CtrlK
BlogDocsLog inGet started
Tessl Logo

nano-banana-pro

Generate or edit images via Gemini 3 Pro Image (Nano Banana Pro).

72

7.23x
Quality

62%

Does it follow best practices?

Impact

94%

7.23x

Average score across 3 eval scenarios

SecuritybySnyk

Passed

No known issues

Fix and improve this skill with Tessl

tessl review fix ./skills/nano-banana-pro/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

92%

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

This is a strong, concise skill that provides clear, executable commands for all supported use cases. It efficiently communicates API key configuration and important behavioral notes without unnecessary verbosity. The only minor weakness is the lack of bundle files to verify the referenced script, and no pointer to additional documentation if the script supports more options.

DimensionReasoningScore

Conciseness

Every line serves a purpose. No unnecessary explanations of what Gemini is or how image generation works. The content is lean and assumes Claude's competence.

3 / 3

Actionability

Provides fully executable, copy-paste-ready bash commands for all three use cases (generate, edit, multi-image). API key configuration is specific and concrete with exact config paths.

3 / 3

Workflow Clarity

This is a simple, single-purpose skill with clear, unambiguous commands for each operation mode. The notes section provides important constraints (don't read image back, use timestamps). No destructive or batch operations requiring validation loops.

3 / 3

Progressive Disclosure

Content is well-organized with clear sections, but no bundle files were provided to verify the referenced script exists. The skill is compact enough to not need external references, but the lack of any link to the actual script's documentation or advanced options is a minor gap.

2 / 3

Total

11

/

12

Passed

Description

32%

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 brief and identifies the core capability (image generation/editing) and the underlying model, but lacks explicit trigger guidance ('Use when...'), comprehensive action listing, and natural user-facing keywords. It would benefit significantly from a 'Use when' clause and more specific capability details to help Claude select it appropriately.

Suggestions

Add a 'Use when...' clause with natural trigger terms, e.g., 'Use when the user asks to create, generate, edit, or modify images, pictures, or photos.'

List more specific capabilities beyond 'generate or edit', such as 'apply style changes, add/remove objects, create from text prompts, modify existing images.'

Include common user-facing keywords like 'picture', 'photo', 'illustration', 'create image', 'image editing' to improve trigger term coverage.

DimensionReasoningScore

Specificity

Names the domain (image generation/editing) and two actions (generate, edit), but doesn't list more specific capabilities like style transfer, inpainting, resizing, format conversion, etc.

2 / 3

Completeness

States what it does (generate or edit images) but has no 'Use when...' clause or explicit trigger guidance, which per the rubric should cap completeness at 2, and the 'what' is also quite thin, bringing this to a 1.

1 / 3

Trigger Term Quality

Includes 'images', 'generate', 'edit', and the model name 'Gemini 3 Pro Image', but misses common user terms like 'create image', 'picture', 'photo', 'illustration', 'modify image', or file format keywords. The parenthetical 'Nano Banana Pro' is an internal/brand name unlikely to be used by users.

2 / 3

Distinctiveness Conflict Risk

Mentioning the specific model name (Gemini 3 Pro Image / Nano Banana Pro) adds some distinctiveness, but 'generate or edit images' is broad enough to overlap with other image-related skills like DALL-E or Stable Diffusion tools.

2 / 3

Total

7

/

12

Passed

Validation

72%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation8 / 11 Passed

Validation for skill structure

CriteriaDescriptionResult

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

8

/

11

Passed

Repository
Hung-Reo/hungreo-openclaw
Reviewed

Table of Contents

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.