable commands for all use cases without any unnecessary explanation. The structure is clean, the examples are concrete, and the notes section efficiently captures important constraints and behaviors.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely lean and efficient. No unnecessary explanations of what Gemini is or how image generation works. Every line provides actionable information Claude needs. | 3 / 3 |
Actionability | Provides complete, copy-paste ready bash commands for all use cases (generate, edit, multi-image, aspect ratio). Includes concrete examples with actual flags and parameters. | 3 / 3 |
Workflow Clarity | For a simple single-task skill, the workflow is unambiguous. Each operation type has its own clear command example. The notes section provides important constraints without cluttering the main instructions. | 3 / 3 |
Progressive Disclosure | Well-organized with clear sections (Generate, Edit, Multi-image, API key, Notes). Content is appropriately sized for a single file with no need for external references. Easy to scan and find relevant information. | 3 / 3 |
Total | 12 / 12 Passed |
Validation
72%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 8 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
metadata_version | 'metadata.version' is missing | Warning |
metadata_field | 'metadata' should map string keys to string values | Warning |
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 8 / 11 Passed | |
d1f07c3
Table of Contents
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.