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

60%

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 ./.opencode/skills/muapi-nano-banana/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

50%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 skill body is well-sectioned and offers a genuinely usable prompting formula, but it is held back by duplicated guidance, references to scripts that are missing from the bundle, and a workflow that ends at script invocation with no handling of the result. Tightening the repeated sections and completing the execution path would lift it significantly.

Suggestions

Consolidate the 'Core Competencies', 'Prompt Optimization Protocol', and 'Constraints & Guardrails' sections — the no-keyword-soup and full-sentence rules each appear twice.

Include the referenced scripts (scripts/generate-nano-art.sh) in the bundle, or remove/document the fallback to core/media/generate-image.sh so the command is actually executable.

Extend the workflow past invocation: state what the script outputs (file path? URL?), how to verify the image matches the brief, and what to do on failure.

DimensionReasoningScore

Conciseness

The body is mostly instruction rather than explanation of known concepts, but guidance is duplicated: 'no keyword soup' appears in both 'Prompt Optimization Protocol' ("Remove '8k, masterpiece, ultra-detailed'") and 'Constraints & Guardrails' ("Do not use 'trending on artstation, masterpiece, 8k'"), and the 'Core Competencies' section previews the later sections. This fits 'mostly efficient but includes some unnecessary explanation or could be tightened' rather than level 4.

3 / 5

Actionability

The bash example with flags is concrete, but the invoked scripts/generate-nano-art.sh does not exist in the bundle (no scripts/ directory), and neither the script's output nor how to use the generated image is described. Concrete guidance exists but key details are missing, matching anchor 3 rather than 4's 'minor gaps'.

3 / 5

Workflow Clarity

A sequence is present (rewrite the prompt into a reasoning brief, then invoke the script), but there are no validation checkpoints and no post-invocation steps (where the image lands, how to report it). This matches 'sequence present but checkpoints missing or implicit'. The destructive/batch cap does not apply since image generation is not destructive, but the workflow still stops at invocation.

3 / 5

Progressive Disclosure

Sections are clearly headed and the content is compact, but the body references scripts/generate-nano-art.sh and core/media/generate-image.sh, neither of which exists in the bundle (no references/, scripts/, or assets/ directories). The body is also ~74 lines, above the under-50-line simple-skill exception. Some structure, but navigation points to files that are absent — anchor 3.

3 / 5

Total

12

/

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 communicates a concrete capability (image generation via muapi.ai with structured prompts) but reads partly as branding, omits natural trigger synonyms, and — most importantly — lacks any 'Use when...' guidance, capping completeness. Adding explicit trigger conditions would substantially improve routing quality.

Suggestions

Add an explicit 'Use when...' clause, e.g. 'Use when the user asks to generate, create, or edit an image, produce AI art, or wants text rendered legibly in an image.'

Include natural trigger synonyms users actually say — 'create an image', 'AI art', 'picture', 'photo', 'illustration' — rather than only 'image generation'.

Trim method-branding phrases like '(Gemini 3 style)' and 'logic-based prompting' in favor of one more concrete capability, e.g. 'renders legible text inside images'.

DimensionReasoningScore

Specificity

The description names the domain and one concrete action ("generates high-fidelity images via muapi.ai"), but the surrounding terms ("Reasoning-Driven", "structured creative briefs", "logic-based prompting") describe a method/branding rather than additional concrete capabilities. This matches the anchor 'Names domain and 1-2 concrete actions, but not comprehensive' rather than level 4, which requires several specific actions.

3 / 5

Completeness

The 'what' is clear (generate images via muapi.ai using structured briefs), but there is no 'Use when...' clause or any equivalent explicit trigger guidance, which per the judging guidelines caps completeness at 3. It does not fall to 2 because the 'what' is concrete, not vague.

3 / 5

Trigger Term Quality

"image generation" and "images" are natural trigger terms, but common user variations such as "create an image", "AI art", "picture", "photo", or "illustration" are absent. Some relevant keywords exist while common synonyms are missing, matching anchor 3 rather than 4's 'good keyword coverage'.

3 / 5

Distinctiveness Conflict Risk

The muapi.ai provider and the structured-brief niche give it a fairly distinct trigger surface with minimal conflict risk, matching 'mostly distinct; minor overlap risk'. It is not a 5 because the generic phrase "image generation" would also match other image-creation skills.

4 / 5

Total

13

/

20

Passed

Validation

87%

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

Validation — 14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

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

Warning

referenced_paths_exist

Referenced path issues: 1 missing

Warning

Total

14

/

16

Passed

Repository

SamurAIGPT/Generative-Media-Skills

Path

.opencode/skills/muapi-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.