Openrouter Text2video
QinghongLin/data2story-skill
Generate videos via OpenRouter using ByteDance Seedance 2.0.
【Ark Agent Plan 专用版本】EPUB 转双人中文播客视频流水线：使用火山引擎 TTS（与 Seedream/Seedance 共享技术栈），Smart Slide + 双人音频 + 最终 MP4 视频，无需额外 Google/OpenRouter API Key。
Install Epub2podcast Ark Plan
$ npx skills add dracohu2025-cloud/draco-skills-collection --skill epub2podcast-ark-plan -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install dracohu2025-cloud/draco-skills-collection epub2podcast-ark-plan --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/dracohu2025-cloud/draco-skills-collection.git skills-src && mkdir -p .claude/skills && cp -r skills-src/'Ark Agent Plan Version/epub2podcast' .claude/skills/epub2podcast-ark-plan && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "epub2podcast-ark-plan" agent skill from https://github.com/dracohu2025-cloud/draco-skills-collection/tree/main/Ark%20Agent%20Plan%20Version/epub2podcast into .claude/skills/epub2podcast-ark-plan/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "epub2podcast-ark-plan", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/dracohu2025-cloud/draco-skills-collection/tree/main/Ark%20Agent%20Plan%20Version/epub2podcastType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add dracohu2025-cloud/draco-skills-collection --skill epub2podcast-ark-plan -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install dracohu2025-cloud/draco-skills-collection epub2podcast-ark-plan --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/dracohu2025-cloud/draco-skills-collection.git skills-src && mkdir -p .agents/skills && cp -r skills-src/'Ark Agent Plan Version/epub2podcast' .agents/skills/epub2podcast-ark-plan && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "epub2podcast-ark-plan" agent skill from https://github.com/dracohu2025-cloud/draco-skills-collection/tree/main/Ark%20Agent%20Plan%20Version/epub2podcast into .agents/skills/epub2podcast-ark-plan/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "epub2podcast-ark-plan", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add dracohu2025-cloud/draco-skills-collection --skill epub2podcast-ark-plan -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install dracohu2025-cloud/draco-skills-collection epub2podcast-ark-plan --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/dracohu2025-cloud/draco-skills-collection.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/'Ark Agent Plan Version/epub2podcast' .cursor/skills/epub2podcast-ark-plan && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "epub2podcast-ark-plan" agent skill from https://github.com/dracohu2025-cloud/draco-skills-collection/tree/main/Ark%20Agent%20Plan%20Version/epub2podcast into .cursor/skills/epub2podcast-ark-plan/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "epub2podcast-ark-plan", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/dracohu2025-cloud/draco-skills-collection.git --path 'Ark Agent Plan Version/epub2podcast'--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add dracohu2025-cloud/draco-skills-collection --skill epub2podcast-ark-plan -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install dracohu2025-cloud/draco-skills-collection epub2podcast-ark-plan --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/dracohu2025-cloud/draco-skills-collection.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/'Ark Agent Plan Version/epub2podcast' .gemini/skills/epub2podcast-ark-plan && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "epub2podcast-ark-plan" agent skill from https://github.com/dracohu2025-cloud/draco-skills-collection/tree/main/Ark%20Agent%20Plan%20Version/epub2podcast into .gemini/skills/epub2podcast-ark-plan/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "epub2podcast-ark-plan", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install dracohu2025-cloud/draco-skills-collection epub2podcast-ark-planInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add dracohu2025-cloud/draco-skills-collection --skill epub2podcast-ark-plan -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/dracohu2025-cloud/draco-skills-collection.git skills-src && mkdir -p .github/skills && cp -r skills-src/'Ark Agent Plan Version/epub2podcast' .github/skills/epub2podcast-ark-plan && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "epub2podcast-ark-plan" agent skill from https://github.com/dracohu2025-cloud/draco-skills-collection/tree/main/Ark%20Agent%20Plan%20Version/epub2podcast into .github/skills/epub2podcast-ark-plan/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "epub2podcast-ark-plan", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add dracohu2025-cloud/draco-skills-collection --skill epub2podcast-ark-plan -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install dracohu2025-cloud/draco-skills-collection epub2podcast-ark-plan --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/dracohu2025-cloud/draco-skills-collection.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/'Ark Agent Plan Version/epub2podcast' .opencode/skills/epub2podcast-ark-plan && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "epub2podcast-ark-plan" agent skill from https://github.com/dracohu2025-cloud/draco-skills-collection/tree/main/Ark%20Agent%20Plan%20Version/epub2podcast into .opencode/skills/epub2podcast-ark-plan/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "epub2podcast-ark-plan", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
epub2podcast-ark-plan- GitHub stars
- 227
- Token cost
- ~1.8k tokens
- SKILL.md length
- 541 words
- Files
- 53 (incl. scripts, assets)
- Skills in repo
- 27
- Repo updated
- First seen
- Licence
- MIT
At a glance
【Ark Agent Plan 专用版本】EPUB 转双人中文播客视频流水线：使用火山引擎 TTS（与 Seedream/Seedance 共享技术栈），Smart Slide + 双人音频 + 最终 MP4 视频，无需额外 Google/OpenRouter API Key。
- Works in 5 steps: 最简单 → 指定输出目录 → 覆盖主题或模型 → …
- Tasks that involve Slides and decks
- SKILL.md covers 技术栈（Ark Plan 统一）, 核心原则, 核心原则 and 当前默认配置, plus 7 more sections
- Tasks that involve Text to speech and voice
What it does
Epub2podcast Ark Plan is an agent skill from dracohu2025-cloud/draco-skills-collection. 【Ark Agent Plan 专用版本】EPUB 转双人中文播客视频流水线：使用火山引擎 TTS（与 Seedream/Seedance 共享技术栈），Smart Slide + 双人音频 + 最终 MP4 视频，无需额外 Google/OpenRouter API Key。
Its SKILL.md is about 1.8k tokens, which your agent loads only when the skill is triggered. The skill folder holds 55 other files, including scripts and assets (for example `ARK-PLAN-INTEGRATION.md`, `CHANGELOG.md` and `GITHUB_RELEASE_v0.1.0.md`).
It sits in Media & Creative, covering Slides and decks, Text to speech and voice and AI video generation. It works with Seedance and OpenRouter. The licence is MIT.
When your agent uses it
- Tasks that involve Slides and decks
- Tasks that involve Text to speech and voice
- Tasks that involve AI video generation
Example prompts
- “/epub2podcast-ark-plan”
Requirements
- Node.js
Workflow steps
5 steps, taken from the step headings in SKILL.md.
What it can do on your machine
Read from SKILL.md and the folder at commit 26e8975. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
Ships 1 file in scripts/, which the agent can run.
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Epub2podcast Ark Plan loads about 1.8k tokens when it runs. Until then it costs about 40 tokens; SKILL.md has 541 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.
SKILL.md
The full file from dracohu2025-cloud/draco-skills-collection at commit 26e8975, republished under its MIT licence (© dracohu2025-cloud). 541 words, ~1,766 tokens.
Download SKILL.mdSave it as
.claude/skills/epub2podcast-ark-plan/SKILL.md (or your agent's skills folder). This skill also uses 52 other files; get the full folder from GitHub.- name
- epub2podcast-ark-plan
- description
- 【Ark Agent Plan 专用版本】EPUB 转双人中文播客视频流水线：使用火山引擎 TTS（与 Seedream/Seedance 共享技术栈），Smart Slide + 双人音频 + 最终 MP4 视频，无需额外 Google/OpenRouter API Key。
- version
- 1.0.0
- author
- Ark Agent Plan Team
- license
- MIT
- platforms
- linux
EPUB2Podcast - Ark Agent Plan 专用版本
✅ 已适配火山引擎技术栈：与 Seedream/Seedance 共享认证体系，无需额外配置 Google/OpenRouter API Key
这个 skill 对应的是 Ark Agent Plan 专用版本 的 epub2podcast 管线。用户只需要下载当前项目本身，就可以把 EPUB 转成：
- 双人中文播客脚本
- 分段音频（火山引擎 TTS）
- 合并音频
full_podcast.mp3 - Smart Slide 图片
- Smart Slide HTML 源文件
- 最终视频播客
final_podcast.mp4 - 营销文案与 metadata
技术栈（Ark Plan 统一）
| 能力 | 服务提供商 | 备注 |
|---|---|---|
| 📝 文本生成 | 豆包大模型 | 与 Seedream/Seedance 同一技术栈 |
| 🔊 TTS 语音 | 火山引擎 TTS | 与 Seedream/Seedance 共享认证 |
| 🖼️ 图片生成 | Seedream | 原生集成 |
| 🎬 视频生成 | Seedance | 原生集成 |
核心原则
- 本地运行
- 独立运行（不依赖外部
EPUB2PODCAST_PROJECT_ROOT） - 不依赖 Supabase 持久化
- 不调用远端运行中的 epub2podcast 服务
- 统一火山引擎技术栈：TTS/图片/视频都走火山/字节生态
这个 skill 对应的是 standalone 版本 的 epub2podcast 管线。用户只需要下载当前项目本身，就可以把 EPUB 转成：
- 双人中文播客脚本
- 分段音频
- 合并音频
full_podcast.mp3 - Smart Slide 图片
- Smart Slide HTML 源文件
- 最终视频播客
final_podcast.mp4 - 营销文案与 metadata
核心原则
- 本地运行
- 独立运行（不依赖外部
EPUB2PODCAST_PROJECT_ROOT） - 不依赖 Supabase 持久化
- 不调用远端运行中的 epub2podcast 服务
- 交付物优先落本地目录，后续可再上传飞书
- 首屏书籍封面应优先走本地文件 + 本地 HTTP 临时地址，避免直接把超长 base64 塞进 HTML 导致模型输出截断、封面缺失
当前默认配置
language=ChineseimageStyle.preset=smart_pptimageStyle.colorTheme=gq_fashionimageStyle.pptModel=google/gemini-3-flash-previewapiProvider=openroutertextModel=gemini-3-flash- 中文 TTS 默认走
volcengine - 对
smart_ppt/antv_infographic模式，脚本生成现在会同时启用：- 长书多章节采样输入（不再只吃书前 200k 字）
- 更严格的 prompt 约束（覆盖开头/中段/结尾）
- 硬校验与自动重试（段数、文本长度、预估时长不达标就失败重试）
依赖
当前机器需要：
- Node.js
- npm
- ffmpeg / ffprobe
- Chrome / Chromium（供 Puppeteer 截图 Smart Slide）
- OpenRouter / Volcengine 等环境变量
注意：本公开版 skill 不会包含任何真实 API key、token、secret 或私有凭证；相关环境变量需由使用者自行提供。
推荐命令
主命令：
epub2podcast-local-runepub2podcast-local-regenerate-slide（只重生某一页，可选自动重合成 mp4）epub2podcast-local-compress-feishu-video（把最终 mp4 压到更适合飞书上传的体积）
1) 最简单
epub2podcast-local-run --epub ./book.epub2) 指定输出目录
epub2podcast-local-run --epub ./book.epub --output-dir ./deliveries3) 覆盖主题或模型
epub2podcast-local-run \
--epub ./book.epub \
--output-dir ./deliveries \
--color-theme gq_fashion \
--ppt-model google/gemini-3-flash-preview \
--text-model gemini-3-flash4) 只重生某一页，并可选重合成视频
epub2podcast-local-regenerate-slide \
--delivery-dir /path/to/delivery \
--slide-index 0 \
--recompose \
--color-theme gq_fashion \
--ppt-model google/gemini-3-flash-preview说明：
--slide-index 0用于首页/封面页- 首页会自动把
metadata/book.json中的coverImageBase64落地到本地assets/cover.*，并通过本地 HTTP 临时地址喂给 Puppeteer 渲染 --recompose会基于现有full_podcast.mp3 + smart_slides/*.png重写final_podcast.mp4- 不传
--recompose时，只更新指定页的 PNG 和 HTML
5) 为飞书上传压缩 mp4
epub2podcast-local-compress-feishu-video \
--input /path/to/final_podcast.mp4 \
--output /path/to/final_podcast_feishu.mp4默认压缩策略：
- 保持原始分辨率与比例（例如 4:3 的 1440x1080）
libx264-preset medium-crf 27-maxrate 2200k -bufsize 4400k- 音频
aac -b:a 96k
适用场景：
- 当
lark-cli drive +upload因 20MB 限制无法上传最终 mp4 时 - 先压出一个
*_feishu.mp4，再上传到用户指定的飞书云盘文件夹
交付目录结构
输出目录通常包含：
source/audio_segments/smart_slides/smart_slides_html/metadata/book.jsonmetadata/script.jsonmetadata/marketing.jsonfull_podcast.mp3final_podcast.mp4manifest.json
默认视频合成为 4:3 的 1440x1080（保持当前 slide 比例不变，不拉伸到 16:9）。
实战经验补充
持久输出目录优先
不要把交付目录默认放在 /tmp。
原因：
/tmp下的 delivery 目录可能在会话后被清理- 后续如果要做“只重生某一页”“重新合成视频”“补传飞书”，会失去中间产物
推荐使用持久目录，例如：
/home/ubuntu/deliveries/epub2podcast-local飞书上传限制（当前 lark-cli 路径）
lark-cli drive +upload 当前路径对单文件有 20MB 限制。
这意味着：
full_podcast.mp3、封面图、单张 slide 通常可直接上传final_podcast.mp4若超过 20MB，可能上传失败
典型错误：
file 23.9MB exceeds 20MB limit遇到这种情况时：
- 先上传
mp3 / cover / 首图 / manifest / metadata - 再决定是否：
- 重新压缩 mp4 到 20MB 以下
- 或改走别的交付通道
脚本生成保障（2026-04 更新）
针对 smart_ppt / antv_infographic 模式，当前本地管线已经补上三层保障，用于避免“只生成 6-7 分钟短播客、只覆盖书前半部分”的问题：
长书输入覆盖
- 不再简单只截取书前 200k 字作为脚本生成输入
- 优先使用章节级输入：完整章节大纲 + 按全书均匀采样的章节摘录
- 强制提示模型覆盖开头 / 中段 / 结尾，而不是只围绕前几章
更严格的 smart_ppt 约束
- 明确要求输出
18-22段 - 中文场景下要求更高的对话密度（至少约
3200中文字符，推荐更高） - 明确要求脚本覆盖多个章节 / 主题 / 对象，而不是只讲第一个案例
- 明确要求输出
硬校验 + 自动重试
- 生成后做程序化质量闸门：
- 段数是否在
18-22 - 对话总长度是否达标
- 预估时长是否至少约
10 分钟 - 是否存在过多过短 segment
- 段数是否在
- 不达标则直接判失败，交由脚本生成重试逻辑继续尝试
- 生成后做程序化质量闸门：
Show full SKILL.md (198 more words)Show less
验证结果（真实案例）
在《十件古物中的丝路文明史》样本上：
- 修复前：
13段，约6分39秒 - 修复后：
18段，约14分10秒
因此，当用户反馈“播客太短”时，优先检查是否走到了上述新逻辑；如果没有，先同步代码或重建产物，再重新运行。
已知问题与排查
首屏缺少书籍封面（local 版常见）
如果用户反馈：
- 本地版
final_podcast.mp4第一页右侧没有封面 - 但另一个实现路径同一本书第一页有封面
优先按下面顺序排查：
- 检查
metadata/book.json是否存在coverImageBase64- 如果存在，说明 EPUB 解析阶段已经成功提取封面，问题不在 parser。
- 检查
smart_slides_html/000.html- 搜索是否有
<img class="book-cover" ...> - 如果 HTML 里有
<img src="data:image/...;base64,...">，但最终 PNG / MP4 里看不到封面，说明问题出在 HTML -> Puppeteer 渲染链路。
- 搜索是否有
经验结论
在当前这套 local 管线里：
- 直接把超长 base64 data URI 塞进第一页
<img src>不够稳 - 可能出现：
- LLM 生成的 HTML 里明明有
<img> - 但 Puppeteer
page.setContent()后，最终 DOM/截图里封面消失
- LLM 生成的 HTML 里明明有
这会导致：
smart_slides_html/000.html看起来有封面代码smart_slides/000.png和最终mp4却没有封面
推荐修法
把 local 管线进一步稳固：
- 不要直接把
coverImageBase64传给第一页 prompt - 先把封面落成一个可访问资源，再传 URL
推荐优先级：
- 最稳：启动一个本地 HTTP 可访问地址，再传
http://.../cover.jpg - 若项目允许外部存储：上传到对象存储/云存储，传公开 URL
- 不推荐继续直接传超长
data:image/...;base64,...
调试提示
若要快速确认是不是这个问题：
- 用视觉或直接检查
smart_slides/000.png，确认右侧是否空白 - 再检查
smart_slides_html/000.html是否仍然包含<img> - 如果 HTML 有
<img>、最终图片无封面，基本就能锁定为 local 首屏封面资源引用方式不对
播客时长明显偏短（例如只有 6-8 分钟）
如果用户反馈：
- 一本正常长度的书只生成了很短的播客
- 预期应该在 10-15 分钟甚至更长
- 怀疑不同运行路径逻辑不一致
优先检查以下几点：
metadata/script.json的段数与总文本量- 当前经验：如果只有
12-13段、总文本很短（例如 2000 多中文字符），最终时长通常会落到 6-8 分钟
- 当前经验：如果只有
src/services/scriptService.ts的真实验收逻辑- prompt 虽然要求 15 分钟 / 4500 words / 18-22 segments
- 但某些模型分支若只做极弱校验，13 段短文本也可能被直接放行
- 输入给脚本生成模型的正文是否被截断
- 如果只把正文前
200000字符送入模型，长书就容易只覆盖前半本内容，覆盖度和时长都会受影响
- 如果只把正文前
对这个问题的经验结论
当用户说“播客应该至少 10 分钟，为什么这么短”时，优先怀疑：
- 脚本生成约束只写在 prompt 里，没有代码级强验收
- 长书输入被前 200k 字符截断，导致覆盖范围不足
而不是优先怀疑：
- ffmpeg 合成
- TTS 合成
- 封面页逻辑
建议修法
- 在脚本生成后增加硬校验：
- 段数必须在
18-22 - 总文本长度达到阈值
- 预估总时长达到阈值（例如至少 10 分钟）
- 段数必须在
- 若不满足，自动重试或切更强模型，而不是直接进入 TTS
- 不要只使用前 200k 字符；长书应改为：
- 章节摘要后再生成，或
- 从全书多段采样，避免内容只集中在前半本
自然语言触发建议
当用户说：
- “把这个 EPUB 做成带 Smart Slide 的视频播客”
- “生成双人音频 + 最终 mp4”
- “本地跑 epub2podcast，不要依赖 Supabase”
优先使用本 skill。
© dracohu2025-cloud, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
SKILL.md and 52 other files (scripts, assets) in Ark Agent Plan Version/epub2podcast of dracohu2025-cloud/draco-skills-collection.
- SKILL.md
- .env.example
- .gitignore
- ARK-PLAN-INTEGRATION.md
- CHANGELOG.md
- GITHUB_RELEASE_v0.1.0.md
- LICENSE
- PUBLISHING.md
- README.md
- RELEASE.md
- assets/example-slide-card-layout.png
- assets/example-slide-center-layout.png
- assets/example-slide-cover.png
- assets/example-slide-infographic.png
- assets/example-slide-list-layout.png
- assets/example-slide-split-layout.png
- docs/epub-namespace-compatibility.md
- examples/env-minimal-example.md
- … and 35 more
Open the folder on GitHubat commit 26e8975
Compare with similar skills
Epub2podcast Ark Plan next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Epub2podcast Ark Plan this skilldracohu2025-cloud/draco-skills-collection | 227 | — | ~1.8k | Automated safety check: Pass | MIT | |
| Openrouter Text2videoQinghongLin/data2story-skill | 155 | — | ~490 | Automated safety check: Pass | MIT | |
| Super Video MakerBomx/super-video-maker-skill | 310 | — | ~11k | Automated safety check: Notes | None | |
| Seedance Faceless Channelrediumvex/ai-video-generator-claude | 409 | — | ~4.4k | Automated safety check: Pass | MIT | |
| Fal AI Mediaaffaan-m/ECC | 277k | 4 repos | ~1.9k | Automated safety check: Pass | MIT | |
| Voice Realismnestyme/awesome-prompts | 151 | — | ~2.3k | Automated safety check: Pass | None |
Similar skills
Super Video Maker
Bomx/super-video-maker-skill
End-to-end AI video production skill for agentic frameworks.
Seedance Faceless Channel
rediumvex/ai-video-generator-claude
Generate faceless content video prompts for Seedance 2.0 on Higgsfield.
Fal AI Media
affaan-m/ECC
Unified media generation via fal.ai MCP — image, video, and audio.
Voice Realism
nestyme/awesome-prompts
Rewrite AI video / text-to-speech prompts so the generated VOICE sounds like a real human, not a robot.
Higgsfield Audio
OSideMedia/higgsfield-ai-prompt-skill
A skill your agent uses when the user asks about audio in Higgsfield videos, needs to add dialogue or lip-sync, wants sound effects or ambient sound in generated video, asks about music or BGM in…
More from dracohu2025-cloud/draco-skills-collection
All 27 skills in this repoAI News Bitable Archive Dingtalk
dracohu2025-cloud/draco-skills-collection
A skill your agent uses when parsing a DingTalk daily news document and syncing title, date, Top 3, summary, conclusion, document link, and status into a DingTalk multidimensional table.
Feishu Seedance Video Pipeline
dracohu2025-cloud/draco-skills-collection
A skill your agent uses when running a Feishu/Lark Base-centered Seedance video production pipeline: inspect/backfill the Base row, create/reference assets, build Row-24-style Chinese Seedance…
Motion Canvas
dracohu2025-cloud/draco-skills-collection
Production pipeline for Motion Canvas — TypeScript-based programmatic vector animation with real-time preview.
News Aggregator Skill
dracohu2025-cloud/draco-skills-collection
A skill your agent uses when collecting public news candidates from Hacker News, GitHub Trending, Hugging Face papers, and other web sources for briefings and daily reports.
Open Design To Open Slide
dracohu2025-cloud/draco-skills-collection
A skill your agent uses when mining Open Design visual systems and converting them into Open Slide React template kits or standalone 20-page template albums, with build, deployment, screenshot QA…
Daily AI Agent Aigc Top News Dingtalk
dracohu2025-cloud/draco-skills-collection
A skill your agent uses when generating a daily 24h AI / Agent / AIGC top-news briefing, publishing it as a DingTalk document, validating it, and optionally archiving it to a DingTalk…
Related
Works with
Categories
Questions about Epub2podcast Ark Plan
What does Epub2podcast Ark Plan do?
【Ark Agent Plan 专用版本】EPUB 转双人中文播客视频流水线：使用火山引擎 TTS（与 Seedream/Seedance 共享技术栈），Smart Slide + 双人音频 + 最终 MP4 视频，无需额外 Google/OpenRouter API Key。. Epub2podcast Ark Plan is an agent skill from dracohu2025-cloud/draco-skills-collection.
When should I use Epub2podcast Ark Plan?
Epub2podcast Ark Plan fits situations like: tasks that involve Slides and decks; tasks that involve Text to speech and voice; tasks that involve AI video generation.
How do I install Epub2podcast Ark Plan in Claude Code?
Run `npx skills add dracohu2025-cloud/draco-skills-collection --skill epub2podcast-ark-plan -a claude-code`. Or copy the skill folder (Ark Agent Plan Version/epub2podcast in dracohu2025-cloud/draco-skills-collection) into .claude/skills/epub2podcast-ark-plan in your project. Claude Code loads it when a task matches its description.
How do I install Epub2podcast Ark Plan in Codex?
Run `npx skills add dracohu2025-cloud/draco-skills-collection --skill epub2podcast-ark-plan -a codex`. Or copy the skill folder (Ark Agent Plan Version/epub2podcast in dracohu2025-cloud/draco-skills-collection) into .agents/skills/epub2podcast-ark-plan in your project. Codex loads it when a task matches its description.
Can I use Epub2podcast Ark Plan in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add dracohu2025-cloud/draco-skills-collection --skill epub2podcast-ark-plan -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/epub2podcast-ark-plan, .gemini/skills/epub2podcast-ark-plan, .github/skills/epub2podcast-ark-plan and .opencode/skills/epub2podcast-ark-plan in your project.
What does Epub2podcast Ark Plan need to run?
SKILL.md names no scripts, command-line tools or credentials: Epub2podcast Ark Plan is instructions for the agent only. Our summary lists: Node.js.
Does Epub2podcast Ark Plan access the network?
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Is Epub2podcast Ark Plan safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.
What licence does Epub2podcast Ark Plan use?
Epub2podcast Ark Plan is published under the MIT licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Epub2podcast Ark Plan use?
About 1.8k tokens (SKILL.md is roughly 7.1k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to Epub2podcast Ark Plan?
Skills that share tags, products or a category with Epub2podcast Ark Plan: Openrouter Text2video (QinghongLin/data2story-skill, 155 stars), Super Video Maker (Bomx/super-video-maker-skill, 310 stars), Seedance Faceless Channel (rediumvex/ai-video-generator-claude, 409 stars) and Fal AI Media (affaan-m/ECC, 277k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Epub2podcast Ark Plan?
dracohu2025-cloud (a GitHub user) maintains it in dracohu2025-cloud/draco-skills-collection, which has 227 GitHub stars. The repository holds 27 skills in this directory. The repository was last updated on September 17, 2026.
Source: dracohu2025-cloud/draco-skills-collection on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.