nano-banana-pro
Generate/edit images with Nano Banana Pro (Gemini 3 Pro Image). Use for image create/modify requests incl. edits. Supports text-to-image + image-to-image; 1K/2K/4K; use --input-image.
92
88%
Does it follow best practices?
Impact
100%
3.12xAverage score across 3 eval scenarios
Risky
Do not use without reviewing
Quality
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, concise description that packs significant detail into a compact format. It names the specific tool, lists concrete capabilities (generate, edit, text-to-image, image-to-image), includes resolution options, and provides explicit trigger guidance. The abbreviations (incl., 1K/2K/4K) keep it terse without sacrificing clarity.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple concrete actions: generate images, edit images, text-to-image, image-to-image, supports multiple resolutions (1K/2K/4K), and mentions the --input-image flag. These are specific, actionable capabilities. | 3 / 3 |
Completeness | Clearly answers 'what' (generate/edit images with specific model, text-to-image, image-to-image, multiple resolutions) and 'when' ('Use for image create/modify requests incl. edits'). The 'Use for...' clause serves as an explicit trigger guidance. | 3 / 3 |
Trigger Term Quality | Includes strong natural trigger terms: 'image', 'create', 'modify', 'edits', 'text-to-image', 'image-to-image', 'generate', plus the specific model names 'Nano Banana Pro' and 'Gemini 3 Pro Image' which users might reference. Covers common variations well. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive due to naming the specific model (Nano Banana Pro / Gemini 3 Pro Image) and the specific flag (--input-image). This clearly carves out a niche for image generation/editing with this particular tool, unlikely to conflict with other skills. | 3 / 3 |
Total | 12 / 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 solid, actionable skill with clear executable commands and a well-defined iterative workflow. Its main weakness is moderate verbosity—several sections (filename generation examples, resolution mapping, prompt templates) could be more compact or split into reference files. The workflow clarity is strong with good preflight checks and error recovery guidance.
Suggestions
Trim the filename generation section to 1-2 examples instead of 4, and condense the format rules into a single line pattern
Consider moving prompt templates and resolution mapping details into a separate reference file to keep the main SKILL.md leaner
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is mostly efficient but includes some sections that could be tightened. The filename generation section with multiple examples is somewhat verbose, the resolution mapping table over-explains, and the prompt templates section adds bulk. The preflight section and API key order explanation are useful but could be more compact. | 2 / 3 |
Actionability | Provides fully executable bash commands with clear argument syntax, concrete examples for both generation and editing workflows, specific resolution mappings, and copy-paste ready command patterns. The {baseDir} placeholder is appropriate for a skill context. | 3 / 3 |
Workflow Clarity | The draft → iterate → final workflow is clearly sequenced with explicit rationale (don't burn time on 4K until prompt is correct). The editing workflow has clear steps, preflight checks serve as validation, and common failure modes with fixes provide error recovery guidance. | 3 / 3 |
Progressive Disclosure | The content is well-structured with clear section headers, but it's a fairly long single file that could benefit from splitting out reference material (prompt templates, resolution mappings) into separate files. No external references are used despite the content length exceeding what's needed for a quick overview. | 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
- Dicklesworthstone/pi_agent_rust
- Commit
47823e3
- 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.