CtrlK
BlogDocsLog inGet started
Tessl Logo

nano-banana-pro

Generate/edit images with Nano Banana Pro (Gemini 3 Pro Image). Use for image create/modify requests incl. edits. Supports text-to-image + image-to-image; 1K/2K/4K; use --input-image.

95

3.12x
Quality

Does it follow best practices?

Impact

100%

3.12x

Average score across 3 eval scenarios

SecuritybySnyk

Risky

Do not use without reviewing

SKILL.md
Quality
Evals
Security

Quality

Content

85%

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

A highly actionable, well-organized single-purpose skill body with executable commands matching the bundled script, a clear iterative workflow, and an error-recovery loop. The only weakness is minor generic listing that slightly inflates token use.

Suggestions

Trim the generic editing-task enumeration ('add/remove elements, change style, adjust colors, blur background, etc.') since Claude already knows common image-editing operations.

Consider compressing the resolution-mapping table to only the non-obvious mappings (e.g., '1080'→1K, 'ultra'→4K) rather than restating self-evident equivalences.

DimensionReasoningScore

Conciseness

Mostly lean with executable commands and compact mapping tables, but includes generic padding Claude already knows ('add/remove elements, change style, adjust colors, blur background, etc.') and partly obvious resolution equivalences that could be tightened.

2 / 3

Actionability

Provides fully executable `uv run` invocations with specific flags and realistic example filenames, and the documented interface (--prompt, --filename, --input-image, --resolution, --api-key) matches the actual bundled script.

3 / 3

Workflow Clarity

The draft → iterate → final workflow is clearly sequenced with explicit rationale, plus a preflight checklist and error→fix troubleshooting feedback loop for recovery.

3 / 3

Progressive Disclosure

Self-contained single-purpose body with one well-signaled, one-level-deep bundle reference ({baseDir}/scripts/generate_image.py) that genuinely exists, and clearly organized sections with no nested references.

3 / 3

Total

11

/

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.

A concise, well-scoped description that names the tool, lists concrete generation/editing capabilities, and provides an explicit 'Use for' trigger with natural terminology. It clearly answers both what the skill does and when to invoke it.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — 'Generate/edit images', 'text-to-image + image-to-image', '1K/2K/4K', '--input-image' — matching the multiple-specific-actions anchor rather than just naming a domain.

3 / 3

Completeness

Explicitly answers what ('Generate/edit images with Nano Banana Pro') and when ('Use for image create/modify requests incl. edits'), with an explicit 'Use for' trigger clause.

3 / 3

Trigger Term Quality

Covers natural phrasings a user would say ('image create/modify requests', 'edits', 'text-to-image', 'image-to-image'), giving good coverage of variations rather than a single generic term.

3 / 3

Distinctiveness Conflict Risk

Targets a specific named API (Nano Banana Pro / Gemini 3 Pro Image) for image generation/editing, a clear niche unlikely to trigger for unrelated skills.

3 / 3

Total

12

/

12

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.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
Dicklesworthstone/pi_agent_rust
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.