CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

nano-banana-build

Generate and edit high-quality images using Gemini 2.5 Flash Image and Gemini 3 Pro Image (Nano Banana). Supports Text-to-Image, Style Transfer, Virtual Try-On, and Character Consistency.

Quality

82%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

86%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 a clean, well-structured overview with executable quick-start code and excellent progressive disclosure into verified reference files. Its main weakness is minor actionability gaps in the code examples (placeholder URI, no output extraction) and a lack of explicit output-validation checkpoints.

Suggestions

Replace the placeholder 'gs://.../shoe.jpg' with a concrete local-file upload pattern (e.g. client.files.upload) so the editing example is fully runnable.

Add a short snippet showing how to read and save the returned image (e.g. response.output[0].data / Image.open) to close the actionability gap.

Add a brief validation note (e.g. check that the response contains an image part before saving) to strengthen workflow clarity.

DimensionReasoningScore

Conciseness

The body is lean and efficient: a one-line purpose, a minimal setup snippet, terse model descriptions, and two compact code workflows with no padding or explanation of concepts Claude already knows; every token earns its place.

5 / 5

Actionability

Provides concrete, mostly copy-paste-ready code for both generation and editing with real SDK calls; not a 5 because the editing example uses a placeholder file_uri ('gs://.../shoe.jpg') and neither example shows how to extract/save the returned image.

4 / 5

Workflow Clarity

The two workflows are unambiguous single-call actions with clear model selection and config; not a 5 because there are no explicit validation or output-handling checkpoints, though image generation is not destructive so the cap does not apply.

4 / 5

Progressive Disclosure

The SKILL.md is a concise overview with six well-signaled, one-level-deep reference links (all verified to exist in references/), each with a clear description; content is appropriately split and easy to navigate.

5 / 5

Total

18

/

20

Passed

Description

70%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 specific and distinctive, naming concrete image capabilities and the Nano Banana model family, but it omits any explicit 'when to use' trigger guidance, which caps its completeness. Adding a 'Use when...' clause would raise the overall score.

Suggestions

Append an explicit trigger clause such as 'Use when the user asks to generate or edit images, apply style transfer, do virtual try-on, or maintain character consistency across images.'

Add common synonyms or natural phrasings users might say (e.g. 'image generation', 'AI image editing', 'text to image') to broaden trigger coverage.

Drop the slightly fluffy 'high-quality' qualifier in favor of more concrete capability detail to tighten specificity.

DimensionReasoningScore

Specificity

Names the image domain and lists several concrete capability actions ('Text-to-Image, Style Transfer, Virtual Try-On, and Character Consistency') plus generate/edit, with only minor gaps in coverage; not a 5 because the actions are high-level category labels rather than fully concrete operations.

4 / 5

Completeness

Clearly states what the skill does ('Generate and edit high-quality images...') but provides no 'Use when...' clause or equivalent explicit trigger guidance, which caps completeness at 3 per the judging guidelines.

3 / 5

Trigger Term Quality

Includes natural terms users would say ('generate', 'edit images', 'text-to-image', 'style transfer', 'virtual try-on', 'character consistency', 'Nano Banana'); a few common synonyms or file/extension variants are missing, so it is not a 5.

4 / 5

Distinctiveness Conflict Risk

Tied to the distinctive 'Nano Banana' / Gemini image models niche with clearly differentiated capabilities, giving minimal overlap risk with other skills.

5 / 5

Total

16

/

20

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository

cnemri/google-genai-skills

Path

skills/nano-banana-build/SKILL.md

Revision

7277476

Reviewed

Table of Contents

DiscoveryImplementationValidation

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.

Claim skill