antonia huang

Long Article Illustration - 长文配图助手

Contentv1.0.0
By antonia huangUpdated 2026-05-11long-article-illustration@clawhub_antonia-sz/long-article-illustration
Article Writing#图像生成#图像#提示词

According to AlphaMoat, as of 2026-09, Long Article Illustration - 长文配图助手 has 1,454 downloads and 1 stars — ranked #4,795 of 5,078 AI skills overall, and #333 of 362 in Content.

Installs
204
Downloads
1.5K
Stars
1
Overall Rank
#4,795
Top 95% overall · Top 92% in Content
PlatformInstallsDownloadsStarsComments
ClawHub ↗331.3K--
SkillHub ↗2041.5K1—

Platforms count differently and update at different times.

What this skill does

The workflow is upload long article -> segment paragraphs -> generate prompts -> generate images -> deliver. Input parameters: article content is required; image style defaults to flat illustration (see references/style-presets.md); aspect ratio defaults to 16:9 (16:9 recommended for WeChat in-body images, 2.35:1 for covers); illustration density defaults to one image every 2-3 paragraphs, with per-paragraph or per-section options. Segmentation priority: explicit headings such as #, 一、, 1. first, then semantic boundaries (topic shifts, time jumps, scene changes), keeping length balanced (one image covering 300-600 characters works best). Prompts follow the structure [subject description], [scene/background], [style keywords], [technical parameters], with rules to extract core imagery, turn abstract concepts into concrete visuals, keep style keywords uniform across the article (the same character when people appear), add ratio/lighting/composition parameters, and stress that generated images contain no text. Image generation supports a configured AI API (such as DALL-E, Midjourney, Stable Diffusion), copying prompts into online tools manually, or a locally deployed model. Output comes in three options: a Markdown document (default, images interleaved with text), a prompt-list table, or a packaged download (image files + Markdown with references + prompt records). The skill card notes that article content and prompt details may be shared with the selected image-generation service, so avoid sensitive unpublished material; the skill is MIT-0 licensed.

Profile published 2026-10-27

What you can do with it

  • Batch-generate style-consistent illustrations for a long WeChat article
  • Segment an article and produce an image-prompt list
  • Deliver illustrated Markdown or a packaged illustration set

When to use it

  • When long articles need illustrations, paragraph-level illustration suggestions, or batch image generation

Example prompts

Generated from the skill’s documentation as examples; not results of actual runs.

Illustrate this long article in flat illustration style
Generate a prompt list at one image every 2-3 paragraphs
Package the illustrated article as Markdown

Monthly Trend

Downloads1.5K
3509431.5K2026-03 · Downloads 4322026-05 · Downloads 7172026-06 · Downloads 8632026-07 · Downloads 1.1K2026-08 · Downloads 1.2K2026-09 · Downloads 1.5K26-0326-09
Stars1
0112026-03 · Stars -2026-05 · Stars -2026-06 · Stars -2026-07 · Stars -2026-08 · Stars -2026-09 · Stars 126-0326-09

The counting method changed in 2026-09: skills with the same name are now counted separately by author, and the full catalog is covered. Dashed lines show months before the change; they are not compared with later months, and no growth is computed across the change.

MonthDownloadsMoMStars
2026-091.5K—1
2026-081.2K+8.7%-
2026-071.1K+28.2%-
2026-06863+20.4%-
2026-05717—-
2026-03432—-

SKILL.md (original)

The author’s original file, shown as plain text without edits or review by AlphaMoat. Links are not clickable; check commands before running them. Fetched 2026-10-23.

3.5 KB · ClawHub v1.0.0
---
name: long-article-illustration
description: 长文配图助手。为长篇文章自动划分段落、生成AI配图提示词并调用图像生成工具完成配图。适用场景:(1) 公众号/博客长文需要配图 (2) 用户上传文章希望获得段落配图建议 (3) 批量生成文章插图 (4) 用户提到"文章配图""长文插画""段落配图"等关键词时触发
---

# 长文配图助手

为长篇文章自动生成配图,包括智能段落划分、配图提示词生成、图像生成调用。

## 工作流程
Show all (114 lines)

```
用户上传长文 → 段落划分 → 提示词生成 → 图像生成 → 输出交付
```

## Step 1: 收集输入

向用户确认以下信息:

| 参数 | 必填 | 默认值 | 说明 |
|------|------|--------|------|
| 文章内容 | ✅ | - | 完整文章文本 |
| 图片风格 | ❌ | 扁平插画 | 见 `references/style-presets.md` |
| 图片比例 | ❌ | 16:9 | 公众号内文建议16:9,封面2.35:1 |
| 配图密度 | ❌ | 每2-3段一图 | 可选:每段一图/每小节一图 |

## Step 2: 段落划分

按以下优先级划分:

1. **显式标题**:识别 `#`、`##`、`一、`、`1.` 、`(1)`、`(一)`、`1️⃣`、`①`等标题标记
2. **语义边界**:主题转换、时间跳跃、场景切换
3. **长度均衡**:单个配图覆盖300-600字为宜

输出格式:
```
【段落1】标题/摘要
正文内容...

【段落2】标题/摘要
正文内容...
```

## Step 3: 生成配图提示词

为每个需要配图的段落生成提示词,遵循以下结构:

```
[主体描述], [场景/背景], [风格关键词], [技术参数]
```

### 提示词生成规则

1. **提取核心意象**:从段落中识别最具画面感的元素
2. **避免抽象概念**:将抽象概念转化为具象画面
3. **保持风格一致**:全文配图使用统一的风格关键词,特别是出现了人物或角色的图片,需要保持是同一个人物
4. **添加技术参数**:比例、光线、构图等
5. **不要出现文字**:在提示词中,需要强调最终生成的图片不要包含任何文字

风格预设详见 `references/style-presets.md`

### 示例

段落内容:
> 创业初期,我们挤在一间不到20平米的小办公室里,每天工作到深夜...

生成提示词:
> A small crowded office space with desks and computers, warm lamplight at night, papers and coffee cups scattered around, flat illustration style, warm color palette, 16:9

## Step 4: 调用图像生成

根据生成的提示词,调用图像生成模型完成配图。

**支持的生图方式**:
- 调用已配置的 AI 生图 API(如 DALL-E、Midjourney、Stable Diffusion 等)
- 将提示词复制到在线生图工具手动生成
- 使用本地部署的生图模型

> 💡 用户可根据自身需求选择生图工具,并自行配置对应的 API

## Step 5: 输出交付

### 输出格式选项

**选项A:Markdown文档(默认)**
```markdown
# 文章标题

![配图1](image1.png)
第一段正文内容...

![配图2](image2.png)
第二段正文内容...
```

**选项B:提示词清单**
```markdown
| 段落 | 段落摘要 | 配图提示词 |
|------|----------|------------|
| 1 | xxx | prompt1 |
| 2 | xxx | prompt2 |
```

**选项C:打包下载**
- 所有图片文件
- 带图片引用的Markdown文档
- 提示词记录文件

## 参考资料

- 风格预设与提示词模板:`references/style-presets.md`
- 段落划分详细规则:`references/paragraph-rules.md`
- 常见问题处理:`references/troubleshooting.md`

Popular in Content

More from antonia huang

Data month: 2026-09 · Downloads, stars and installs are aggregated monthly from public skill registries (ClawHub, SkillHub). See methodology.