CtrlK
BlogDocsLog inGet started
Tessl Logo

nanobanana-skill

Generate or edit images via Google Gemini (nanobanana). This is the DEFAULT image skill — use whenever the user asks to generate, create, or edit an image and does NOT name another provider. Triggers: "nanobanana", "generate image", "create image", "edit image", "图片生成", "生成图片", "AI绘图", "图片编辑". Do NOT use for diagrams (架构图/流程图/时序图) — draw those with Mermaid or code instead.

72

Quality

88%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

SKILL.md
Quality
Evals
Security

Quality

Content

77%

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 executable commands and clear generation/editing workflows, but it is somewhat token-heavy due to redundant examples and inline reference tables that could be offloaded to a bundled reference file.

Suggestions

Consolidate the five overlapping Examples into one or two representative generation and editing examples to reduce redundancy.

Move the aspect-ratio, model, and resolution option tables into a references/ file (e.g. OPTIONS.md) and link to it from the main body to improve progressive disclosure.

Trim the Best Practices section of items that restate option defaults already listed under Available Options.

DimensionReasoningScore

Conciseness

Mostly efficient with executable commands, but the five Examples overlap heavily and the Best Practices section restates option guidance (e.g., model speed/quality tradeoffs) already covered in Available Options; could be tightened.

2 / 3

Actionability

Provides fully executable, copy-paste-ready commands with real flags (--prompt, --size, --model, --resolution, --input, --output) and concrete examples for both generation and editing.

3 / 3

Workflow Clarity

Generation and editing flows are each laid out as clear numbered sequences (ask for inputs → run script → show path); this is a simple non-destructive task so the absence of validation checkpoints does not cap the score per the simple-skills note.

3 / 3

Progressive Disclosure

Sections are well-organized, but everything is inline in a 135-line file with no bundle references; the long aspect-ratio/model/resolution option tables are reference material that could be split into a separate file, matching the 'content that should be separate is inline' anchor.

2 / 3

Total

10

/

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 strong: it states concrete capabilities, provides explicit use-when triggers in both English and Chinese, and draws a clear boundary against diagram skills. It uses appropriate third-person/imperative voice without fluff.

DimensionReasoningScore

Specificity

Names concrete actions ("Generate or edit images") tied to a specific provider/tool ("Google Gemini (nanobanana)"), matching the multiple-specific-actions anchor; not a 2 because it goes beyond naming only a domain.

3 / 3

Completeness

Explicitly answers what (generate/edit images via Gemini) and when ("use whenever the user asks to generate, create, or edit an image") with an explicit Triggers clause; not a 2 because the when-guidance is explicit, not implied.

3 / 3

Trigger Term Quality

Lists natural terms users would say — "generate image", "create image", "edit image", plus Chinese variants ("图片生成", "AI绘图") and the tool name, giving broad coverage.

3 / 3

Distinctiveness Conflict Risk

Declares a clear niche ("DEFAULT image skill") with explicit exclusion ("Do NOT use for diagrams... draw those with Mermaid or code"), making conflicts unlikely.

3 / 3

Total

12

/

12

Passed

Validation

93%

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

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

allowed_tools_field

'allowed-tools' contains unusual tool name(s)

Warning

Total

15

/

16

Passed

Repository
feiskyer/claude-code-settings
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.