nanobanana

Generate and edit images using Google Gemini 3 Pro Image (Nano Banana Pro). Supports text-to-image, image editing, various aspect ratios, and high-resolution output (2K/4K). Use when user wants to generate images, create images, use Gemini image generation, or do AI image generation.

Quality

78%

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

Fix and improve this skill with Tessl

tessl review fix ./skills/nanobanana/SKILL.md

Quality

Content

68%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 body is highly actionable with copy-paste-ready commands and a real Python API, but it carries padding in the Features, Best Practices, and Rate Limits sections that Claude does not need. The batch workflow lacks validation/feedback loops, capping workflow clarity.

Suggestions

Trim the 'Features', 'Best Practices > Prompt Writing', and 'Rate Limits' sections — they restate concepts Claude already knows; keep only Gemini-specific behaviors.

Add a verification/retry step to batch generation (e.g., check each output file exists and is a valid image before proceeding, retry on safety-filter or rate-limit responses).

Fix the broken './examples/' reference (create the directory or remove the link) and consider moving prompt examples fully into references/prompts.md.

Dimension	Reasoning	Score
Conciseness	The core Quick Start, Script Reference, and Python API sections are efficient, but padded sections like 'Features' ('The model excels at: Photorealistic images, Artistic styles...'), 'Best Practices > Prompt Writing' (generic subject/style/lighting advice Claude already knows), and 'Rate Limits' restate concepts Claude knows. Not a 2 because the actionable core is genuinely lean; not a 4 because several sections are clearly trimmable fluff rather than minor instances.	3 / 5
Actionability	Fully executable, copy-paste-ready commands cover the common cases — 'python3 <skill_dir>/scripts/generate.py ...', documented CLI options, a runnable Python API example, and a batch example. Specific examples span text-to-image, editing, aspect ratios, and high-res output.	5 / 5
Workflow Clarity	The skill includes a batch operation (batch_generate.py with '-n 20') but provides no validation or verification feedback loop, and the rubric caps workflow_clarity at 3 for batch skills without validation — this cap takes precedence over the simple-skill exception. The single generate action is unambiguous, which is why this is not below 3.	3 / 5
Progressive Disclosure	Clear section structure with a well-signaled, one-level-deep References section pointing to the real references/prompts.md and scripts. Not a 5 because the referenced examples/ directory does not exist (broken link) and inline content like Features/Best Practices could live in reference files; not a 3 because references are clearly signaled and not buried.	4 / 5
	Total	15 / 20 Passed

Description

87%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 names the specific model, lists concrete capabilities, and provides an explicit 'Use when...' trigger clause with natural phrasing. It uses clean third-person voice with no fluff.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions — 'Generate and edit images', 'text-to-image, image editing, various aspect ratios, and high-resolution output (2K/4K)' — with only minor gaps in coverage (e.g., no mention of style transfer). Not a 5 because the listed actions lean on feature descriptions rather than the exhaustive, distinct concrete-action enumeration of the anchor 5 example.	4 / 5
Completeness	Explicitly answers both what ('Generate and edit images using Google Gemini 3 Pro Image ... Supports text-to-image, image editing, various aspect ratios, and high-resolution output') and when ('Use when user wants to generate images, create images, use Gemini image generation, or do AI image generation') with concrete trigger phrases, matching the anchor 5 example.	5 / 5
Trigger Term Quality	Good keyword coverage with natural phrases users say — 'generate images, create images, use Gemini image generation, or do AI image generation'. Not a 5 because common synonyms like 'make images', 'draw', or 'pictures' are missing even though generate/create and Gemini/AI variants are covered.	4 / 5
Distinctiveness Conflict Risk	Clearly scoped to 'Google Gemini 3 Pro Image (Nano Banana Pro)' with Gemini-specific triggers, giving it a clear niche with minimal conflict risk against other skills.	5 / 5
	Total	18 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
relative_links	Relative link issues: 1 missing	Warning

	Total	15 / 16 Passed

Repository: ReScienceLab/opc-skills
Path: skills/nanobanana/SKILL.md
Commit: 8cb68e3

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.