nano-banana

Generate or edit images via Nano Banana image models. Triggers on "generate image", "image generation", "nano banana", "edit image", "nano banana pro", "nano banana 2"

Quality

92%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Quality

Content

85%

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

The body is well-structured and highly actionable with executable commands and a clear output-delivery rule. The main weakness is a duplicated sentence in the Output section that wastes tokens and should be removed.

Suggestions

Remove the duplicated sentence on line 73 ('Absolute paths are used as-is.' appears twice) to eliminate wasted tokens.

Consider whether 'This keeps requests fast and avoids File API auth issues with the enterprise endpoint.' in Input image handling is needed, or whether it can be tightened to the actionable rule alone.

Verify the {baseDir} placeholder convention is documented elsewhere or note it once so the commands are unambiguous to any reader.

Dimension	Reasoning	Score
Conciseness	The body is mostly lean tables and commands, but line 73 duplicates "Absolute paths are used as-is. Absolute paths are used as-is.", wasting tokens, which fits the 'mostly efficient but could be tightened' anchor rather than the score-3 'every token earns its place'.	2 / 3
Actionability	Copy-paste-ready commands like "node {baseDir}/scripts/generate-image.js --prompt ... --filename ..." plus a complete options table provide fully executable, specific guidance, matching the score-3 anchor rather than the pseudocode score-2 example.	3 / 3
Workflow Clarity	This is a simple single-action skill (run one script) whose action is unambiguous, and the 'Sending images to the user' section adds an explicit output checkpoint (the verbatim MEDIA: line); per the simple-skills note, that clears the score-3 bar.	3 / 3
Progressive Disclosure	Well-organized sections keep the SKILL.md as an overview with a single one-level-deep reference to scripts/generate-image.js (a real, verified bundle file), matching the 'clear overview with well-signaled one-level-deep references' anchor.	3 / 3
	Total	11 / 12 Passed

Description

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.

The description is concise, third-person, and answers both what and when with explicit, natural trigger terms. It is distinctive and unlikely to mis-trigger, with no over-claims or fluff.

Dimension	Reasoning	Score
Specificity	"Generate or edit images via Nano Banana image models" lists multiple concrete actions (generate, edit) tied to a specific model family, matching the 'lists multiple specific concrete actions' anchor rather than the score-2 partial coverage.	3 / 3
Completeness	It states what ("Generate or edit images via Nano Banana image models") and explicitly when ("Triggers on ..."), satisfying both halves the score-3 anchor requires; the score-2 anchor caps completeness when the 'when' is missing or only implied, which is not the case here.	3 / 3
Trigger Term Quality	"Triggers on 'generate image', 'image generation', 'nano banana', 'edit image', 'nano banana pro', 'nano banana 2'" gives broad coverage of natural phrases a user would actually say, matching the 'good coverage of natural terms' anchor; it is not jargon-only like the score-1 example.	3 / 3
Distinctiveness Conflict Risk	The Nano Banana niche with model-specific triggers (nano banana, nano banana pro, nano banana 2) is a clear niche unlikely to collide with other skills, matching the 'clear niche with distinct triggers' anchor rather than the score-2 'could still overlap' case.	3 / 3
	Total	12 / 12 Passed

Validation

81%

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 — 13 / 16 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	13 / 16 Passed

Repository: nexu-io/nexu
Path: skills/nexubot/nano-banana/SKILL.md
Commit: dadfb1c

Reviewed: about 15 hours 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.