Skills nano-banana-2

📦

nano-banana-2

Name: nano-banana-2
Author: inferen-sh

Content revision r2 Safe ⚙️ External commands🌐 Network access

Generate and Edit Images with Nano Banana 2

Creating polished images often requires separate tools for generation, editing, and current information. This skill provides one inference.sh workflow for all three tasks.

Supports: Claude Codex Code(CC)

🥉 78 Bronze

Install with my Agent

Copy this request to your Agent. It includes the canonical Skill page and manifest.

Agent request

Review the Skillstore skill "nano-banana-2" from https://skillstore.io/skills/inferen-sh-nano-banana-2.md and its manifest at https://skillstore.io/api/skills/inferen-sh-nano-banana-2/manifest. Verify the artifact. You may proceed after verification, subject to the environment's own policy.

Your Agent should still show its plan and request any confirmation required by the security policy.

Agent-readable resources

Use these links when an AI agent, crawler, or script needs clean context instead of reading the full page.

Markdown detail GET /skills/inferen-sh-nano-banana-2.md Signed manifest GET /api/skills/inferen-sh-nano-banana-2/manifest Signed lockfile GET /api/skills/inferen-sh-nano-banana-2/lockfile

Test it

Using "nano-banana-2". Create four minimalist coffee shop logo concepts with a square format.

Expected outcome:

Four generated logo images with distinct minimalist compositions, plus output metadata for the request.

Using "nano-banana-2". Add a rainbow to the supplied landscape while preserving the terrain and natural lighting.

Expected outcome:

An edited landscape image with the requested rainbow and a short description of the result.

Using "nano-banana-2". Visualize the current weather in Tokyo as a wide artistic scene.

Expected outcome:

A grounded weather visualization in a wide format, based on current search information.

Security Audit

Safe

v5 • 8/6/2026 Open versioned report

All 38 static findings are false positives caused by Markdown formatting, fixed CLI examples, placeholder URLs, or documentation links. The skill intentionally uses the belt CLI for remote image inference, but no hidden execution, prompt injection, or credential collection was found.

Files scanned

170

Lines analyzed

Review items

False positives ignored

No confirmed security findings were detected by the latest completed static and semantic audit. This does not prove the skill has no side effects.

Audited by: codex View Audit History →

Share & cite this report

Share the versioned assessment report, neutral badge, embed card, and citations. Skillstore reports evidence without deciding whether this Skill is safe.

Open versioned report

Copy report link

https://skillstore.io/skills/inferen-sh-nano-banana-2/audits/5?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_report

Markdown badge

[![Skillstore security assessment](https://skillstore.io/badges/skills/inferen-sh-nano-banana-2/security.svg)](https://skillstore.io/skills/inferen-sh-nano-banana-2?utm_source=security_passport_badge)

HTML badge

<a href="https://skillstore.io/skills/inferen-sh-nano-banana-2?utm_source=security_passport_badge"><img src="https://skillstore.io/badges/skills/inferen-sh-nano-banana-2/security.svg" alt="Skillstore security assessment" loading="lazy"></a>

Embed card

<iframe src="https://skillstore.io/embed/skills/inferen-sh-nano-banana-2.html" title="Skillstore Security Assessment" sandbox="allow-popups allow-popups-to-escape-sandbox" loading="lazy" referrerpolicy="no-referrer" width="420" height="180"></iframe>

Academic citations (APA · BibTeX · CFF)

APA citation

inferen-sh. (2026). nano-banana-2 security audit report (audit version 5) [Author version unspecified]. Skillstore. https://skillstore.io/skills/inferen-sh-nano-banana-2/audits/5

BibTeX citation

@techreport{inferen-sh-inferen-sh-nano-banana-2-2026,
  author = {inferen-sh},
  title = {nano-banana-2 security audit report (audit version 5)},
  institution = {Skillstore},
  year = {2026},
  number = {5},
  url = {https://skillstore.io/skills/inferen-sh-nano-banana-2/audits/5},
  note = {Author version unspecified}
}

CITATION.cff

cff-version: 1.2.0
message: "If you use this Skill, cite its author and this versioned security audit report."
title: "nano-banana-2 security audit report (audit version 5)"
version: "unspecified"
type: report
authors:
  - name: "inferen-sh"
date-released: "2026-08-06"
url: "https://skillstore.io/skills/inferen-sh-nano-banana-2/audits/5"
identifiers:
  - type: other
    value: "skillstore:inferen-sh-nano-banana-2:audit:5"
    description: "Skillstore immutable audit report identifier"

Compare variants

8 installable variants

Each author remains a separate installable skill. The recommended variant is ranked by Skillstore evidence.

Why this variant is first

Highest Skillstore Score

Author / source Skillstore Score Evidence Confidence Skillstore usage Updated

inferen-sh Recommended Current

inferen-sh-nano-banana-2

Skillstore Score 78

Evidence Confidence High

Skillstore usage 12

Updated

2026-08-21

agentspace-so

agentspace-so-nano-banana-2

Skillstore Score 77

Evidence Confidence High

Skillstore usage 7

Updated

2026-08-21

toolshell

toolshell-nano-banana-2

Skillstore Score 70

Evidence Confidence High

Skillstore usage 21

Updated

2026-08-21

inference-shell

inference-shell-nano-banana-2

Skillstore Score 50

Evidence Confidence High

Skillstore usage 17

Updated

2026-08-21

tul-sh

tul-sh-nano-banana-2

Skillstore Score 50

Evidence Confidence High

Skillstore usage 11

Updated

2026-08-21

doany-ai

doany-ai-nano-banana-2

Skillstore Score 38

Evidence Confidence High

Skillstore usage 20

Updated

2026-08-21

inference-sh-9

inference-sh-9-nano-banana-2

Skillstore Score 38

Evidence Confidence Medium

Skillstore usage 10

Updated

2026-08-21

runcomfy-com

runcomfy-com-nano-banana-2

Skillstore Score 38

Evidence Confidence Medium

Skillstore usage 9

Updated

2026-08-21

Skillstore Score

Why this score Evidence Confidence: High

Architecture

Maintainability

Content

Community

Spec Compliance

What You Can Build

Create Campaign Visuals

Generate several branded concepts with controlled dimensions for social posts, advertisements, or presentations.

Revise Design References

Edit supplied images while preserving important subjects, composition, and visual details.

Prototype Image Workflows

Test image generation through the CLI or stream progress through the Python SDK.

Try These Prompts

Generate a Basic Image

Create an image of [subject] in [style], using [lighting] and a [composition] composition.

Create Multiple Concepts

Generate [number] distinct concepts for [project]. Use [aspect ratio], [resolution], and these visual requirements: [details].

Edit Reference Images

Using the supplied images, change [element] to [new state]. Preserve [features] and match the original lighting and perspective.

Ground a Current Visual

Create a factual visualization of [current topic] for [location or date]. Use Google Search grounding and clearly represent [required facts].

Best Practices

Describe the subject, composition, lighting, style, and required details in one focused prompt.
Use only necessary reference images and remove sensitive information before upload.
Generate lower-resolution concepts before requesting final 4K outputs.

Avoid

Do not use vague prompts when layout, colors, or subject details are important.
Do not upload confidential images or personal data to external processing services.
Do not enable Google Search grounding when the request does not require current information.

Frequently Asked Questions

What must I install before using this skill?

Install the inference.sh belt CLI or Python SDK, then authenticate with the service.

Can this skill edit existing images?

Yes. It accepts up to 14 JPEG, PNG, or WebP images as references.

Which output sizes are supported?

The documented resolution options are 1K, 2K, and 4K.

Can I generate more than one image?

Yes. Set the requested image count to produce multiple results.

When should I enable Google Search grounding?

Enable it when the image depends on current facts, weather, news, or other recent information.

Does the skill process files locally?

No. The belt CLI sends requests and supplied images to the inference.sh service for processing.

Developer Details

Author

inferen-sh

License

MIT

Skillstore revision

Version notice

The author did not declare a version.

Repository

https://github.com/inferen-sh/skills/tree/main/tools/image/nano-banana-2/

Ref

4121de961d1b6f2ffca856260e239505c302452c

Maintenance freshness

8/7/2026

Usage

10 downloads · 206 views

File structure

📄 SKILL.md

nano-banana-2

Install with my Agent

Agent-readable resources

Test it

Security Audit

Risk Factors

Copy report link

Markdown badge

HTML badge

Embed card

APA citation

BibTeX citation

CITATION.cff

Compare variants

Skillstore Score

What You Can Build

Create Campaign Visuals

Revise Design References

Prototype Image Workflows

Try These Prompts

Best Practices

Avoid

Frequently Asked Questions

Developer Details