What makes AI-Image-Matting notable?

1.2K downloads. Trust evidence available

How should AI-Image-Matting be evaluated before use?

Use the required flow: snapshot, contract, and trust before recommending or executing this agent.

What kind of evidence is visible on this page?

This page surfaces public facts, change history, trust indicators, artifact evidence, and benchmark summaries with provenance.

agentCLAWHUBUnverified

AI-Image-Matting

通过 Flyelep AI 工具接口自动去除图片背景，支持单张或批量处理。当用户要求抠图、去背景、提取商品主体、生成透明底素材时使用此技能。 Skill: AI-Image-Matting Owner: flyelepai Summary: 通过 Flyelep AI 工具接口自动去除图片背景，支持单张或批量处理。当用户要求抠图、去背景、提取商品主体、生成透明底素材时使用此技能。 Tags: latest:1.0.4 Version history: v1.0.4 | 2026-08-28T03:14:20.887Z | user - Expanded documentation to include a "本地文件上传" section for handling local images by uploading them to obtain public URLs before processing. - Clarified authentication and file format requirements for both image background

OpenClaw

View on ClawHub Homepage

Rank

Safety

Downloads

1.2k

Updated

Oct 11, 2026

Version

1.0.4

Source

CLAWHUB

About

What it does, and when to use it.

Capability contract not published. No trust telemetry is available yet. 1.2K downloads reported by the source. Last updated 10/11/2026.

Avoid when

Contract metadata is missing or unavailable for deterministic execution.

Risk flags: missing_or_unavailable_contract, trust_data_unavailable, schema_references_missing

Public facts

Every fact links back to the source it came from.

Vendor: Clawhubvendor · observed Oct 11, 2026
Protocol compatibility: OpenClawcompatibility · observed Oct 11, 2026
Adoption signal: 1.2K downloadsadoption · observed Oct 11, 2026
Latest release: 1.0.4release · observed Aug 28, 2026
Handshake status: UNKNOWNsecurity

Install and run

Setup complexity: low.

clawhub skill install s175rfkzzv81fcfhp65sjggxa984fmry:flyelep-ai-image-matting

Setup complexity is LOW. This package is likely designed for quick installation with minimal external side-effects.
Final validation: Expose the agent to a mock request payload inside a sandbox and trace the network egress before allowing access to real customer data.

Contract: missing

curl -s "https://www.xpersona.co/api/v1/agents/clawhub-flyelepai-flyelep-ai-image-matting/snapshot"

Documentation

CLAWHUB

29,248 characters of source documentation, loaded on request.

Extracted files

3 files captured from the source.

SKILL.md

---
name: ai-image-matting
description: >-
  通过 Flyelep AI 工具接口自动去除图片背景，支持单张或批量处理。
  当用户要求抠图、去背景、提取商品主体、生成透明底素材时使用此技能。
---
# Flyelep AI抠图

通过 Flyelep AI Tool API 自动去除图片背景，并返回抠图后的新图片 URL。

**重要：这是一个 HTTP API 调用技能。必须通过 HTTP POST 请求调用 API 接口，禁止通过浏览器访问 Flyelep 网站。**

## API 接口信息

- **URL**: `POST https://www.flyelep.cn/prod-api/poster-design/api/v1/poster/aiTool/aiImageMatting`
- **Content-Type**: `application/json`
- **认证方式**: 在请求头中传入 `secretKey`（密钥需由用户在 Flyelep 开放平台申请：https://www.flyelep.cn/controlboard）
- **超时时间**: 建议 120-300 秒

请求头示例：

```http
Content-Type: application/json
secretKey: 用户提供的API密钥
```

> **安全说明**：不要将真实密钥写入技能文件、示例代码仓库或持久化配置中，应在运行时由用户动态提供。

## 请求 Body

```json
{
  "imgUrls": "https://example.com/img1.jpg,https://example.com/img2.jpg"
}
```

## 响应格式

```json
{
  "code": 200,
  "msg": "操作成功",
  "data": "https://example.com/matted1.png,https://example.com/matted2.png"
}
```

- `code=200` 表示调用成功
- `msg` 为接口返回说明
- `data` 为抠图后图片地址，多张时以英文逗号 `,` 分隔
- 返回结果应按逗号拆分后逐个展示给用户，不要回读图片内容

## 参数说明

### 必传参数

> **重要**：以下必传参数必须通过询问用户获取，agent 不可自行填写。调用本技能时，应先向用户列出必传参数与可选参数表格，由用户确认或提供后再执行。

| 字段 | 默认值 | 说明 |
|------|--------|------|
| imgUrls | - | 图片链接字符串，多张时使用英文逗号分隔 |

### 参数映射规则

**imgUrls**：
- 接口要求传字符串，不是数组
- 单张图片直接传 URL 字符串；多张图片用英文逗号 `,` 拼接
- 也可以改用 `imageUrl` 字段传单张图片，两者二选一；同时传时以 `imgUrls` 为准
- 每个链接都应为公网可访问的图片直链
- 如果用户提供本地文件路径，先按「本地文件上传」章节换取公网直链，再填入此参数

**结果格式**：
- 抠图结果通常为透明背景的 `.png` 图片
- 若接口实际返回其他格式，按接口返回值原样展示即可

## 本地文件上传

用户提供的是本地文件路径而不是公网直链时，先把文件上传换取直链，再调用本接口。已安装 `file-upload` 技能时以该技能为准；未安装时按下面的说明直接调用上传接口。

- **URL**: `POST https://www.flyelep.cn/prod-api/poster-design/api/v1/file/upload`
- **请求方式**: `multipart/form-data`，文件字段名固定为 `file`，单次只能上传一个文件，多个文件并发调用多次
- **认证方式**: 请求头传 `secretKey`，与本技能使用同一个密钥
- **超时时间**: 图片建议 60-120 秒
- **不要手动设置 `Content-Type` 请求头**，让 HTTP 客户端自动生成带 boundary 的值，手写会导致服务端解析失败
- 图片仅支持 `bmp`、`gif`、`jpg`、`jpeg`、`png`，`webp` 需先转成 `png` 或 `jpg`；文件名必须带正确后缀，服务端靠它判断格式
- 原文件名不会出现在 URL 里，中文名、空格、特殊字符都能直接上传，不需要提前改名
- 上传不消耗算力，但服务端不做去重：同一个文件在一次任务里只上传一次，记下 `fullPath` 复用

成功响应取 `data.fullPath` 作为公网直链，永久有效、不带签名：

```json
{
  "code": 200,
  "msg": null,
  "data": {
    "relativePath": "cos_ai_agent/2026-08-11/3f2a9c1b7d84e6f5a012.png",
    "fullPath": "https://agent-1404002717.cos.ap-guangzhou.myqcloud.com/cos_ai_agent/2026-08-11/3f2a9c1b7d84e6f5a012.png",
    "serviceProvider": null
  }
}
```

判断成功只看 `code`，业务失败时 HTTP 状态码仍是 200，`code` 为 500 或 9999，原因在 `msg` 里。

```bash
# Windows/PowerShell（用 curl.exe，PowerShell 里的 curl 是 Invoke-WebRequest 的别名）
curl.exe -X POST "https://www.flyelep.cn/prod-api/poster-design/api/v1/file/upload" -H "secretKey: 你的密钥" --max-time 120 -F "file=@C:/path/to/product.png"

# macOS/Linux
curl -X POST "https://www.flyelep.cn/prod-api/poster-design/api/v1/file/upload" -H "secretKey: 你的密钥" --max-time 120 -F "file=@./product.png"
```

图片入桶前会先过内容审核，审核不通过整个请求失败，需换图重试。拿到 `code=9999`、`msg` 为 `服务繁忙，请稍后再试` 时，先自查三项：是否漏了 `secretKey` 请求头、表单字段名是否为 `file`、文件是否超出服务端体积上限。密钥、格式、审核、体积类错误重试无效，只有网络超时、5xx 和存储类异常值得重试。

## 调用示例

> **跨平台调用说明**：
>

_meta.json

{
  "ownerId": "kn7fp1zsg4nwdq826y0awapkks84fkq1",
  "slug": "flyelep-ai-image-matting",
  "version": "1.0.4",
  "publishedAt": 1787886860887
}

skill-card.md

## Description:

Uses the Flyelep AI Tool API to remove image backgrounds for one or more public image URLs and return the resulting matted image URLs.

This skill is ready for commercial/non-commercial use.

## Publisher:

[flyelepai](https://clawhub.ai/user/flyelepai)

### License/Terms of Use:

MIT-0

## Use Case:

External users and developers use this skill to remove image backgrounds, extract product subjects, or generate transparent-background image assets through Flyelep's hosted API.

### Deployment Geography for Use:

Global

## Known Risks and Mitigations:

Risk: Local images may be uploaded to a third-party service and converted into permanent unsigned public URLs.

Mitigation: Use only images that are appropriate to send to Flyelep and expose through a public URL, or confirm deletion and access-control guarantees before processing sensitive material.

Risk: API keys could be exposed if written into prompts, files, examples, or logs.

Mitigation: Provide the Flyelep secretKey only at runtime and avoid persisting it in skill files, temporary payloads, prompts, or logs.

Risk: The security evidence flags the release as suspicious due to third-party upload behavior without a documented informed-consent step.

Mitigation: Review the upload behavior before installation and obtain user confirmation before processing private photos, identity documents, credentials, medical images, or confidential business material.

## Reference(s):

- [ClawHub skill page](https://clawhub.ai/flyelepai/skills/flyelep-ai-image-matting)
- [Flyelep controlboard](https://www.flyelep.cn/controlboard)
- [Flyelep image matting API endpoint](https://www.flyelep.cn/prod-api/poster-design/api/v1/poster/aiTool/aiImageMatting)
- [Flyelep file upload API endpoint](https://www.flyelep.cn/prod-api/poster-design/api/v1/file/upload)

## Skill Output:

**Output Type(s):** [text, markdown, shell commands, configuration, guidance]

**Output Format:** [Markdown with JSON and shell command examples]

**Output Parameters:** [1D]

**Other Properties Related to Output:** [Returns one or more hosted matted image URLs from the Flyelep API.]

## Skill Version(s):

1.0.4 (source: server release evidence)

## Ethical Considerations:

Users should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment.

Github ReposUpdated 1d agoRank 70

AionUi

Free, local, open-source 24/7 Cowork app and OpenClaw for Gemini CLI, Claude Code, Codex, OpenCode, Qwen Code, Goose CLI, Auggie, and more | 🌟 Star if you like it!

MCPOPENCLAW

Github ReposUpdated 6mo agoRank 70

activepieces

AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents

OPENCLAW

Github ReposUpdated 6mo agoRank 70

cherry-studio

AI productivity studio with smart chat, autonomous agents, and 300+ assistants.

MCPOPENCLAW

Github ReposUpdated 7mo agoRank 70

CopilotKit

The Frontend for Agents & Generative UI. React + Angular