CtrlK
BlogDocsLog inGet started
Tessl Logo

nano-banana-prompts

Generate optimized prompts for Gemini 2.5 Flash Image (Nano Banana). Use for image generation, crafting photo prompts, art styles, or multi-turn editing workflows with best practices.

85

1.03x
Quality

79%

Does it follow best practices?

Impact

97%

1.03x

Average score across 3 eval scenarios

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

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

Quality

Content

71%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.

Highly actionable prompt templates and examples make this skill immediately usable, supported by clear editing workflows. Its weaknesses are token efficiency — significant redundancy across validation, issues, and troubleshooting sections — and a monolithic structure that underuses progressive disclosure.

Suggestions

Consolidate the 'Common Issues & Solutions', 'Troubleshooting Guide' table, and 'Prompt Validation' checklists, which repeat the same guidance (e.g., text under 25 chars, one change per turn, rule-of-thirds); merge into a single troubleshooting section to cut length.

Move the per-domain template and example blocks (photography, art, product, landscape, abstract) into a references/ file linked from a concise overview, so the main SKILL.md stays a lean overview with one-level-deep pointers.

Either reference and populate assets/nano-banana.png or remove it; a '404: Not Found' asset file signals a broken bundle.

DimensionReasoningScore

Conciseness

The ~415-line body is mostly useful but visibly padded — the 'Prompt Validation' checklists restate the components already given, and 'Common Issues & Solutions' overlaps heavily with the 'Troubleshooting Guide' table, so it could be tightened substantially.

3 / 5

Actionability

It provides numerous copy-paste-ready, filled-in prompt templates and worked examples across photography, art, product, landscape, and abstract cases, fully covering the common scenarios.

5 / 5

Workflow Clarity

The multi-turn editing and refinement workflows are clearly sequenced with validation checklists and a one-change-per-turn rule, but the sequences are spread across sections rather than presented as a single checkpointed flow.

4 / 5

Progressive Disclosure

It is a monolithic single-file skill with no signaled one-level-deep references; the provided asset (nano-banana.png) is a '404: Not Found' placeholder and is never referenced, and content this large (templates, reference lists) could be split into separate files.

3 / 5

Total

15

/

20

Passed

Description

87%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.

A strong, third-person description that explicitly answers both what the skill does and when to use it, with concrete trigger terms tied to a distinct niche. Minor gaps in keyword synonyms and action enumeration keep specificity and trigger quality just below full marks.

DimensionReasoningScore

Specificity

Names the domain and several concrete actions — 'Generate optimized prompts', 'crafting photo prompts', 'art styles', and 'multi-turn editing workflows' — but coverage is more templated than fully enumerated, leaving minor gaps versus the comprehensive anchor.

4 / 5

Completeness

It clearly states the 'what' ('Generate optimized prompts for Gemini 2.5 Flash Image (Nano Banana)') and an explicit 'Use for ...' 'when' clause with concrete trigger phrases, matching the both-answered anchor.

5 / 5

Trigger Term Quality

Good natural trigger coverage with 'image generation', 'photo prompts', 'art styles', and 'multi-turn editing workflows', but it omits common synonyms users might say (e.g., 'AI images', 'Gemini image') and any file/format markers.

4 / 5

Distinctiveness Conflict Risk

The niche is explicit and narrow (Gemini 2.5 Flash Image / Nano Banana prompt generation) with distinct triggers, giving minimal overlap risk with other skills.

5 / 5

Total

18

/

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.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
secondsky/claude-skills
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.