CtrlK
BlogDocsLog inGet started
Tessl Logo

nano-banana-image-ad

Generate one or more standalone Meta image-ad creatives via Nano Banana 2 / Nano Banana Pro (Gemini Flash Image family) through the Arcads external API. Locks the model family, auto-strips platform chrome, enforces edge-safe layouts. Use when the user asks for a "Nano Banana ad", "Gemini image ad", "nano-banana-2 ad creative", "make a static image ad with Gemini", or anchors on a need for photoreal / lifestyle / multi-reference / handheld-object / clay-texture ad creatives (sticky-note flatlays, held-whiteboard signs, lifestyle portraits, ingredient collages, OOH photography). Does NOT trigger on ChatGPT Image cues — use chatgpt-image-ad for those.

76

Quality

96%

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

SKILL.md
Quality
Evals
Security

Quality

Content

92%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.

A well-structured, highly actionable skill body with a clear phased workflow, mandatory validation checkpoints, and clean one-level-deep references. Only minor conciseness trimming is warranted.

Suggestions

Trim the KIE sibling digression in the 'Supported aspect ratios' section to a single clause or move it under 'See also' to reduce token cost.

The model-variant rationales repeat information already conveyed by the hard rules and the Generation modes table; consider collapsing to a compact table.

DimensionReasoningScore

Conciseness

Mostly lean and operational with tables, hard rules, and concrete command blocks, but a few asides (e.g., the KIE sibling tangent in the aspect-ratio section) could be trimmed.

4 / 5

Actionability

Fully executable, copy-paste-ready script invocations for image / pro / edit modes with concrete flags that match the verified generate_image.py script, plus mode and error tables.

5 / 5

Workflow Clarity

Seven numbered phases with explicit validation checkpoints (Phase 1 health-check, Phase 4 MANDATORY cost confirmation, Phase 6 MANDATORY Visual QA) and a capped retry feedback loop for the batch operation.

5 / 5

Progressive Disclosure

Clear overview with a 'Read order' list pointing one level deep to shared prompting files; bulk detail is offloaded to referenced files, and the bundled script matches the documented flags.

5 / 5

Total

19

/

20

Passed

Description

100%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 highly specific, third-person description that cleanly states concrete capabilities, provides extensive natural trigger phrases, and explicitly disambiguates from a sibling skill. Both the 'what' and 'when' are answered with no vague fluff.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — 'Generate one or more standalone Meta image-ad creatives', 'Locks the model family', 'auto-strips platform chrome', 'enforces edge-safe layouts' — with comprehensive coverage and no gaps.

5 / 5

Completeness

Explicitly answers both what (generates Meta image-ad creatives via Arcads with locked model, chrome-stripping, edge-safe layouts) and when (concrete 'Use when...' trigger phrases), and adds an explicit negative boundary.

5 / 5

Trigger Term Quality

Includes comprehensive natural trigger phrases users would actually say ('Nano Banana ad', 'Gemini image ad', 'make a static image ad with Gemini') plus synonym-style creative-type cues, covering the full surface.

5 / 5

Distinctiveness Conflict Risk

Clear niche (Nano Banana / Gemini image ads via Arcads) with explicit disambiguation against the sibling chatgpt-image-ad, minimizing conflict risk.

5 / 5

Total

20

/

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.

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

relative_links

Relative link issues: 11 suspicious

Warning

Total

15

/

16

Passed

Repository
krusemediallc/arcads-claude-code
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.