What makes Doubao Image Gen 豆包图片生成 notable?

2K downloads. Trust evidence available

How should Doubao Image Gen 豆包图片生成 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

Doubao Image Gen 豆包图片生成

豆包AI图片生成技能 - 视觉设计师专用 Skill: Doubao Image Gen 豆包图片生成 Owner: zhuchenggong19851114-design Summary: 豆包AI图片生成技能 - 视觉设计师专用 Tags: latest:1.0.0 Version history: v1.0.0 | 2026-03-25T23:23:44.580Z | auto doubao-image-gen v1.0.0 - Initial release of the 豆包AI图片生成技能，专为视觉设计师设计 - 明确要求先询问用户图片需求与偏好后再生成图片 - 规定了详细的十步图片生成、选择、确认并保存的流程 - 强调每一个步骤须获得用户确认才能进入下一步 - 所有截图必须通过 message 工具实际发图给用户，禁止使用虚拟路径 - 强制下载后复制文件到 D:\OpenClaw\downloads\images\ 目录 Archive index: Ar

OpenClaw

View on ClawHub Homepage

Rank

Safety

Downloads

2.0k

Updated

Oct 9, 2026

Version

1.0.0

Source

CLAWHUB

About

What it does, and when to use it.

Capability contract not published. No trust telemetry is available yet. 2K downloads reported by the source. Last updated 10/9/2026.

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 9, 2026
Protocol compatibility: OpenClawcompatibility · observed Oct 9, 2026
Adoption signal: 2K downloadsadoption · observed Oct 9, 2026
Latest release: 1.0.0release · observed Mar 25, 2026
Handshake status: UNKNOWNsecurity

Install and run

Setup complexity: low.

clawhub skill install s175hh7wvdt1z18hr1txy3da4h83haab:zhuchenggong-doubao-image-gen

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-zhuchenggong19851114-design-zhuchenggong-doubao-image-g/snapshot"

Documentation

CLAWHUB

3,500 characters of source documentation, loaded on request.

Extracted files

4 files captured from the source.

SKILL.md

---
name: doubao-image-gen
description: 豆包AI图片生成技能 - 视觉设计师专用
---

# 豆包生图技能

## ★★★ 调度时必读 ★★★
收到任务后，**第一步**必须是：问用户想要什么样的图片？有什么要求？
不要直接去生成图片！

---

## 完整流程

一、点开豆包AI创作页面
二、**问客户**想要什么样的图片/有什么要求 ← 第一步！
三、客户确认后，输入提示词
四、设置比例：默认3:4，**如果客户选了比例则按客户的**
五、点击发送按钮生成图片
六、等待图片生成完成
七、**★ 子Agent截大图** - 生成后立即截4张图，通过 message 工具发给用户选择
八、用户选好后，点开大图确认
九、用户确认后，点击下载原图保存
十、**★ 复制到 D 盘** - 下载后立即复制到 D:\OpenClaw\downloads\images\

## 生成前确认要素（必须）

1. ★ 先问客户：想要什么样的图片？有什么提示词/要求？
2. 客户确认后，输入提示词
3. 设置比例：默认3:4，如果客户选了比例则按客户的
4. 点击发送按钮生成

## 关键规则

1. ★ 必须先问客户想要什么样的图片
2. 输入提示词后，点发送按钮（向上的箭头），不要按回车
3. 等待图片完全生成后再截图
4. 用户选好后要点开大图确认
5. 用户确认后才能保存
6. 每步必须拿到结果才能下一步
7. ★ **截图必须用 message 工具发图片给用户**，不要用虚拟路径
8. ★ 截图路径用实际路径：`/home/success/.openclaw/media/browser/xxx.jpg`
9. ★ **下载后必须复制到 D 盘**：`cp xxx.jpg /mnt/d/OpenClaw/downloads/images/`

README.md

# doubao-image-gen

豆包AI图片生成技能，供视觉设计师使用。

## 功能

用豆包网页版AI生成图片。

## 使用方法

1. 打开 https://www.doubao.com/chat/create-image
2. 输入图片描述（主体、风格、颜色、尺寸）
3. 选择比例和风格
4. 等待生成完成后截图给用户选择
5. 用户确认后保存图片

## 详细说明

请参阅 [SKILL.md](./SKILL.md)

_meta.json

{
  "ownerId": "kn74j8mb29k20hsggp7f6j0bbs82p8gx",
  "slug": "zhuchenggong-doubao-image-gen",
  "version": "1.0.0",
  "publishedAt": 1774481024580
}

skill-card.md

## Description:

豆包AI图片生成技能 - 视觉设计师专用.

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

## Publisher:

[zhuchenggong19851114-design](https://clawhub.ai/user/zhuchenggong19851114-design)

### License/Terms of Use:

MIT-0

## Use Case:

External visual designers use this skill to guide an agent through collecting image requirements, generating images on Doubao's web image-creation page, presenting generated options for user selection, and saving confirmed outputs.

### Deployment Geography for Use:

Global

## Known Risks and Mitigations:

Risk: Confirmed generated images are saved and copied to a persistent local D drive folder.

Mitigation: Avoid sensitive or proprietary prompts and images unless persistent local storage is acceptable, and delete saved outputs manually when no longer needed.

## Reference(s):

- [Doubao image creation page](https://www.doubao.com/chat/create-image)
- [ClawHub skill page](https://clawhub.ai/zhuchenggong19851114-design/skills/zhuchenggong-doubao-image-gen)

## Skill Output:

**Output Type(s):** [Guidance, Shell commands, Files]

**Output Format:** [Markdown guidance with inline shell commands and generated image files]

**Output Parameters:** [1D]

**Other Properties Related to Output:** [Selected images are saved locally and copied to a persistent D drive folder after user confirmation.]

## Skill Version(s):

1.0.0 (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 9h 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.