auto-article-images

auto-article-images Smart Image Assistant

Overview

The Smart Image Assistant is used to answer "still need images, so troublesome", image matching, cover, and article images. It is suitable for content creators, operations, technical staff, and content media to call after clarifying business goals, content materials, or analysis targets. It combines inputs such as the main text, article body, or Markdown to organize key context, and outputs summaries, diagnostic conclusions, action recommendations, and reusable deliverables, making it easy to continue execution, review, or delivery.

When to Use

Applicable Scenarios

The user raises issues like "still need images, so troublesome" and needs to quickly break down goals, determine priorities, and form executable results.
Content creators, operations, technical staff, and content media need to generate summaries, diagnostic conclusions, action recommendations, and reusable deliverables around the Smart Image Assistant.
The user has already prepared the visual style, title, and number of images, and hopes to organize them into executable analysis or optimization results.
The user needs to turn materials related to the Smart Image Assistant into clear conclusions, priorities, and next steps.

How to Call

Call the AI Skills API directly through the exported Python runner:

Command Example

Basic Call

python3 scripts/run.py --params '{}'

Call with Common Parameters

python3 scripts/run.py --params '{"style":"clean-commercial"}'

Parameter Description

Parameter	Type	Required	Default	Description
`style`	string	No	`clean-commercial`	Visual style; optional values: clean commercial (`clean-commercial`), magazine photography (`editorial-photo`), soft illustration (`soft-illustration`), tech diagram (`tech-diagram`）
`title`	string	No	-	Title
`imageCount`	integer	No	`4`	Number of images
`sourceText`	string	No	-	Article body or Markdown
`coverRatios`	array	No	`["2.35:1","1:1","16:9","3:4","9:16"]`	Cover ratio
`watermarkMode`	string	No	`off`	Watermark; optional values: none (`off`), bottom right (`corner`), tiled (`tiled`), both (`both`）
`sourceDocument`	string	No	-	Supports text files such as docx, md, txt, etc.
`publishPlatform`	string	No	`all`	Publishing platform; optional values: all platforms (`all`), WeChat Official Account (`wechat`), Xiaohongshu (`xhs`), blog (`blog`), Zhihu (`zhihu`）
`brandRequirements`	string	No	-	Brand requirements

See the complete machine-readable parameter structure at references/form-schema.json。

Parameter Value Reference

This skill currently has no categorical parameters that require additional lookup.

Supported Input Formats

This skill directly accepts JSON parameters and does not involve parsing shared links.

Example Request

The example parameters below can be passed directly to scripts/run.py, and the runner will send them to the AI Skills API.

python3 scripts/run.py --params '{"style":"clean-commercial"}'

Equivalent --params JSON：

{
  "style": "clean-commercial"
}

Example Return Result

{
  "success": true,
  "data": {
    "mode": "async",
    "status": "completed",
    "resultEnvelope": {
      "status": "completed",
      "title": "配图结果已生成",
      "summary": "已生成正文配图和多比例封面。",
      "items": [
        {
          "id": "image-package",
          "type": "attachmentGroup",
          "title": "配图文件",
          "artifactIds": [
            "content-01.webp",
            "cover-wechat-2_35x1.webp"
          ]
        }
      ],
      "artifacts": [
        {
          "id": "content-01.webp",
          "name": "content-01.webp",
          "relativePath": "content-01.webp",
          "mimeType": "image/webp",
          "url": "/api/skill-artifacts/job_demo/file/content-01.webp"
        },
        {
          "id": "cover-wechat-2_35x1.webp",
          "name": "cover-wechat-2_35x1.webp",
          "relativePath": "cover-wechat-2_35x1.webp",
          "mimeType": "image/webp",
          "url": "/api/skill-artifacts/job_demo/file/cover-wechat-2_35x1.webp"
        }
      ],
      "presentation": {
        "mode": "single"
      }
    },
    "zipUrl": "/api/skill-artifacts/job_demo/archive"
  },
  "meta": {
    "executionTime": 842,
    "cached": false
  }
}

Deliverables

Body images: generate image assets that can be inserted into the content around the article topic.
Multi-ratio covers: adapt to cover usage scenarios on different content platforms.
Image delivery package: convenient for continued download, filtering, publishing, or secondary design.

Suggestions for using the results

First check whether the images accurately express the article topic, then choose assets suitable for body insertion and cover display.
Different platforms have different requirements for cover aspect ratios and visual styles, so before use it is recommended to make the final choice according to the publishing channel.
The clearer the input article summary, target platform, and style preference, the easier it is for the generated results to fit the content.

Preparation before running

AISKILLS_BASE_URL: default https://ai-skills.ai
AISKILLS_API_KEY: required, used for authenticated calls
AISKILLS_TENANT_ID: default default