可独立运行的 GPT-Image 增强版 EPUB2Podcast：在本地把 EPUB 转成双人中文音频、GPT-Image/Smart Slide 视觉页、最终 MP4，并生成 YouTube 发布素材。
$ npx skills add dracohu2025-cloud/draco-skills-collection --skill epub2podcast-gpt-image -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install dracohu2025-cloud/draco-skills-collection epub2podcast-gpt-image --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/epub2podcast-gpt-image .claude/skills/epub2podcast-gpt-image && 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-gpt-image" agent skill from https://github.com/dracohu2025-cloud/draco-skills-collection/tree/main/epub2podcast-gpt-image into .claude/skills/epub2podcast-gpt-image/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "epub2podcast-gpt-image", 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/epub2podcast-gpt-imageType 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-gpt-image -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install dracohu2025-cloud/draco-skills-collection epub2podcast-gpt-image --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/epub2podcast-gpt-image .agents/skills/epub2podcast-gpt-image && 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-gpt-image" agent skill from https://github.com/dracohu2025-cloud/draco-skills-collection/tree/main/epub2podcast-gpt-image into .agents/skills/epub2podcast-gpt-image/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "epub2podcast-gpt-image", 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-gpt-image -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install dracohu2025-cloud/draco-skills-collection epub2podcast-gpt-image --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/epub2podcast-gpt-image .cursor/skills/epub2podcast-gpt-image && 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-gpt-image" agent skill from https://github.com/dracohu2025-cloud/draco-skills-collection/tree/main/epub2podcast-gpt-image into .cursor/skills/epub2podcast-gpt-image/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "epub2podcast-gpt-image", 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 epub2podcast-gpt-image--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-gpt-image -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install dracohu2025-cloud/draco-skills-collection epub2podcast-gpt-image --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/epub2podcast-gpt-image .gemini/skills/epub2podcast-gpt-image && 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-gpt-image" agent skill from https://github.com/dracohu2025-cloud/draco-skills-collection/tree/main/epub2podcast-gpt-image into .gemini/skills/epub2podcast-gpt-image/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "epub2podcast-gpt-image", 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-gpt-imageInstalls 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-gpt-image -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/epub2podcast-gpt-image .github/skills/epub2podcast-gpt-image && 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-gpt-image" agent skill from https://github.com/dracohu2025-cloud/draco-skills-collection/tree/main/epub2podcast-gpt-image into .github/skills/epub2podcast-gpt-image/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "epub2podcast-gpt-image", 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-gpt-image -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-gpt-image --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/epub2podcast-gpt-image .opencode/skills/epub2podcast-gpt-image && 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-gpt-image" agent skill from https://github.com/dracohu2025-cloud/draco-skills-collection/tree/main/epub2podcast-gpt-image into .opencode/skills/epub2podcast-gpt-image/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "epub2podcast-gpt-image", 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.
epub2podcast-gpt-image可独立运行的 GPT-Image 增强版 EPUB2Podcast：在本地把 EPUB 转成双人中文音频、GPT-Image/Smart Slide 视觉页、最终 MP4，并生成 YouTube 发布素材。
Epub2podcast Gpt Image is an agent skill from dracohu2025-cloud/draco-skills-collection. 可独立运行的 GPT-Image 增强版 EPUB2Podcast：在本地把 EPUB 转成双人中文音频、GPT-Image/Smart Slide 视觉页、最终 MP4，并生成 YouTube 发布素材。
Its SKILL.md is about 1.9k tokens, which your agent loads only when the skill is triggered. The skill folder holds 87 other files, including scripts, reference files and assets (for example `CHANGELOG.md`, `GITHUB_RELEASE_v0.1.0.md` and `PUBLISHING.md`).
It sits in Media & Creative, covering Image generation and Slides and decks. It works with YouTube and DeepSeek. The licence is MIT.
7 steps, taken from the step headings in SKILL.md.
Read from SKILL.md and the folder at commit 26e8975. It shows what the files ask for, not the result of running them.
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.
Ships 1 file in scripts/, which the agent can run.
Shell commands in SKILL.md call:
nodepython3bashFrom the folder's file list and the shell code blocks in SKILL.md.
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Epub2podcast Gpt Image loads about 1.9k tokens when it runs, and up to ~8.3k if it reads all its reference files. Until then it costs about 32 tokens; SKILL.md has 548 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.
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.
The full file from dracohu2025-cloud/draco-skills-collection at commit 26e8975, republished under its MIT licence (© dracohu2025-cloud). 548 words, ~1,913 tokens.
.claude/skills/epub2podcast-gpt-image/SKILL.md (or your agent's skills folder). This skill also uses 84 other files; get the full folder from GitHub.这个 skill 对应的是 GPT-Image 增强 standalone 版本 的 epub2podcast 管线。旧的 Smart Slide 基础公开版保留在 epub2podcast/。用户只需要下载当前项目本身，就可以把 EPUB 转成：
full_podcast.mp3final_podcast.mp4EPUB2PODCAST_PROJECT_ROOT）language=ChineseimageStyle.preset=smart_pptimageStyle.colorTheme=gq_fashionimageStyle.pptModel=deepseek/deepseek-v4-flashapiProvider=openroutertextModel=deepseek-v4-flashvolcenginesmart_ppt / antv_infographic 模式，脚本生成现在会同时启用：当前机器需要：
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。
主命令：
node dist/cli/run.js 或 bash scripts/epub2podcast_local_run.shnode dist/cli/generate-gpt-images.js（对已有 delivery 生成 GPT-Image 视觉页，可选重合成 mp4）node dist/cli/regenerate-slide.js（只重生某一页，可选自动重合成 mp4）node dist/cli/compress-video.js（把最终 mp4 压到更适合上传的体积）python3 scripts/publish_podcast_site.py（生成 YouTube 发布交接页）node dist/cli/run.js --epub ./book.epubnode dist/cli/run.js --epub ./book.epub --output-dir ./deliveriesnode dist/cli/run.js \
--epub ./book.epub \
--output-dir ./deliveries \
--color-theme gq_fashion \
--ppt-model deepseek/deepseek-v4-flash \
--text-model deepseek-v4-flashnode dist/cli/regenerate-slide.js \
--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--recompose 时，只更新指定页的 PNG 和 HTMLnode dist/cli/compress-video.js \
--input /path/to/final_podcast.mp4 \
--output /path/to/final_podcast_feishu.mp4node dist/cli/run.js \
--epub ./book.epub \
--output-dir ./deliveries \
--visual-mode gpt-image-slide \
--image-density segment \
--resolution 1440x1080如果已有 delivery，只想补生或重生 GPT-Image 视觉页：
node dist/cli/generate-gpt-images.js \
--delivery-dir /path/to/delivery \
--recomposemetadata/marketing.json 会包含 title、description、thumbnailPrompt。如果 delivery 目录里已有 youtube_thumbnail.png/.jpg，发布脚本会优先原样使用该封面，不裁切、不补边。
python3 scripts/publish_podcast_site.py \
--delivery-dir /path/to/delivery \
--output-root ./published-podcasts默认压缩策略：
libx264-preset medium-crf 27-maxrate 2200k -bufsize 4400kaac -b:a 96k适用场景：
lark-cli drive +upload 因 20MB 限制无法上传最终 mp4 时*_feishu.mp4，再上传到用户指定的飞书云盘文件夹输出目录通常包含：
source/audio_segments/smart_slides/smart_slides_html/gpt_image_slides/（使用 GPT-Image 模式时）gpt_image_raw/（使用 GPT-Image 模式时）metadata/book.jsonmetadata/script.jsonmetadata/marketing.json（YouTube 标题、description、缩略图 prompt）full_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）。
metadata/marketing.json.description。[MM:SS] Topic / MM:SS 主题；不要把对应台词直接贴上去。visualPrompt 的标题、字幕、关键句或结构化 【标题】... 中提取，缺失时再生成中性的章节标签。细节见：references/youtube-marketing-description.md。
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推荐使用持久目录，例如：
./deliveries/epub2podcast-locallark-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：
mp3 / cover / 首图 / manifest / metadata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
更严格的 smart_ppt 约束
18-22 段3200 中文字符，推荐更高）硬校验 + 自动重试
18-2210 分钟在《十件古物中的丝路文明史》样本上：
13 段，约 6分39秒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。
如果用户反馈：
final_podcast.mp4 第一页右侧没有封面优先按下面顺序排查：
metadata/book.json 是否存在 coverImageBase64smart_slides_html/000.html<img class="book-cover" ...><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。在当前这套 local 管线里：
<img src> 不够稳<img>page.setContent() 后，最终 DOM/截图里封面消失这会导致：
smart_slides_html/000.html 看起来有封面代码smart_slides/000.png 和最终 mp4 却没有封面把 local 管线进一步稳固：
coverImageBase64 传给第一页 prompt推荐优先级：
http://.../cover.jpgdata:image/...;base64,...若要快速确认是不是这个问题：
smart_slides/000.png，确认右侧是否空白smart_slides_html/000.html 是否仍然包含 <img><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如果用户反馈：
优先检查以下几点：
metadata/script.json 的段数与总文本量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src/services/scriptService.ts 的真实验收逻辑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当用户说“播客应该至少 10 分钟，为什么这么短”时，优先怀疑：
而不是优先怀疑：
18-22当用户说：
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
SKILL.md and 84 other files (scripts, references, assets) in epub2podcast-gpt-image of dracohu2025-cloud/draco-skills-collection.
Open the folder on GitHubat commit 26e8975
Epub2podcast Gpt Image 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 Gpt Image this skilldracohu2025-cloud/draco-skills-collection | 227 | — | ~1.9k | Automated safety check: Pass | MIT | |
| Orange Line Illustrationorange2ai/orange-line-illustration | 441 | — | ~2.5k | Automated safety check: Pass | Proprietary | |
| CarouselsTheCraigHewitt/skills | 159 | — | ~2.3k | Automated safety check: Pass | MIT | |
| Gpt Image Slide Renderhumantonylee/future-slide | 150 | — | ~966 | Automated safety check: Pass | Apache-2.0 | |
| Canva Designerasgeirtj/system_prompts_leaks | 69k | — | ~2.1k | Automated safety check: Pass | CC0-1.0 | |
| Guizang Material Illustrationop7418/guizang-material-illustration | 1.2k | — | ~1.6k | Automated safety check: Pass | None |
orange2ai/orange-line-illustration
Generate New Yorker-style minimalist editorial illustrations — thin black ink lines on white, vast negative space, a single orange accent (F97316) — for articles, principles, covers, concept…
TheCraigHewitt/skills
Turns a piece of Craig's content (an email, a YouTube script, an essay, or pasted text) into a polished image carousel publishable to both LinkedIn and Instagram from one set of 1080x1350 slides.
humantonylee/future-slide
Render slide images sequentially from DESIGN.md and slide prompt JSON using Codex native image generation, saving each output into the workspace with page-number filenames.
asgeirtj/system_prompts_leaks
Creates and edits Canva designs, generates images and works with brand kits through the canva CLI and Canva's official MCP server, from decks to social posts.
op7418/guizang-material-illustration
Generate Guizang-style material illustrations, labeled explanatory visuals, material-styled chart illustrations, and data-first editorial images from articles, notes, product concepts, workplace…
kkoppenhaver/cc-nano-banana
REQUIRED for all image generation requests. An agent skill from kkoppenhaver/cc-nano-banana.
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.
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…
dracohu2025-cloud/draco-skills-collection
Production pipeline for Motion Canvas — TypeScript-based programmatic vector animation with real-time preview.
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.
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…
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…
Categories
可独立运行的 GPT-Image 增强版 EPUB2Podcast：在本地把 EPUB 转成双人中文音频、GPT-Image/Smart Slide 视觉页、最终 MP4，并生成 YouTube 发布素材。. Epub2podcast Gpt Image is an agent skill from dracohu2025-cloud/draco-skills-collection.
Epub2podcast Gpt Image fits situations like: tasks that involve Image generation; tasks that involve Slides and decks.
Run `npx skills add dracohu2025-cloud/draco-skills-collection --skill epub2podcast-gpt-image -a claude-code`. Or copy the skill folder (epub2podcast-gpt-image in dracohu2025-cloud/draco-skills-collection) into .claude/skills/epub2podcast-gpt-image in your project. Claude Code loads it when a task matches its description.
Run `npx skills add dracohu2025-cloud/draco-skills-collection --skill epub2podcast-gpt-image -a codex`. Or copy the skill folder (epub2podcast-gpt-image in dracohu2025-cloud/draco-skills-collection) into .agents/skills/epub2podcast-gpt-image in your project. Codex loads it when a task matches its description.
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-gpt-image -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-gpt-image, .gemini/skills/epub2podcast-gpt-image, .github/skills/epub2podcast-gpt-image and .opencode/skills/epub2podcast-gpt-image in your project.
Going by SKILL.md and its folder, Epub2podcast Gpt Image needs the command-line tools its instructions call (node, python3 and bash). Our summary lists: Python 3; Node.js.
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.
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.
Epub2podcast Gpt Image is published under the MIT licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.
About 1.9k tokens (SKILL.md is roughly 7.7k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 6.4k tokens, read only when the agent opens those files.
Skills that share tags, products or a category with Epub2podcast Gpt Image: Orange Line Illustration (orange2ai/orange-line-illustration, 441 stars), Carousels (TheCraigHewitt/skills, 159 stars), Gpt Image Slide Render (humantonylee/future-slide, 150 stars) and Canva Designer (asgeirtj/system_prompts_leaks, 69k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
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.
