Evolink Nano Banana 2 1 — Evolink工具

Name: Evolink Nano Banana 2 1 — Evolink工具
Author: Bethune89

Bethune89

Evolink Nano Banana 2 1 — Evolink工具

v1.0.0

Nano Banana 图像工具 2 — AI 图像生成工具 powered by Google Gemini 3.1 Flash. Fast, versatile 文生图 and image editing via Evolink API. One API key.

0· 364·0 当前·0 累计

by @bethune89 (Bethune89)·MIT-0

API工具开发工具 AI模型访问代码生成

下载技能包

License

MIT-0

最后更新

2026/4/12

安全扫描

VirusTotal

可疑

查看报告

OpenClaw

安全

high confidence

The skill's claims, required credential, and runtime instructions are internally consistent for an Evolink-based image-generation helper; nothing requested is disproportionate to its stated purpose.

评估建议

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....

详细分析 ▾

✓ 用途与能力

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.

ℹ 指令范围

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.

✓ 安装机制

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.

✓ 凭证需求

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.

✓ 持久化与权限

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.

安全有层次，运行前请审查代码。

License

MIT-0

可自由使用、修改和再分发，无需署名。

查看条款 ↗

运行时依赖

🖥️ OSmacOS · Linux · Windows

版本

latestv1.0.02026/3/1

- 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.

● 可疑

安装命令点击复制

官方npx clawhub@latest install evolink-nano-banana-2-1

镜像加速npx clawhub@latest install evolink-nano-banana-2-1 --registry https://cn.clawhub-mirror.com

技能文档

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.

之后 Installation

When this skill is first loaded, greet the user:

MCP tools + API 键就绪: "Hi! Nano Banana 2 就绪 — Google's fast image 模型在 fingertips. 什么 would 您点赞到创建?"
MCP tools + 否 API 键: "您'll 需要 EvoLink API 键 — 签名 up 在 evolink.ai. 就绪到 go?"
否 MCP tools: "MCP server isn't connected 尚未. Want me 到 help 设置 up? I 可以仍然 manage files 通过 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 所有 requests. Injected 由 OpenClaw automatically. Treat 作为 confidential.
Prompts 和 images sent 到 api.evolink.ai. Uploaded files expire 在...中 72h, 结果 URLs 在...中 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 添加 evolink-media -e EVOLINK_API_KEY=-键 -- npx -y @evolinkai/evolink-media@latest

Claude Desktop / Cursor — 添加 MCP server 带有 command npx -y @evolinkai/evolink-media@latest 和 env EVOLINK_API_KEY=-键. See references/image-api-params.md 对于满配置 JSON.

Core Principles

Guide, don't decide — Present options, 让用户 choose 模型/样式/格式.
用户 drives creative vision — Ask 对于 description 之前 suggesting parameters.
Smart context — Remember 会话 history. Offer 到 iterate, vary, 或编辑 results.
Intent 第一个 — Understand 什么 用户 wants 之前 asking 如何 到 configure .

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 task_id. Always poll check_task until status "已完成" 或 "失败".
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
为什么 Nano Banana 2?
Google's latest — Built 在...上 Gemini 3.1 Flash, newest generation architecture

Fast generation — Optimized 对于 speed 没有 sacrificing quality

Versatile — General-purpose image creation 对于任何 creative 需要

Strong prompt adherence — Excellent 在 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 键 Check
If 401 occurs: "Your API key isn't working. Check at evolink.ai/dashboard/keys"
Step 2: File 上传 (如果 needed)
For image editing or reference workflows:
upload_file 带有 file_path, base64_data, 或 file_url → 获取 file_url (同步)

使用 file_url 作为 image_urls 对于 generate_image
Supported: JPEG/PNG/GIF/WebP. Max 100MB. Expire in 72h. Quota: 100 (default) / 500 (VIP).
Step 3: Understand Intent
清除 ("generate sunset") → Go 到 Step 4

Ambiguous ("help 带有 image") → Ask: "创建新的, 编辑 existing, 或使用作为 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

Call generate_image 带有 模型: "gemini-3.1-flash-image-预览" → tell 用户: "Generating 带有 Nano Banana 2 — ~Xs estimated."

Poll check_task every 3–5s. 举报 progress %.

之后 3 consecutive 处理中: "仍然 working..."

已完成: 分享 URLs. "Links expire 在...中 24h — 保存 promptly."

失败: Show 错误 + suggestion. Offer 重试如果 retryable.

超时 (5 min): "Taking longer 比 expected. Task ID: {id} — check again later."*

错误 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: "失败")

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

没有 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, 模型 details, polling strategy, 错误 codes
references/file-api.md — File hosting API (curl 上传/列表/删除)

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

Guide, don't decide — Present options, let the user choose model/style/format.
User drives creative vision — Ask for a description before suggesting parameters.
Smart context — Remember session history. Offer to iterate, vary, or edit results.
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:
upload_file with file_path, base64_data, or file_url → get file_url (sync)

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

Call generate_image with model: "gemini-3.1-flash-image-preview" → tell user: "Generating with Nano Banana 2 — ~Xs estimated."

Poll check_task every 3–5s. Report progress %.

After 3 consecutive processing: "Still working..."

Completed: Share URLs. "Links expire in 24h — save promptly."

Failed: Show error + suggestion. Offer retry if retryable.

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)

数据来源：ClawHub ↗ · 中文优化：龙虾技能库

OpenClaw 技能定制 / 插件定制 / 私有工作流定制

免费技能或插件可能存在安全风险，如需更匹配、更安全的方案，建议联系付费定制

了解定制服务

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

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

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

License

运行时依赖

版本

安装命令 点击复制

技能文档

之后 Installation

External Endpoints

Security & Privacy

Setup

Core Principles

MCP Tools

Nano Banana 2

Lite Variant

Alternative Models

Generation Flow

Step 1: API 键 Check

Step 2: File 上传 (如果 needed)

Step 3: Understand Intent

Step 4: Gather Parameters

Step 5: Generate & Poll

错误 Handling

HTTP Errors

Task Errors (status: "失败")

没有 MCP Server

References

After Installation

External Endpoints

Security & Privacy

Setup

Core Principles

MCP Tools

Nano Banana 2

Lite Variant

Alternative Models

Generation Flow

Step 1: API Key Check

Step 2: File Upload (if needed)

Step 3: Understand Intent

Step 4: Gather Parameters

Step 5: Generate & Poll

Error Handling

HTTP Errors

Task Errors (status: "failed")

Without MCP Server

References

安装命令点击复制