Tessl • The management layer for AI agent skills

SkillPublic

nano-banana-use

Generate, edit, and compose images using Gemini Nano Banana models via portable Python scripts. Handles authentication via API Key or Vertex AI environment variables. Available parameters: prompt, model, aspect-ratio, safety-filter-level. Always confirm parameters with the user or explicitly state defaults before running.

Quality

76%

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/nano-banana-use/SKILL.md

Quality

Content

83%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 lean, action-oriented, and provides copy-paste-ready commands for all operations with verified bundle scripts. The main weakness is workflow clarity: the edit and compose operations overwrite or consume inputs without explicit verification or validation checkpoints.

Suggestions

Add an explicit verification step after image generation/editing (e.g. confirm the output file exists and is a valid image before reporting success), especially for edit and compose which overwrite inputs.

Surface key non-default script options earlier or note where to find the full argument set, since the inline Options list only covers the generate case.

Add a brief note on expected behavior when auth is missing or an API call fails, to give Claude a clear recovery path.

Dimension	Reasoning	Score
Conciseness	The body is lean and efficient: prerequisites, parameter confirmation, and executable uv commands with no padding or explanation of concepts Claude already knows; every section earns its place.	5 / 5
Actionability	Provides fully executable, copy-paste-ready `uv run` commands for all three operations (generate, edit, compose) with concrete arguments and outputs, plus an explicit Options list covering defaults and supported values.	5 / 5
Workflow Clarity	The generate flow has a clear two-step sequence with parameter confirmation as a checkpoint, but the destructive/batch-adjacent operations (edit, compose that overwrite or consume inputs) lack explicit validation or verification steps before running, capping the score at 3 per the feedback-loop guideline.	3 / 5
Progressive Disclosure	Well-organized with clear sections (Prerequisites, Usage, Options) and references to real bundle scripts (generate_image.py, edit_image.py, compose_image.py) verified to exist; minor gap is that all guidance is inline with no separate deeper-reference file, but the structure is appropriate for this skill size.	4 / 5
	Total	17 / 20 Passed

Description

56%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 concrete and specific about capabilities, models, parameters, and auth, but it omits any explicit 'when to use this skill' trigger guidance, which is the main weakness. Trigger-term naturalness is moderate rather than comprehensive.

Suggestions

Add an explicit 'Use when...' clause (e.g. 'Use when the user asks to generate, edit, or compose images') to satisfy the completeness dimension and provide trigger guidance.

Broaden trigger terms with natural user phrasing and synonyms such as 'make an image', 'image generation', 'edit a photo', or 'combine images'.

Mention supported input image formats or output formats to improve distinctiveness and trigger-term coverage.

Dimension	Reasoning	Score
Specificity	Names the domain (Nano Banana image models) and multiple concrete actions ('Generate, edit, and compose images') plus specific parameters (prompt, model, aspect-ratio, safety-filter-level) and auth methods, leaving only minor gaps in coverage.	4 / 5
Completeness	The 'what' is clearly stated, but there is no explicit 'Use when...' clause or trigger guidance describing when Claude should invoke the skill, which caps completeness at 3 per the rubric guideline.	3 / 5
Trigger Term Quality	Includes relevant keywords like 'generate', 'edit', 'compose images' and model names, but lacks common synonyms users would naturally say (e.g. 'make an image', 'image generation', 'edit photo') and file extensions; coverage is moderate rather than comprehensive.	3 / 5
Distinctiveness Conflict Risk	The 'Nano Banana' branding and named Gemini image models carve a clear niche with distinct triggers, with only minor overlap risk against other generic image-generation skills.	4 / 5
	Total	14 / 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: cnemri/google-genai-skills
Path: skills/nano-banana-use/SKILL.md
Revision: 7277476

Reviewed: 1 month ago

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.

nano-banana-use

Table of Contents

Is this your skill?