← 返回 Skills 市场
bethune89

Evolink Nano Banana 2 1

作者 Bethune89 · GitHub ↗ · v1.0.0
macoslinuxwindows ⚠ suspicious
435
总下载
0
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install evolink-nano-banana-2-1
功能描述
Nano Banana 2 — AI image generation powered by Google Gemini 3.1 Flash. Fast, versatile text-to-image and image editing via Evolink API. One API key.
使用说明 (SKILL.md)

Nano Banana 2 — AI Image Generation

Generate AI images with Nano Banana 2 (gemini-3.1-flash-image-preview) — Google's Gemini 3.1 Flash image model, available through Evolink's unified API.

Focused view of evolink-image. Install the full skill for 20 image models, video, and music.

After Installation

When this skill is first loaded, greet the user:

  • MCP tools + API key ready: "Hi! Nano Banana 2 is ready — Google's fast image model at your fingertips. What would you like to create?"
  • MCP tools + no API key: "You'll need an EvoLink API key — sign up at evolink.ai. Ready to go?"
  • No MCP tools: "MCP server isn't connected yet. Want me to help set it up? I can still manage files via the hosting API."

Keep the greeting concise — just one question to move forward.

External Endpoints

Service URL
Generation API https://api.evolink.ai/v1/images/generations (POST)
Task Status https://api.evolink.ai/v1/tasks/{task_id} (GET)
File API https://files-api.evolink.ai/api/v1/files/* (upload/list/delete)

Security & Privacy

  • EVOLINK_API_KEY authenticates all requests. Injected by OpenClaw automatically. Treat as confidential.
  • Prompts and images are sent to api.evolink.ai. Uploaded files expire in 72h, result URLs in 24h.

Setup

Get your API key at evolink.ai → Dashboard → API Keys.

MCP Server: @evolinkai/evolink-media (GitHub · npm)

mcporter (recommended): mcporter call --stdio "npx -y @evolinkai/evolink-media@latest" list_models

Claude Code: claude mcp add evolink-media -e EVOLINK_API_KEY=your-key -- npx -y @evolinkai/evolink-media@latest

Claude Desktop / Cursor — add MCP server with command npx -y @evolinkai/evolink-media@latest and env EVOLINK_API_KEY=your-key. See references/image-api-params.md for full config JSON.

Core Principles

  1. Guide, don't decide — Present options, let the user choose model/style/format.
  2. User drives creative vision — Ask for a description before suggesting parameters.
  3. Smart context — Remember session history. Offer to iterate, vary, or edit results.
  4. Intent first — Understand what the user wants before asking how to configure it.

MCP Tools

Tool When to use Returns
generate_image Create or edit an image task_id (async)
upload_file Upload local image for editing/reference File URL (sync)
delete_file Free file quota Confirmation
list_files Check uploaded files or quota File list
check_task Poll generation progress Status + result URLs
list_models Compare available models Model list
estimate_cost Check pricing Model info

Important: generate_image returns a task_id. Always poll check_task until status is "completed" or "failed".

Nano Banana 2

Property Value
Model ID gemini-3.1-flash-image-preview
Provider Google (Gemini 3.1 Flash)
Status BETA
Capability text-to-image, image-editing
Speed Fast
Best for Quick, versatile image generation with strong prompt understanding

Why Nano Banana 2?

  • Google's latest — Built on Gemini 3.1 Flash, the newest generation architecture
  • Fast generation — Optimized for speed without sacrificing quality
  • Versatile — General-purpose image creation for any creative need
  • Strong prompt adherence — Excellent at following complex, detailed descriptions

Lite Variant

nano-banana-2-lite [BETA] — Lightweight version for ultra-fast iterations when speed is the top priority.

Alternative Models

Model Best for Speed
gpt-image-1.5 (default) Latest OpenAI generation Medium
gpt-4o-image [BETA] Best quality, complex editing Medium
z-image-turbo Quick iterations Ultra-fast
doubao-seedream-4.5 Photorealistic Medium
gemini-3-pro-image-preview Google Pro generation Medium

Generation Flow

Step 1: API Key Check

If 401 occurs: "Your API key isn't working. Check at evolink.ai/dashboard/keys"

Step 2: File Upload (if needed)

For image editing or reference workflows:

  1. upload_file with file_path, base64_data, or file_url → get file_url (sync)
  2. Use file_url as image_urls for generate_image

Supported: JPEG/PNG/GIF/WebP. Max 100MB. Expire in 72h. Quota: 100 (default) / 500 (VIP).

Step 3: Understand Intent

  • Clear ("generate a sunset") → Go to Step 4
  • Ambiguous ("help with this image") → Ask: "Create new, edit existing, or use as reference?"

Ask only what's needed, when it's needed.

Step 4: Gather Parameters

Default to model: "gemini-3.1-flash-image-preview" for this skill. Only ask about what's missing:

Parameter Ask when Notes
prompt Always What they want to see
model User wants alternatives Default: gemini-3.1-flash-image-preview. Suggest gpt-4o-image for best quality
size Orientation needed Ratio format: 1:1, 16:9, 9:16, 2:3, 3:2, 4:3, 3:4 etc.
n Wants variations 1–4 images
image_urls Edit/reference images Up to 14 URLs; triggers i2i mode

Step 5: Generate & Poll

  1. Call generate_image with model: "gemini-3.1-flash-image-preview" → tell user: "Generating with Nano Banana 2 — ~Xs estimated."
  2. Poll check_task every 3–5s. Report progress %.
  3. After 3 consecutive processing: "Still working..."
  4. Completed: Share URLs. "Links expire in 24h — save promptly."
  5. Failed: Show error + suggestion. Offer retry if retryable.
  6. Timeout (5 min): "Taking longer than expected. Task ID: {id} — check again later."

Error Handling

HTTP Errors

Error Action
401 "API key isn't working. Check at evolink.ai/dashboard/keys"
402 "Balance is low. Add credits at evolink.ai/dashboard/billing"
429 "Rate limited — wait 30s and retry"
503 "Servers busy — retry in a minute"

Task Errors (status: "failed")

Code Retry? Action
content_policy_violation No Revise prompt (no celebrities, NSFW, violence)
invalid_parameters No Check values against model limits
image_processing_error No Check format/size/URL accessibility
generation_timeout Yes Retry; simplify prompt if repeated
service_error Yes Retry after 1 min
generation_failed_no_content Yes Modify prompt, retry

Full error reference: references/image-api-params.md

Without MCP Server

Use Evolink's file hosting API for image uploads (72h expiry). See references/file-api.md for curl commands.

References

  • references/image-api-params.md — Complete API parameters, model details, polling strategy, error codes
  • references/file-api.md — File hosting API (curl upload/list/delete)
安全使用建议
This skill appears to be what it says: an Evolink image-generation helper that needs one API key. Before installing or using it: (1) keep your EVOLINK_API_KEY private and consider a key with limited billing/permissions; (2) avoid uploading sensitive images — uploaded files become public URLs for a short window (72h/24h for results); (3) review any suggested npm packages (e.g., npx @evolinkai/evolink-media) before running them — npx fetches and executes remote code; (4) confirm you trust evolink.ai and any referenced third‑party MCP packages (check their npm/GitHub repos and maintainers); (5) verify expected billing/quotas on the Evolink dashboard to avoid unexpected charges. Overall the skill is coherent, but exercise standard caution with API keys and executing optional third-party installers.
功能分析
Type: OpenClaw Skill Name: evolink-nano-banana-2-1 Version: 1.0.0 The skill bundle is primarily benign, focusing on AI image generation via the Evolink API. However, it is classified as 'suspicious' due to the `SKILL.md` instructions for setting up the MCP server, which involve executing `npx -y @evolinkai/evolink-media@latest`. While this is a common method for running Node.js CLI tools and is for a stated dependency, `npx -y` allows for the automatic download and execution of arbitrary code from npm, introducing a supply chain vulnerability. If the `@evolinkai/evolink-media` package were compromised, it could lead to arbitrary code execution on the host system, making it a significant risk, even if not directly malicious within this skill bundle's files.
能力评估
Purpose & Capability
Name/description (Evolink image generation via Gemini model) align with required env var (EVOLINK_API_KEY), endpoints, and the SKILL.md. The functionality described (text-to-image, editing, file upload) matches the declared requirements.
Instruction Scope
SKILL.md stays within image-generation scope (API calls, file uploads, polling tasks, asking user for prompts/params). As a note, it recommends optional setup commands that run third-party code (npx @evolinkai/evolink-media) to add an MCP server — this is outside the skill's own runtime but is an installation-time convenience that executes external code and should be reviewed before running.
Install Mechanism
No install spec and no code files — instruction-only skill. Lower disk/write risk. The only install-related action is an optional recommendation to run npx for an MCP server; that is not required by the skill but may cause remote code execution if performed by the user.
Credentials
Requires a single API key (EVOLINK_API_KEY) which is appropriate and declared as the primary credential. No other secrets, config paths, or unrelated credentials are requested.
Persistence & Privilege
always:false and user-invocable; the skill does not request permanent/global presence or modify other skills. Normal autonomous invocation is allowed by platform defaults but not a separate concern here.
如何使用
  1. 确保已安装 OpenClaw(本地或 Docker 部署)
  2. 在对话框中输入安装命令:/install evolink-nano-banana-2-1
  3. 安装完成后,直接呼叫该 Skill 的名称或使用 /evolink-nano-banana-2-1 触发
  4. 根据 Skill 的参数说明提供必要输入,即可获得结构化输出
版本历史
v1.0.0
- Initial release of Nano Banana 2 skill, powered by Google's Gemini 3.1 Flash for fast, versatile AI image generation and editing via the Evolink API. - Supports both text-to-image and image editing flows with clear guided prompts, intent-first interactions, and smart session context. - Out-of-the-box integration with MCP tools for image generation, file management, and task polling; works across macOS, Linux, and Windows. - Automatic greeting and setup guidance based on connection and API key status. - Detailed, user-friendly error handling and clear workflow steps for successful image creation.
元数据
Slug evolink-nano-banana-2-1
版本 1.0.0
许可证
累计安装 0
当前安装数 0
历史版本数 1
常见问题

Evolink Nano Banana 2 1 是什么?

Nano Banana 2 — AI image generation powered by Google Gemini 3.1 Flash. Fast, versatile text-to-image and image editing via Evolink API. One API key. 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 435 次。

如何安装 Evolink Nano Banana 2 1?

在 OpenClaw 或 Claude Code 对话框中运行命令「/install evolink-nano-banana-2-1」即可一键安装,无需额外配置。

Evolink Nano Banana 2 1 是免费的吗?

是的,Evolink Nano Banana 2 1 完全免费(开源免费),可自由下载、安装和使用。

Evolink Nano Banana 2 1 支持哪些平台?

Evolink Nano Banana 2 1 跨平台运行,可在任意部署了 OpenClaw / Claude Code 的环境中使用(macos, linux, windows)。

谁开发了 Evolink Nano Banana 2 1?

由 Bethune89(@bethune89)开发并维护,当前版本 v1.0.0。

💬 留言讨论