Skip to content
Agentmart
Submit a tool

scipop-comic-xinghe

科普连环画自动生成工具 - 基于百度星河社区 API 的三阶段闭环创作系统。 TRIGGER when: 用户想要将科普文章/科学内容转化为连环画、漫画、视觉叙事; 用户提到"连环画"、"科普漫画"、"可视化科普"、"科学故事画";…

Skill by AgenticAIPlan

IndexedMIT★ 12
Write a review

Chalk Labs

Need help deploying scipop-comic-xinghe?

Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.

Book a call

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/agenticaiplan-scipop-comic-xinghe

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

科普连环画自动生成工具 - 基于百度星河社区 API 的三阶段闭环创作系统。 TRIGGER when: 用户想要将科普文章/科学内容转化为连环画、漫画、视觉叙事; 用户提到"连环画"、"科普漫画"、"可视化科普"、"科学故事画"; 用户有科普内容需要视觉化呈现;用户提到"星河API"或"Ernie-image"生图。 不要触发: 用户只是想生成单张图片(非连环画)、用户要处理非科普类内容。

Use cases: backend

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found
Runs as
Python package

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/scipop-comic-xinghe

What's inside

Skill name
scipop-comic-xinghe
Description
科普连环画自动生成工具 - 基于百度星河社区 API 的三阶段闭环创作系统。 TRIGGER when: 用户想要将科普文章/科学内容转化为连环画、漫画、视觉叙事; 用户提到"连环画"、"科普漫画"、"可视化科普"、"科学故事画"; 用户有科普内容需要视觉化呈现;用户提到"星河API"或"Ernie-image"生图。 不要触发: 用户只是想生成单张图片(非连环画)、用户要处理非科普类内容。
License
MIT
Instructions
334 lines in SKILL.md · view on GitHub

Before installing

  • Ships executable scripts
  • Instructions call the network

Files (10)

  • README.md
  • SKILL.md
  • evals.json · evals/
  • api_reference.md · references/
  • article_analysis_prompts.md · references/
  • ernie_image_prompt_guide.md · references/
  • script_writing_guide.md · references/
  • style_guide.md · references/
  • generate_comic.py · scripts/
  • retry_utils.sh · scripts/

SKILL.md (first lines)

---
name: scipop-comic-xinghe
description: |
  科普连环画自动生成工具 - 基于百度星河社区 API 的三阶段闭环创作系统。

  TRIGGER when: 用户想要将科普文章/科学内容转化为连环画、漫画、视觉叙事;
  用户提到"连环画"、"科普漫画"、"可视化科普"、"科学故事画";
  用户有科普内容需要视觉化呈现;用户提到"星河API"或"Ernie-image"生图。

  不要触发: 用户只是想生成单张图片(非连环画)、用户要处理非科普类内容。
---

# SciPop Comic Orchestrator(科普连环画编排器)

基于百度星河社区 API 的自动化科普连环画生成工具,实现多模态解析 × 单 Panel 精修 × N×N 全局合成的三阶段闭环创作。

---

## 环境配置

> 📖 详细 API 文档参见 [references/api_reference.md](references/api_reference.md)

### 必需条件

| 项目 | 要求 |
|------|------|
| **API Key** | 星河社区 API Key,环境变量 `AISTUDIO_API_KEY` |
| **API 端点** | `https://aistudio.baidu.com/llm/lmapi/v3/chat/completions` |
| **分析模型** | `ernie-5.0-thinking-preview`(原生全模态大模型) |
| **生图模型** | `ernie-image-turbo`(图像生成 API) |

### 配置验证

```bash
# 设置 API Key
export AISTUDIO_API_KEY="your-key"

# 验证连通性
curl -s https://aistudio.baidu.com/llm/lmapi/v3/chat/completions \n  -H "Content-Type: application/json" \n  -H "Authorization: Bearer $AISTUDIO_API_KEY" \n  -d '{"model": "ernie-5.0-thinking-preview", "messages": [{"role": "user", "content": "ping"}], "stream": true, "max_completion_tokens": 100}'
```

---

## 参考文档

| 文档 | 用途 |
|------|------|
| [references/api_reference.md](references/api_reference.md) | 星河社区 API 详细参考 |
| [references/article_analysis_prompts.md](references/article_analysis_prompts.md) | 文章解析提示词模板 |
| [references/ernie_image_prompt_guide.md](references/ernie_image_prompt_guide.md) | ERNIE-Image 提示词撰写指南 |
| [references/style_guide.md](references/style_guide.md) | 连环画风格设计指南 |

---

## 工作流程

### Phase 1: 文章解析与 Prompt 建模

**目标**: 将科普文章拆解为 4-6 个视觉场景,生成风格一致的图像 Prompt。

> 📖 详细规范参见 [references/article_analysis_prompts.md](references/article_analysis_prompts.md)

#### 提示词结构规范

**系统提示词模板**:

```
你是一位科普连环画脚本编写专家。分析文章并根据内容的丰富程度和结构确定最合适的 Panel 数量(4-6个)。输出一个 JSON 对象,包含四个字段:"recommended_panels"(整数,4-6),"recommendation_reason"(一句话中文解释为什么这个 Panel 数量适合该文章),"style_seed"(简短的中文风格描述,在所有 Panel 中复用),"panels"(与推荐数量匹配的对象数组,每个对象包含 "id"、"scene" 中文场景描述、"image_prompt" 中文图像生成提示)。仅输出原始 JSON,不要使用 markdown 代码块。
```

**image_prompt 撰写规范**(详见 [references/ernie_image_prompt_guide.md](references/ernie_image_prompt_guide.md)):

```
{主体特征},{动作姿态},{环境背景},{细节元素},{风格关键词},{质量标签}
```

**示例**:
```
一位戴眼镜的女科学家,穿着白色实验服,正激动地指着屏幕,现代实验室背景有显微镜和电脑,屏幕上显示橙红色的黑洞光环图像,扁平插画风格,清晰轮廓,科学配色,高质量,连环画
```

#### Panel 数量决策规则

| Panel数 | 适用场景 |
|--------|---------|
| 4 | 内容简洁,结构清晰,有明确的起承转合 |
| 5 | 内容适中,需要一个过渡或高潮格 |
| 6 | 内容丰富,知识点多,需要完整叙事链 |

#### 风格种子设计规范

> 📖 详细规范参见 [references/style_guide.md](references/style_guide.md)

**格式**: `{画风},{色调},{线条/质感},{氛围}`

| 主题类型 | 推荐风格种子 |
|---------|-------------|
| 天文/物理 | 扁平插画风格,深邃太空蓝配色,清晰轮廓,科学严谨氛围 |
| 生物/医学 | 可爱卡通风,柔和粉彩配色,圆润造型,温馨友好 |
| 环境/生态 | 水彩手绘风,清新自然色调,柔和笔触,生态感 |
| 科技/AI | 赛博朋克风格,霓虹光效,高科技质感,未来感 |
| 科学史 | 复古连环画风,怀旧暖色调,经典漫画风格 |

**步骤**:
1. 接收用户提供的科普文章全文
2. 调用 `ernie-5.0-thinking-preview` 进行解析
3. 向用户展示推荐的 Panel 数量及理由,获取确认

**API 调用模板**:

```bash
curl -s https://aistudio.baidu.com/llm/lmapi/v3/chat/completions \n  -H "Content-Type: application/json" \n  -H "Authorization: Bearer $AISTUDIO_API_KEY" \n  -d '{
    "model": "ernie-5.0-thinking-preview",
    "messages": [
      {
        "role": "system",
        "content": "你是一位科普连环画脚本编写专家。分析文章并根据内容的丰富程度和结构确定最合适的 Panel 数量(4-6个)。输出一个 JSON 对象,包含四个字段:"recommended_panels"(整数,4-6),"recommendation_reason"(一句话中文解释为什么这个 Panel 数量适合该文章),"style_seed"(简短的中文风格描述,在所有 Panel 中复用),"panels"(与推荐数量匹配的对象数组,每个对象包含 "id"、"scene" 中文场景描述、"image_prompt" 中文图像生成提示)。仅输出原始 JSON,不要使用 markdown 代码块。"
      },
      {
        "role": "user",

From AgenticAIPlan/AgenticAISkills, MIT.

More from AgenticAIPlan/AgenticAISkills

Signals

Stars
12
Forks
55
Open issues
4
Last commit (this folder)
Apr 24, 2026 (6 months ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from AgenticAIPlan

Done for you

Rather not set it up yourself?

Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.

See how we build AI agents →Read the case studies

Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.

launches shipped
50+
launches shipped
media placements
500+
media placements
founders on every account
2
founders on every account

Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block

Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.

Get scipop-comic-xinghe running in your business

Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.

Goes to the Chalk Labs founders, not the newsletter. Privacy

Need help deploying scipop-comic-xinghe?

CallGet help
Cite this page

scipop-comic-xinghe skill. Agent Mart. https://agentmart.dev/skills/agenticaiplan-scipop-comic-xinghe (last updated 2026-10-24)