Xpersona
1

1688-item-image-optimizer

CLAWHUB · Unverified

商品图片制作统一入口：主图优化、轮播图、详情图、背景替换、数字模特。 核心能力：verify_permission（高级版权限校验）、build_tool_url（构建工具页 URL）、configure（AK 配置）。 触发词：做一套图、做图、出图、优化主图、主图优化、轮播图、详情图、背景替换、数字模特、商品图片、改图、图片优化。 不应触发：新品发布/批量上架（走发品 skill）、品牌VI/海报/店铺装修、图片规范问答。 本 Skill 的图片制作流程已由 workflow 编排覆盖，命中触发词时直接执行 workflow。如果 workflow 无法完成任务（如纯能力问答、单命令调用、探索性使用），加载本 SKILL.md 进行推理。

62
Rank
84
Safety
965
Downloads

About

What it does, and when to use it.

Capability contract not published. No trust telemetry is available yet. 965 downloads reported by the source. Last updated 10/12/2026.

Avoid when

  • Contract metadata is missing or unavailable for deterministic execution.

Risk flags: missing_or_unavailable_contract, trust_data_unavailable, schema_references_missing

Install and run

Setup complexity: low.

clawhub skill install s177df9srv6z2y0gd1kw90rern83hzxb:1688-item-image-optimizer
  1. Install using `clawhub skill install s177df9srv6z2y0gd1kw90rern83hzxb:1688-item-image-optimizer` in an isolated environment before connecting it to live workloads.
  2. No published capability contract is available yet, so validate auth and request/response behavior manually.
  3. Review the upstream CLAWHUB listing at https://clawhub.ai/1688aiinfra/1688-item-image-optimizer before using production credentials.

Contract: missing

curl -s "https://www.xpersona.co/api/v1/agents/clawhub-1688aiinfra-1688-item-image-optimizer/snapshot"

Run-check

$0.02 USD

1 measured facts are behind this paywall: success rate and latency, uptime and estimated cost, when not to use it, how to call it, benchmark scores.

Agents pay $0.02 in USDC. A card payment is $0.50, the smallest a card allows.

Documentation

CLAWHUB

19,865 characters of source documentation, loaded on request.

Extracted files

4 files captured from the source.

SKILL.md

---
name: 1688-item-image-optimizer
version: 1.0.0
description: >-
  商品图片制作统一入口：主图优化、轮播图、详情图、背景替换、数字模特。
  核心能力：verify_permission（高级版权限校验）、build_tool_url（构建工具页 URL）、configure（AK 配置）。
  触发词：做一套图、做图、出图、优化主图、主图优化、轮播图、详情图、背景替换、数字模特、商品图片、改图、图片优化。
  不应触发：新品发布/批量上架（走发品 skill）、品牌VI/海报/店铺装修、图片规范问答。
  本 Skill 的图片制作流程已由 workflow 编排覆盖，命中触发词时直接执行 workflow。如果 workflow 无法完成任务（如纯能力问答、单命令调用、探索性使用），加载本 SKILL.md 进行推理。
metadata:
  engine: false
  openclaw:
    emoji: "🖼"
interactions:
  - name: open_tab_image_optimize
    type: open_tab
    selectionType: shop_backend
    description: "路由到商品图片工具页面（主图优化/轮播图/详情图/背景替换/数字模特），URL 由 build_tool_url capability 构建"
    required_data:
      url: "完整工具页面 URL（由 build_tool_url 返回的 data.open_tab.url）"
      title: "页面标题（主图优化/轮播图制作/详情图制作/背景替换/数字模特）"
  - name: select_image_type
    type: card
    selectionType: image_type
    description: "用户意图模糊时，引导选择要制作的图片类型"
    required_data:
      questions: "图片类型选项数组"
  - name: select_images
    type: card
    selectionType: image
    description: "上传图片超出工具限制时，引导用户选择要处理的图片子集"
    required_data:
      questions: "图片选项数组（多选）"
---

# 1688-item-image-optimizer — 商品图片制作统一入口

> 编排流程（意图识别 → 权限校验 → 构建入口 → open_tab）由 `workflow/1688-item-image-optimizer.js` 确定性执行。本文件只描述**能力**：有哪些 CLI 命令、各自怎么调、返回什么、业务约束是什么。供纯问答 / 单命令调用 / 引擎委托时参考。

统一入口：`python3 {baseDir}/cli.py <command> [options]`
所有命令输出 JSON：`{"success": bool, "markdown": str, "data": {...}}`

## 命令速查

| 命令 | 必填参数 | 说明 |
|------|---------|------|
| `verify_permission` | 无 | 校验数字模特权限（返回 isAi/digitalModel/faceFix） |
| `build_tool_url` | `--type` | 构建图片工具页面 URL，返回 open_tab 透传对象 |
| `configure` | （AK 位置参数，可选） | 配置/查看 AK；无参看状态 |

## 能力详述

### verify_permission

- **签名**：`cli.py verify_permission`（无参，商家身份由 AK 网关签名自动识别）
- **返回结构**：业务数据嵌套在 `data.data` 内 —— `{"success": true, "data": {"data": {"isAi": bool, "digitalModel": bool, "faceFix": bool}}}`
- **关键字段**：
  - `isAi`：是否高级版（保留字段，当前 skill 不做权限判断）
  - `digitalModel`：是否有数字模特权限（决定 digitalModel 能否使用）
  - `faceFix`：脸部修复权限（暂未使用）
- **业务含义**：仅数字模特（digitalModel）路由前必须校验；一次会话内结果可复用。

### build_tool_url

- **签名**：`cli.py build_tool_url --type <type> [--offer-id ID] [--img-url URL] [--img-url-list URL1,URL2]`
- **返回结构**：`{"success": bool, "markdown": str, "data": {"open_tab": {"type": "open_tab", "url": "...", "title": "..."}}}`
- **`--type` 取值**（CLI 支持 7 个；前 5 个为当前业务动线类型，后 2 个 CLI 支持但编排动线未独立暴露）：

  | type | 中文标题 | 图片参数 | 业务动线 |
  |------|---------|---------|---------|
  | `main` | 主图优化 | `--img-url`（单图） | ✅ |
  | `carousel` | 轮播图制作 | `--img-url-list`（多图） | ✅ |
  | `detail` | 详情图制作 | `--img-url-list`（多图） | ✅ |
  | `replaceSubject` | 背景替换 | `--img-url`（单图） | ✅ |
  | `digitalModel` | 数字模特 | `--img-url`（单图） | ✅ |
  | `matting` | 白底图 | `--img-url`（单图） | CLI 支持 |
  | `outpainting` | 一键扩图 | `--img-url`（单图） | CLI 支持 |

- **图片参数与工具类型必须匹配**：单图工具传 `--img-url`、多图工具传 `--img-url-list`，错配 CLI 直接报错（让上游自纠）。空字符串视为无效图片报错；不传则跳过（工具页自带上传入口）。
- **业务含义**：URL 由 CLI 构建（已 URL encode），**禁止 LLM 编造/拼接**。`success=false` 时禁止触发 open_tab。

### configure

_meta.json

{
  "ownerId": "kn76msg8cwkep3b08z7zffx9fx82p5wj",
  "slug": "1688-item-image-optimizer",
  "version": "0.51.0",
  "publishedAt": 1788490712302
}

references/interaction-specs.md

# 交互组件详细规范 — 1688-item-image-optimizer

本文档定义了本 Skill 中所有交互组件的具体数据结构与映射规则。大模型在调用 `show_interaction` 前需查阅本文档，确保数据结构正确。

---

## 1. open_tab_image_optimize（open_tab 组件）

### 组件类型
`type: open_tab`

### 数据槽位

| 字段 | 类型 | 必填 | 说明 |
|------|------|------|------|
| `type` | string | ✅ | 固定 `"open_tab"` |
| `selectionType` | string | ✅ | 固定 `"shop_backend"` |
| `url` | string | ✅ | 由 `build_tool_url` capability 返回的完整 URL（已经过 URL encode） |
| `title` | string | ✅ | 页面标题：`主图优化` / `轮播图制作` / `详情图制作` / `背景替换` / `数字模特` |

### 完整调用示例

**主图优化（main）：**
```json
{
  "type": "open_tab",
  "selectionType": "shop_backend",
  "url": "https://pre-air.1688.com/app/CSBC-modules/csbc-ai-component-loader/picture-optimize.html?__mtop_subdomain__=wapa&type=oneOptimization&imgUrl=%2FUsers%2Fseller%2FDesktop%2Fproduct.jpg",
  "title": "主图优化"
}
```

**轮播图（多图）：**
```json
{
  "type": "open_tab",
  "selectionType": "shop_backend",
  "url": "https://pre-air.1688.com/app/CSBC-modules/csbc-ai-component-loader/picture-optimize.html?__mtop_subdomain__=wapa&type=carouselImage&imgUrlList=%2Fpath%2F1.jpg%2C%2Fpath%2F2.jpg",
  "title": "轮播图制作"
}
```

**详情图（商品 ID）：**
```json
{
  "type": "open_tab",
  "selectionType": "shop_backend",
  "url": "https://pre-air.1688.com/app/CSBC-modules/csbc-ai-component-loader/picture-optimize.html?__mtop_subdomain__=wapa&type=detailImage&offerId=1016555587352",
  "title": "详情图制作"
}
```

**背景替换（replaceSubject，单图）：**
```json
{
  "type": "open_tab",
  "selectionType": "shop_backend",
  "url": "https://pre-air.1688.com/app/CSBC-modules/csbc-ai-component-loader/picture-optimize.html?__mtop_subdomain__=wapa&type=replaceSubject&imgUrl=%2Fpath%2Fproduct.jpg",
  "title": "背景替换"
}
```

> 其余单图工具——数字模特（`type=digitalModel` / 标题`数字模特`）——URL 结构同背景替换，仅 `type` 与 `title` 不同，均用 `imgUrl` 单图参数。

### 注意事项
- URL 必须来自 `build_tool_url` 返回，**禁止 LLM 编造/拼接**
- `build_tool_url` 返回 `success=false` 时禁止触发
- 触发即为 skill 终态，不追加文字引导

---

## 2. select_image_type（card 组件）

### 组件类型
`type: card`

### 触发时机
触发词命中但 LLM 无法确定具体图片类型时（如"帮我做一套图"）

### ⚠️ 有权限的所有 type 全部平铺 + 先校验权限

1. 弹出前**先执行** `python3 {baseDir}/cli.py verify_permission` 拿权限（`data.data.isAi` / `data.data.digitalModel`），`success=false` 时按铁律 6 fail-closed 拦截。
2. 按权限把**有权限的所有 type 全部平铺**进 `options`（不做收纳/Top3/「其他功能」）：

| 权限 | `options`（全平铺） | 项数 |
|------|--------------------|------|
| `isAi=false`（基础版） | 主图优化、背景替换 | **2** |
| `isAi=true, digitalModel=false`（高级版无数字模特） | ＋轮播图、详情图 | **4** |
| `isAi=true, digitalModel=true`（高级版全权限） | ＋数字模特 | **5** |

### 完整调用示例

**基础版（2 项全平铺）：**
```json
{
  "type": "card",
  "selectionType": "image_type",
  "questions": [
    { "question": "你想制作哪种商品图片？", "options": ["主图优化", "背景替换"], "allowMultiple": false, "required": true }
  ]
}
```

**高级版全权限（5 项全平铺）：**
```json
{
  "type": "card",
  "selectionType": "image_type",
  "questions": [
    { "question": "你想制作哪种商品图片？", "options": ["主图优化", "轮播图", "详情图", "背景替换", "数字模特"], "allowMultiple": false, "required": true }
  ]
}
```

### 回传映射

| 用户选择 | 对应 --type 参数 |
|---------|

skill-card.md

## Description:

Routes 1688 sellers to product image workflows for main image optimization, carousel images, detail images, background replacement, and digital model generation through permission checks and tool-page URL construction.

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

## Publisher:

[1688aiinfra](https://clawhub.ai/user/1688aiinfra)

### License/Terms of Use:

MIT-0

## Use Case:

External 1688 sellers use this skill to choose and open the correct product-image creation tool for main images, carousels, detail images, background replacement, or digital model generation. The skill can also configure access credentials and verify digital model permission before routing restricted workflows.

### Deployment Geography for Use:

Global

## Known Risks and Mitigations:

Risk: The skill can persist a 1688 access key in local OpenClaw configuration.

Mitigation: Install only where local credential persistence is permitted; use scoped credentials where available and rotate or remove the key when the skill is no longer needed.

Risk: The skill sends authenticated usage telemetry through the 1688 gateway after CLI commands.

Mitigation: Review telemetry acceptability before installation and deploy only in environments where this reporting is allowed.

Risk: Opened tool URLs may include a session identifier and image or offer parameters.

Mitigation: Avoid sharing generated tool URLs or logs that contain them, and confirm that session handling matches the account's data-handling policy.

Risk: Workflow instructions can limit what the parent agent says after execution.

Mitigation: Review and test workflow behavior before deployment so suppressed responses do not hide errors or unexpected outcomes.

## Reference(s):

- [ClawHub skill page](https://clawhub.ai/1688aiinfra/skills/1688-item-image-optimizer)
- [Interaction specs](references/interaction-specs.md)
- [1688 image tool entrypoint](https://air.1688.com/app/CSBC-modules/csbc-ai-component-loader/picture-optimize.html)

## Skill Output:

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

**Output Format:** [JSON command results, Markdown messages, and OpenClaw interaction payloads.]

**Output Parameters:** [1D]

**Other Properties Related to Output:** [May open 1688 tool pages, show image-type or image-selection cards, and return fail-closed guidance when permission checks fail.]

## Skill Version(s):

0.51.0 (source: ClawHub release metadata; artifact frontmatter declares 1.0.0)

## 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.

Sponsored

Ads related to 1688-item-image-optimizer and adjacent AI workflows.