CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

muapi-nano-banana

Reasoning-driven image generation using structured creative briefs (Gemini 3 style) — generates high-fidelity images via muapi.ai with logic-based prompting

Quality

65%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./library/visual/nano-banana/SKILL.md

The canonical home for this skill is muapi-nano-banana in SamurAIGPT/Generative-Media-Skills

SKILL.md
Quality
Evals
Security

Quality

Content

61%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 well-structured and action-oriented with a real executable script and example, but it repeats guidance across sections and lacks validation checkpoints in its workflow. Tightening redundancy and adding a verify step would improve both conciseness and workflow clarity.

Suggestions

Consolidate the repeated 'No Keyword Soup' guidance into a single Constraints section to remove triplicated padding.

Add a validation/feedback step to the protocol (e.g. verify the generated image matches the requested text and lighting before returning, retry if not).

Extend the bash example to show --lighting, --text, and --resolution so it covers the common cases copy-paste ready.

DimensionReasoningScore

Conciseness

Mostly efficient with sectioned structure, but the 'No Keyword Soup' guidance is repeated across Core Competencies, the Prompt Optimization Protocol, and Constraints, and introductory framing ('moves beyond keyword stuffing', 'Based on the advanced prompting architecture of Google's Gemini 3') pads the skill; not a 2 because the core tables and example earn their place.

3 / 5

Actionability

Provides a concrete, executable bash invocation with real flags and a real backing script (scripts/generate-nano-art.sh verified present); not a 5 because the example omits --lighting/--text/--resolution variations and the optimization protocol is advisory rather than copy-paste ready.

4 / 5

Workflow Clarity

A rough two-step sequence (Step 1 Define Creative Logic, Step 2 Invoke the script) is present plus the pre-call rewrite protocol, but there are no validation checkpoints or error-handling feedback loops; not a 4 because checkpoints are entirely implicit.

3 / 5

Progressive Disclosure

Content is well organized into clearly headed sections with a single, clearly signaled script reference (scripts/generate-nano-art.sh) at one level deep and no nested references; not a 5 because the body exceeds ~50 lines and some inlined reference-style material (advanced features, optimization protocol) could move to a references file.

4 / 5

Total

14

/

20

Passed

Description

53%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 clearly states what the skill does and ties it to a specific provider and prompting style, but it omits any explicit 'when to use' trigger guidance and leans on jargon over natural user phrasing. Adding a 'Use when...' clause with everyday synonyms would lift completeness and trigger quality.

Suggestions

Append a 'Use when...' clause naming natural trigger phrases (e.g. 'Use when the user wants to generate AI images, art, or pictures, especially photorealistic or text-rendered output').

Replace some jargon ('Gemini 3 style', 'logic-based prompting') with everyday synonyms users actually say, like 'AI image generation' or 'generate pictures'.

List one or two more concrete capabilities (e.g. legible text rendering, identity consistency) to broaden action coverage.

DimensionReasoningScore

Specificity

Names the domain and concrete actions ('generates high-fidelity images via muapi.ai', 'logic-based prompting', 'structured creative briefs') but coverage is not comprehensive; not a level 4 because only a couple of distinct actions are listed.

3 / 5

Completeness

The 'what' is clear ('generates high-fidelity images via muapi.ai with logic-based prompting') but there is no 'Use when...' clause or equivalent trigger guidance, which caps completeness at 3 per the judging guidelines.

3 / 5

Trigger Term Quality

Includes the natural term 'image generation' but relies heavily on jargon ('Gemini 3 style', 'muapi.ai', 'logic-based prompting') and misses common synonyms users would say like 'AI art', 'pictures', or 'photos'.

3 / 5

Distinctiveness Conflict Risk

The muapi.ai and Gemini 3 / nano-banana framing carves out a fairly distinct niche with only minor overlap risk against generic image-generation skills; not a 5 because image generation itself is a broad shared domain.

4 / 5

Total

13

/

20

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.

Validation — 15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository

SamurAIGPT/Generative-Media-Skills

Path

library/visual/nano-banana/SKILL.md

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.