← 返回 Skills 市场
api00

PDF to Video

作者 api00 · GitHub ↗ · v1.0.0 · MIT-0
cross-platform ✓ 安全检测通过
33
总下载
0
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install revid-pdf-to-video
功能描述
Turn a PDF (whitepaper, ebook chapter, slide deck export, research paper) into a short summary video. Use when the source is a PDF URL or a PDF the agent can...
使用说明 (SKILL.md)

PDF → summary video

Take a PDF URL and produce a short summary video. Internally this routes through article-to-video once the PDF text has been extracted by Revid's scraper.

When to use this skill

  • Source is a public PDF URL (whitepaper, paper, ebook, slide export).
  • Goal is a 30–90 s summary, not a full reading.
  • For HTML articles use revid-article-to-short.
  • For local PDFs the agent must first upload to public storage (S3, Supabase Storage, etc.) so Revid can fetch it.

Inputs

Field Required Notes
url yes Public PDF URL (must be reachable, no auth)
aspectRatio no Default 9:16
targetDuration no Default 60 (s); raise to 90 s for dense papers

Step-by-step

  1. Confirm the URL ends in .pdf or returns Content-Type: application/pdf.
  2. Set source.scrapingPrompt to bias the summary toward what the user cares about ("Focus on the methodology section", "Focus on the executive summary", "Pull the 3 biggest takeaways").
  3. POST /render with the payload below.
  4. Poll /status.

API call template

POST /api/public/v3/render
Host: www.revid.ai
Content-Type: application/json
key: $REVID_API_KEY
{
  "workflow": "article-to-video",
  "source": {
    "url": "{PDF_URL}",
    "scrapingPrompt": "Extract the executive summary and the 3 biggest takeaways. Skip references and appendices."
  },
  "aspectRatio": "9:16",
  "voice":    { "enabled": true, "stability": 0.65, "speed": 0.95, "language": "en-US" },
  "captions": { "enabled": true, "position": "middle", "autoCrop": true },
  "music":    { "enabled": true, "syncWith": "beats" },
  "media": {
    "type": "stock-video",
    "density": "medium",
    "animation": "soft",
    "quality": "pro",
    "imageModel": "good",
    "videoModel": "pro"
  },
  "options": {
    "targetDuration": 60,
    "summarizationPreference": "summarize",
    "soundEffects": true,
    "hasToGenerateCover": true,
    "coverTextType": "title"
  },
  "render": { "resolution": "1080p", "frameRate": 30 }
}

Examples

Failure modes

Symptom Fix
scrape failed PDF behind auth or login wall. Re-host the PDF on public storage.
Summary skips the section the user cares about Tighten scrapingPrompt (be specific: section names, page ranges).
Visuals are abstract / off-topic PDFs rarely have crawlable hero images. Pre-render a few key figures as images and pass them in media.provided.
Voice rushes through technical terms Lower voice.speed to 0.9.

See also

安全使用建议
This skill sends PDFs (or a public URL) and requests that Revid process them; you must provide REVID_API_KEY. If your PDF is private or contains sensitive information, note the SKILL.md explicitly instructs re-hosting it on public storage so Revid can fetch it — that can expose content. Before installing: 1) confirm you trust https://www.revid.ai and review its privacy/retention policies; 2) avoid using production/confidential PDFs unless you control the storage and access; 3) use a scoped or disposable API key if possible and rotate keys after testing; 4) test with non-sensitive documents first to confirm costs and behavior; 5) if you do not want autonomous calls, restrict or disable autonomous invocation at the agent/platform level. Overall the skill is coherent with its purpose, but treat private content and API keys cautiously.
功能分析
Type: OpenClaw Skill Name: revid-pdf-to-video Version: 1.0.0 The skill is a legitimate integration with the Revid.ai service for converting PDF documents into summary videos. It uses standard API interaction patterns (POST requests and status polling) via the Revid.ai endpoint (www.revid.ai). The provided bash script (examples/run.sh) and JSON templates (examples/whitepaper.json) are consistent with the stated purpose and do not contain any evidence of data exfiltration, malicious execution, or harmful prompt injection.
能力标签
requires-sensitive-credentials
能力评估
Purpose & Capability
Name/description match the behavior: the SKILL.md and examples call Revid's public API (www.revid.ai) and require a REVID_API_KEY. No unrelated credentials, binaries, or surprising capabilities are requested.
Instruction Scope
Instructions stay focused on extracting PDF text and calling Revid's article-to-video workflow. One important operational note: local PDFs must be uploaded to public storage (S3, Supabase, etc.) so Revid can fetch them — this is a privacy/availability requirement, not hidden malicious behavior. The example scripts only POST to revid.ai and poll status; they do not read or send unrelated files or secrets.
Install Mechanism
No install spec (instruction-only) and included example scripts are small shell/json files. Nothing is downloaded from arbitrary URLs or written to disk beyond the provided examples.
Credentials
Only REVID_API_KEY is required (declared in SKILL.md metadata and used by examples). That single credential is proportionate to a service that requires API authentication; no other secrets are requested.
Persistence & Privilege
The skill does not request always:true, does not modify other skills, and is user-invocable. Default autonomous invocation is enabled (platform default) but not combined with other concerning flags.
如何使用
  1. 确保已安装 OpenClaw(本地或 Docker 部署)
  2. 在对话框中输入安装命令:/install revid-pdf-to-video
  3. 安装完成后,直接呼叫该 Skill 的名称或使用 /revid-pdf-to-video 触发
  4. 根据 Skill 的参数说明提供必要输入,即可获得结构化输出
版本历史
v1.0.0
Initial release of revid-pdf-to-video - Create short summary videos from public PDF URLs (whitepapers, research papers, slide decks, ebooks). - Supports custom prompts to focus summaries on user-specified sections. - Allows optional aspect ratio and video duration settings. - Outlines API usage and failure troubleshooting. - Must upload local PDFs to public storage for processing. - Linked to related skills for HTML articles and advanced media control.
元数据
Slug revid-pdf-to-video
版本 1.0.0
许可证 MIT-0
累计安装 0
当前安装数 0
历史版本数 1
常见问题

PDF to Video 是什么?

Turn a PDF (whitepaper, ebook chapter, slide deck export, research paper) into a short summary video. Use when the source is a PDF URL or a PDF the agent can... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 33 次。

如何安装 PDF to Video?

在 OpenClaw 或 Claude Code 对话框中运行命令「/install revid-pdf-to-video」即可一键安装,无需额外配置。

PDF to Video 是免费的吗?

是的,PDF to Video 完全免费,采用 MIT-0 许可证,可自由下载、安装和使用。

PDF to Video 支持哪些平台?

PDF to Video 跨平台运行,可在任意部署了 OpenClaw / Claude Code 的环境中使用(cross-platform)。

谁开发了 PDF to Video?

由 api00(@api00)开发并维护,当前版本 v1.0.0。

💬 留言讨论