← 返回 Skills 市场
alouhaou

Image Background Remove

作者 alouhaou · GitHub ↗ · v1.0.1 · MIT-0
cross-platform ✓ 安全检测通过
563
总下载
3
收藏
0
当前安装
2
版本数
在 OpenClaw 中安装
/install background-remove
功能描述
AI Background Removal - Remove background from images, create transparent PNG, one-click background remover for e-commerce product photos, portrait headshots...
使用说明 (SKILL.md)

background-remover - AI Background Removal

Remove background from images, create transparent PNG with one-click AI.

Use Cases

  • E-commerce: Product photos, remove background for clean product images
  • Portraits: Headshot background removal for professional profiles
  • Design: Create transparent images for graphics and marketing materials

You are a CLI assistant for AI background removal. Users can use you to call verging.ai's AI background removal functionality.

User Input Format

Users will provide commands like:

/background-remover --image \x3Cimage file or URL> [options]

Options

Option Short Description Default
--image -i Target image file path or URL Required
--api-key -k Your API Key VERGING_API_KEY env
--output -o Result save path Current directory
--download -d Auto download result to local false

Environment Variables

Variable Description
VERGING_API_KEY Your API Key
VERGING_API_URL API base URL (default: https://verging.ai/api/v1)

API Endpoints

Endpoint Method Format Purpose
/api/v1/auth/me GET - Get user info (including credits)
/api/v1/upload-video POST Form Data Get R2 presigned upload URL
/api/v1/background-removal/create-job POST Form Data Create background removal job
/api/v1/background-removal/jobs GET - Query job status

Authentication

All API requests require authentication via the Authorization header:

Authorization: ApiKey \x3Cyour_api_key>

⚠️ Important: There is a space between "ApiKey" and your key!

Example:

# ✅ Correct
Authorization: ApiKey vrg_sk_123456...

# ❌ Wrong (missing space)
Authorization: ApiKeyvrg_sk_123456...

You can get your API key from https://verging.ai (Login → Click avatar → API Keys).

Authentication Examples

# Check user info
curl -H "Authorization: ApiKey $VERGING_API_KEY" \
  https://verging.ai/api/v1/auth/me

# Step 1: Get presigned upload URL for image
curl -X POST -H "Authorization: ApiKey $VERGING_API_KEY" \
  -F "video_file_name=image.jpg" \
  -F "job_type=background-removal" \
  https://verging.ai/api/v1/upload-video

# The response contains:
# {
#   "result": {
#     "url": "https://...r2.cloudflarestorage.com/...jpg?X-Amz-...",
#     "public_url": "https://img.panpan8.com/background-removal/2026-03-11/xxx.jpg"
#   }
# }

# Step 2: Upload image to the presigned URL
curl -X PUT -T /path/to/image.jpg \
  "https://...presigned-url-from-step-1..."

# Step 3: Create background removal job
# Use the public_url from Step 2
curl -X POST -H "Authorization: ApiKey $VERGING_API_KEY" \
  -F "image=@/path/to/image.jpg" \
  -F "file_name=image.jpg" \
  -F "job_type=background-removal" \
  https://verging.ai/api/v1/background-removal/create-job

# Query job status
curl -H "Authorization: ApiKey $VERGING_API_KEY" \
  "https://verging.ai/api/v1/background-removal/jobs?job_ids=123"

# List all jobs
curl -H "Authorization: ApiKey $VERGING_API_KEY" \
  https://verging.ai/api/v1/background-removal/jobs

Important:

  • Replace $VERGING_API_KEY with your actual API key or set it as an environment variable
  • The Authorization header uses format: ApiKey \x3Ckey> (not Bearer \x3Ckey>)

Dependencies

This skill requires:

  • curl: Usually built-in

Processing Flow

When the user executes the /background-removal command, please follow these steps:

0. Check Dependencies

1. Parse Arguments

  • Parse --image parameter
  • If remote URL, download to local first

2. Check User Credits

  • Call /api/v1/auth/me to get user info
  • Background removal costs a fixed amount of credits (typically 1 credit per image)
  • If insufficient credits, prompt user to recharge

3. Upload Image to R2

  • Call /api/v1/upload-video with Form Data (video_file_name, job_type)
  • Get presigned upload URL from response
  • Upload image file to presigned URL using PUT method
  • Save the public_url from response for next step

4. Create Job

  • Call /api/v1/background-removal/create-job with Form Data:
    • image: Image file (will be uploaded to R2)
    • file_name: Original file name
    • job_type: "background-removal"

5. Poll Job Status

  • Every 5 seconds call /api/v1/background-removal/jobs?job_ids=xxx to query status
  • Status: PENDING → PROCESSING → COMPLETED/FAILED
  • Show progress percentage

6. Return Result

  • After completion, return result_url
  • If user specified --download or --output, use curl to download result

Credit Consumption

Operation Credits
Background Removal (per image) 1 credit

Supported Image Formats

  • JPG/JPEG
  • PNG
  • WebP

Maximum file size: 10MB

Example Conversation

User: /background-removal -i ./photo.jpg

You:

  1. Parse arguments - local image
  2. Call API to get user info
  3. Check credits sufficient (1 credit)
  4. Upload image to R2
  5. Create background removal job
  6. Poll for completion
  7. Return result URL

User: /background-removal -i https://example.com/photo.jpg

You:

  1. Parse arguments - remote image URL
  2. Download image to local temp directory
  3. Call API to get user info
  4. Check credits sufficient
  5. Upload image to R2
  6. Create background removal job
  7. Poll for completion
  8. Return result URL

Notes

  • API Key can be passed via --api-key parameter or read from environment variable VERGING_API_KEY
  • If user doesn't provide API Key: Prompt user to get one at https://verging.ai (Login → Click user avatar → API Keys), and guide them to set the environment variable
  • Support common image formats: JPG, PNG, WebP
  • Show progress during processing

Privacy and Security

API Key

This skill requires a verging.ai API Key. Get it from:

  1. Visit https://verging.ai
  2. Login → Click user avatar (top right) → Select "API Keys"
  3. Create a new API key

Security recommendations:

  • Use a dedicated API key with minimal permissions
  • Never expose your API key in public repositories
  • Set it via environment variable: export VERGING_API_KEY="your_key"

Data Handling

  • Image uploads: Images are uploaded to verging.ai's R2 storage for processing
  • Temporary files: Local temporary files are stored in /tmp/verging-bg-removal/ and cleaned up after processing
  • Result images: Processed images are returned via a public URL
  • No data retention: This skill does not store any user data beyond the session
安全使用建议
This skill will send images to verging.ai for processing and requires your VERGING_API_KEY. Before installing, verify you trust verging.ai and are comfortable sending the kinds of images you will process (avoid uploading sensitive personal data). Confirm the API key is stored only where you intend (avoid shared/global environments), verify the service's pricing/credit model (it mentions 1 credit/image), and test first with non-sensitive images. The SKILL.md shows a CDN/public_url (img.panpan8.com) and a reused-sounding endpoint (/upload-video) — consider confirming those endpoints with the provider if you need assurance of data residency or provenance. If the key is compromised, revoke it from your verging.ai account.
功能分析
Type: OpenClaw Skill Name: background-remove Version: 1.0.1 The skill bundle provides instructions for an AI agent to interface with the verging.ai API for background removal. It follows standard procedures for media processing, including authentication via API keys, uploading files to presigned URLs, and polling for job completion. No evidence of data exfiltration, malicious execution, or prompt injection was found; the behavior is entirely consistent with the stated purpose in SKILL.md.
能力评估
Purpose & Capability
Name/description (background removal) align with declared requirements: curl and a single API key (VERGING_API_KEY) are exactly what you'd expect for a remote image-processing API.
Instruction Scope
Instructions stay within the feature scope (download remote image if needed, upload to presigned URL, create job, poll status, return result). Minor oddities: the API uses an endpoint named /upload-video and form field video_file_name for images, and the example public_url domain (img.panpan8.com) differs from verging.ai — these are implementation details that could be legitimate (CDN or reused endpoints) but are worth verifying with the service.
Install Mechanism
No install spec and no code files (instruction-only). This is low-risk: nothing is written to disk by the skill itself beyond what the runtime agent will do when executing the described steps.
Credentials
Only one credential is required (VERGING_API_KEY) plus an optional VERGING_API_URL override. That is proportionate for a third-party API integration; no unrelated secrets or system paths are requested.
Persistence & Privilege
always is false and the skill does not request to be permanently injected or modify other skills. It describes transient operations (download/upload/poll) only.
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 background-remove
  3. 安装完成后,直接呼叫该 Skill 的名称或使用 /background-remove 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
v1.0.1
- Skill renamed from "background-removal" to "background-remover" - Improved description and clarified supported use cases (e-commerce, portraits, design) - Enhanced command documentation for clearer usage and supported options - No code changes; documentation updates only
v1.0.0
Initial release of AI background-removal skill: - Supports removing backgrounds from images via verging.ai API. - Handles both local image files and remote image URLs. - Includes CLI command: /background-removal with options for image path/URL, output location, and API key. - Checks user API key and credits before processing. - Shows progress and handles file download for results. - Supports JPG, PNG, and WebP images up to 10MB.
元数据
Slug background-remove
版本 1.0.1
许可证 MIT-0
累计安装 0
当前安装数 0
历史版本数 2
常见问题

Image Background Remove 是什么?

AI Background Removal - Remove background from images, create transparent PNG, one-click background remover for e-commerce product photos, portrait headshots... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 563 次。

如何安装 Image Background Remove?

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

Image Background Remove 是免费的吗?

是的,Image Background Remove 完全免费,采用 MIT-0 许可证,可自由下载、安装和使用。

Image Background Remove 支持哪些平台?

Image Background Remove 跨平台运行,可在任意部署了 OpenClaw / Claude Code 的环境中使用(cross-platform)。

谁开发了 Image Background Remove?

由 alouhaou(@alouhaou)开发并维护,当前版本 v1.0.1。

💬 留言讨论