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.
Install with Tessl CLI
npx tessl i github:Dicklesworthstone/pi_agent_rust --skill nano-banana-pro90
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 a strong skill description that efficiently packs specific capabilities, clear trigger conditions, and distinctive identifiers into a concise format. It uses third person voice correctly, provides concrete actions, and includes both natural user terms and technical specifics. The abbreviated style (incl., +) maintains clarity while being economical.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple concrete actions: 'Generate/edit images', 'text-to-image + image-to-image', specifies resolution options '1K/2K/4K', and mentions specific flag '--input-image'. These are specific, actionable capabilities. | 3 / 3 |
Completeness | Clearly answers both what ('Generate/edit images', 'text-to-image + image-to-image', resolution options) and when ('Use for image create/modify requests incl. edits'). Has explicit trigger guidance. | 3 / 3 |
Trigger Term Quality | Includes natural keywords users would say: 'image', 'create', 'modify', 'edits', 'text-to-image', 'image-to-image'. Also includes the tool name 'Nano Banana Pro' and 'Gemini 3 Pro Image' for users who know the specific tool. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with specific tool name 'Nano Banana Pro (Gemini 3 Pro Image)', clear image generation/editing niche, and specific technical details like '--input-image' flag that distinguish it from other potential image 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 workflow for iterative image generation. The content provides good error handling guidance and practical examples. Minor improvements could be made in trimming redundant explanations and potentially splitting detailed reference sections into separate files.
Suggestions
Tighten the resolution mapping section - Claude can infer most of these mappings from a shorter list
Consider moving prompt templates to a separate TEMPLATES.md file and referencing it, keeping SKILL.md as a quick-start overview
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is mostly efficient but includes some redundancy (e.g., resolution mapping table could be tighter, filename examples are somewhat verbose). The prompt templates section adds value but the overall document could be trimmed by ~20%. | 2 / 3 |
Actionability | Provides fully executable bash commands with clear parameter options. Examples are copy-paste ready with concrete filenames, prompts, and resolution flags. The preflight checks and common failures section gives specific diagnostic commands. | 3 / 3 |
Workflow Clarity | Clear draft→iterate→final workflow with explicit resolution progression. Includes validation steps (preflight checks), error recovery guidance (common failures with fixes), and explicit checkpoints for when to move from 1K to 4K. | 3 / 3 |
Progressive Disclosure | Content is well-organized with clear section headers, but everything is inline in a single file. The prompt templates, resolution mapping, and filename generation sections could potentially be split out for a cleaner overview, though the current length (~100 lines) is borderline acceptable. | 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.
- 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.