doubao-creator
Skill1 starsChanged 3 months agoApache-2.0View on GitHub
豆包（字节跳动 AI）网页操作 skill——通过 CDP 控制夸克浏览器中的豆包网页版（doubao.com）。能力：①看图分析/反推形象描述（普通对话看图，无限制）；②文生视频（Seedance 2.0，10s 竖屏等）；③图生视频（⚠️ 肖像保护：Seedance 不支持上传真实人脸参考图，会拒绝；破局法=先让豆包看图反推形象文字描述 → 再用文字锚定文生视频）。零 API Key，需豆包账号登录态。当需要豆包分析图片、生成视频、或做字节系 AI 任务时使用。
In this repository51 other files it gives its agents.
- 3d-animation-short-generatorSkill
- brand-promo-video-generatorSkill
- colleague-cameronSkill
- colleague-muskSkill
- colleague-supermateSkill
- comfyui-zimage-9bSkill
- context-handoffSkill
- co-op-game-intro-generatorSkill
- deepseek-eyesSkill
- dot-skillSkill
- dsh-deepseek-vision-bridgeSkill
- dsh-im-wecomSkill
- cordis-plugin-developmentSkill
- dsh-archive-agent-notesSkill
- dsh-code-reviewSkill
- dsh-doc-site-syncSkill
- dsh-doc-standardsSkill
- dsh-find-simplificationsSkill
- dsh-merging-stacked-prsSkill
- dsh-pre-push-checksSkill
- dsh-prose-standardSkill
- dsh-translate-docsSkill
- dsh-trim-cot-leakageSkill
- editing-cordis-compositionsSkill
- record-browser-gifSkill
- dsh-upgrade-runbookSkill
- h3-prompt-writingSkill
- handdrawn-live-video-generatorSkill
- hermes-memorySkill
- image-analysisSkill
- lyric-mv-storyboardSkill
- lyric-to-storyboard-face-lockSkill
- lyric-to-storyboard-lrcSkill
- lyric-to-storyboardSkill
- minimalist-product-ad-generatorSkill
- h3-video-producerSkill
- modelscope-apiSkill
- multi-agent-orchestratorSkill
- music-video-subtitle-generatorSkill
- paper-collage-explainer-generatorSkill
- papercraft-stop-motion-explainerSkill
- quark-driveSkill
- quark-qwen-visionSkill
- rh-workflow-9bSkill
- rh-workflowSkill
- supermate-code-reviewSkill
- Supermate-harness-launcherSkill
- supermate-scriptSkill
- colleague-supermateSkill
- video-production-studioSkill
- visual-file-organizerSkill
The file
Files
doubao-creator — 豆包网页操作 Skill
通过 CDP 控制夸克浏览器里的豆包网页版（doubao.com/chat/），零 API Key、零本地算力。 前置：夸克以
--remote-debugging-port=9222运行 + 豆包已登录（doubao.com/chat/页面打开）。
脚本清单
| 脚本 | 用途 |
doubao-vision.js | 看图分析 / 反推形象描述（上传图片 → 提问 → 读回复） |
doubao-genvideo-text.js | 文生视频（Seedance 2.0）：输入需求 → 长轮询 → 自动点卡片播放 → 抓抖音 CDN URL → 下载 |
doubao-genvideo2.js | 图生视频（仅非人脸图可用，见下方肖像保护） |
cdp.js | CDP 客户端库 |
调用方式
# 看图/反推形象
node "<skill>\scripts\doubao-vision.js" <图片路径> "请详细描述图中人物形象特征，用于视频生成提示词"
# 文生视频（10s 竖屏广告等）
node "<skill>\scripts\doubao-genvideo-text.js" "请生成一个10秒的竖屏广告视频，主题：...画面：...主角形象：..."⚠️ 肖像保护限制（关键踩坑）
- Seedance 2.0 不支持上传真实人脸参考图：图生视频传人物照片 → 豆包拒绝（"出于肖像保护考虑…"）
- 非人脸参考图（物品/风景/背景）可以图生视频
- 破局法（人物形象）：先让豆包看图反推文字描述（看图不受限制）→ 把精确描述写进文生视频提示词 → Seedance 按文字生成近似形象
关键经验
- 视频生成耗时：Seedance 预计 5 分钟，脚本最长轮询 10 分钟
- 检测完成：页面出现新
.block-video卡片 = 视频生成完成；必须点击卡片播放后<video>元素才出现，URL 指向抖音 CDN（v6/v9-default.douyin.com） - 下载：带
Referer: https://www.doubao.com/头 - 文生视频提示词：主角形象要写"写实真人+发色+发型+服装+气质"（越具体越像）；豆包反推的 Prompt 片段可直接复用
- 误判防范：拒绝检测用精确短语（"出于肖像保护"等），且发送后至少等 30 秒再判定
故障排查
| 现象 | 处理 |
| "未找到豆包页面" | 确认夸克调试模式 + doubao.com/chat/ 已打开 |
| 拒绝提示（肖像保护） | 换非人脸参考图，或走"看图反推→文生视频"路线 |
| 视频未出现 | 等待 5-10 分钟；检查是否需点击卡片播放 |
| 找不到"生成视频"按钮 | 对话内直接文字描述需求即可触发 Seedance（已验证） |
关联
- 工具脚本目录：
<skill 目录>\scripts\（cdp.js 客户端 / doubao-vision.js 看图 / doubao-genvideo-text.js 文生视频 / doubao-genvideo2.js 图生视频） - 同族 skill：
quark-qwen-vision（夸克千问看图/生图） - 模型矩阵：DeepSeek（主脑）+ 千问（视觉/生图）+ 豆包（视频/字节系）
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.