nano-banana-2

Generate and edit images using Google's Nano Banana 2 (Gemini 3.1 Flash Image Preview) API. This skill should be used when the user asks to create or modify images, especially when they need fast iteration, explicit aspect-ratio control, or resolution control from 512px to 4K.

Quality

83%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

82%Weight 40%Scale 1-5

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

The content is highly actionable and well-structured, with executable commands and clear parameter guidance throughout. The main gaps are minor: slight redundancy in the Examples section and the absence of an explicit error-recovery feedback loop for API failures.

Suggestions

Add a short error-recovery note for API failures (e.g. retry on transient errors, surface the API error message to the user) to strengthen the workflow's validation/feedback loop.

Trim redundancy between the Usage and Examples sections — the Examples could show only the distinctive flags rather than repeating the full command template.

Consider moving the resolution/aspect-ratio mapping tables into a separate reference file so the SKILL.md overview stays leaner, improving progressive disclosure.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes Claude's competence — sections like Resolution Options and Aspect Ratios provide useful disambiguation tables rather than padding — but the Examples section partially duplicates the Usage commands and a few lines ('Do not use gemini-3-pro-image-preview in this skill') could be trimmed, so it is efficient with minor over-explanation.	4 / 5
Actionability	Provides fully executable, copy-paste-ready `uv run` commands with complete argument lists, concrete parameter mappings for resolution and aspect ratios, and worked examples covering the common generate and edit-with-references cases.	5 / 5
Workflow Clarity	The single action (run generate_image.py) is unambiguous and the API-key resolution is given as an explicit ordered sequence with a stop-and-report checkpoint, but there is no error-recovery feedback loop (e.g. what to do on an API error or retry), leaving a minor validation gap.	4 / 5
Progressive Disclosure	The body is well-organized into clear sections with a single one-level-deep reference (the generate_image.py script) clearly signaled in code blocks; no bundle files exist to verify further, and the content is appropriately placed in one file with only minor organization gaps.	4 / 5
	Total	17 / 20 Passed

Description

83%Weight 40%Scale 1-5

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 strong: it clearly states what the skill does and when to use it, with concrete trigger phrases and model-specific distinctiveness. It could be improved by adding a few more natural synonyms and acknowledging reference-image composition as a capability.

Dimension	Reasoning	Score
Specificity	Names the domain and several concrete actions/capabilities — 'Generate and edit images', 'fast iteration', 'explicit aspect-ratio control', 'resolution control from 512px to 4K' — but does not enumerate every capability (e.g. reference-image composition), so it falls at 'several specific actions; minor gaps' rather than comprehensive.	4 / 5
Completeness	Explicitly answers both 'what' (generate and edit images via the Nano Banana 2 API) and 'when' ('This skill should be used when the user asks to create or modify images, especially when they need fast iteration, explicit aspect-ratio control, or resolution control from 512px to 4K'), with concrete trigger phrases.	5 / 5
Trigger Term Quality	Includes natural user phrases like 'create or modify images', 'fast iteration', 'aspect-ratio control', and 'resolution control', giving good keyword coverage, but misses common synonyms users might say ('draw', 'render', 'make a picture') so it is not fully comprehensive.	4 / 5
Distinctiveness Conflict Risk	Naming the specific model ('Nano Banana 2', 'Gemini 3.1 Flash Image Preview') gives it a clear niche, but the trigger 'when the user asks to create or modify images' is broad and could overlap with other general image-generation skills, so minor overlap risk remains.	4 / 5
	Total	17 / 20 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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: intellectronica/agent-skills
Path: plugins/nano-banana-2/skills/SKILL.md
Commit: 9b0e00a

Reviewed: 5 days 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.