What makes Book Video Generator En notable?

2.8K downloads. Trust evidence available

How should Book Video Generator En 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.

Claim this agent

agentCLAWHUBUnverified

Book Video Generator En

Generates a 3-minute English video summarizing any book by creating script, storyboard, AI illustrations, TTS narration, subtitles, and final MP4 automatically.

OpenClaw

View on ClawHub Homepage

Rank

Safety

Downloads

2.8k

Updated

Oct 9, 2026

Version

0.1.0

Source

CLAWHUB

About

What it does, and when to use it.

Capability contract not published. No trust telemetry is available yet. 2.8K 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: 2.8K downloadsadoption · observed Oct 9, 2026
Latest release: 0.1.0release · observed Jul 30, 2026
Handshake status: UNKNOWNsecurity

Install and run

Setup complexity: low.

clawhub skill install s17a48tchm7k3vgry0mm17137n83hnzn:book-video-generator-en

Install using `clawhub skill install s17a48tchm7k3vgry0mm17137n83hnzn:book-video-generator-en` in an isolated environment before connecting it to live workloads.
No published capability contract is available yet, so validate auth and request/response behavior manually.
Review the upstream CLAWHUB listing at https://clawhub.ai/chenjun198711/book-video-generator-en before using production credentials.

Contract: missing

curl -s "https://www.xpersona.co/api/v1/agents/clawhub-chenjun198711-book-video-generator-en/snapshot"

Documentation

CLAWHUB

92,438 characters of source documentation, loaded on request.

Extracted files

5 files captured from the source.

SKILL.md

---
name: book-video-generator-en
slug: book-video-generator-en
version: 1.0.0
displayName: 三分钟精读一本书英文版
description: English 3-minute book digest video generator. Input a book title + author, one-click generate a 3-minute book review video (review script → storyboard → AI illustrations → English TTS narration → subtitles → final MP4). Trigger words: book video, 3 minute book summary, read a book in 3 minutes, book digest, make a book video. Cross-platform compatible with WorkBuddy / OpenClaw / Codex CLI / TRAE Work.
---

# 3-Minute Book Digest — English Version

## Overview

Automatically turn any book into a 3-minute explainer video: from writing the
review script, splitting it into storyboards, AI illustration, English TTS
narration, to subtitle compositing — fully automated.

Derived from the Coze workflow "Pipadushu_video_1". This Skill follows the
[Agent Skills open standard](https://agentskills.io) and is cross-platform
compatible with WorkBuddy, OpenClaw, Codex CLI, and TRAE Work.

It replaces Coze plugins with local open-source tools: 剪映小助手 (Jianying
assistant) → ffmpeg, Coze image generation → multi-model image generation
(default ImageGen + alternatives Volcano Seedream / Gemini / Agnes), Coze TTS →
Volcano Engine TTS (default) / edge-tts (fallback). All script, narration,
on-screen text, and prompts are **fully in English**.

## Platform Tool Mapping

This Skill's workflow involves 3 platform-related tools. Pick the matching tool
for the platform you are running on.

### Web Search (Stage 1 — search for book info)

| Platform | Tool | Notes |
|----------|------|-------|
| WorkBuddy | `WebSearch` | Built-in tool, call directly |
| OpenClaw | built-in web search | Auto-available |
| Codex CLI | `shell: curl` or search MCP | Use shell commands or install a search MCP |
| TRAE Work | built-in web search | Auto-available |

### Image Generation (Stage 4a — storyboard illustrations)

Provides **1 default + 3 alternatives**. Switch via the `IMAGE_API` env var:

| Plan | Tool | Model | Env var | Notes |
|------|------|-------|---------|-------|
| 🏠 **Default** | `ImageGen` | Tencent Hunyuan (WorkBuddy built-in) | none | Call `DeferExecuteTool` directly in WorkBuddy |
| 🏔️ Alt | `volcengine` | Volcano Seedream 5.0 lite (ByteDance) | `ARK_API_KEY` (recommended) or `VOLCENGINE_AK` + `VOLCENGINE_SK` | Original Coze image model; best for flat Chinese/English style, supports watermark removal |
| 🤖 Alt | `gemini` | Google Gemini 3 Pro Image | `GEMINI_API_KEY` | Rich detail, strong semantic understanding |
| ✨ Alt | `agnes` | Agnes AI (completely free) | `AGNES_API_KEY` | Free registration, OpenAI-compatible API |

**Switching**:
- **WorkBuddy**: uses `ImageGen` by default. To switch, set `IMAGE_API=volcengine|gemini|agnes`, the script auto-calls `scripts/generate_image.py`.
- **CLI platforms** (Codex CLI / OpenClaw): run `scripts/generate_image.py --api <plan>` directly.

> On every platform, the image prompt uses the `desc_promopt` field from th

assets/README.md

# 素材文件说明

本目录用于存放视频合成的可选音频素材。**这些文件是可选的**——如果缺失，视频仍可正常生成，只是没有背景音乐和转场音效。

## 所需文件

| 文件名 | 用途 | 大小 | 必需性 |
|--------|------|------|--------|
| `bgm_reading.mp3` | 背景音乐（全程循环，音量0.15） | ~9MB | 可选 |
| `transition_page_flip.mp3` | 转场音效（翻页声，每3个分镜触发） | ~3KB | 可选 |

## 获取方式

### 方式1：自行下载免费素材

- **BGM**：从 [Pixabay Music](https://pixabay.com/music/) 或 [Free Music Archive](https://freemusicarchive.org/) 下载轻柔的阅读背景音乐，重命名为 `bgm_reading.mp3`
- **翻页音效**：从 [Pixabay Sound Effects](https://pixabay.com/sound-effects/) 搜索 "page flip" 或 "page turn"，下载后重命名为 `transition_page_flip.mp3`

### 方式2：用 ffmpeg 生成简单音效

```bash
# 生成一个简单的翻页音效（白噪声+衰减）
ffmpeg -f lavfi -i "anoisesrc=d=0.15:c=pink:a=0.5" -af "afade=t=in:st=0:d=0.02,afade=t=out:st=0.1:d=0.05" assets/transition_page_flip.mp3
```

### 方式3：从 GitHub 仓库获取

如果本技能有对应的 GitHub 仓库，可以从仓库的 `assets/` 目录下载这些文件。

## 代码处理逻辑

`compose_video.py` 中的 `_find_asset()` 函数会按以下顺序查找：
1. 脚本同级 `assets/` 目录
2. 脚本父级 `assets/` 目录（技能根目录）
3. 脚本同级目录

如果找不到文件，`mix_audio()` 函数会自动跳过混音步骤，直接输出仅含 TTS 旁白的视频。

README.md

# 3-Minute Book Digest (English Version)

An English fork of the **三分钟精读一本书** book-video generator. Given a book
title + author, it produces a ~3-minute book-explainer video entirely in English:
review script → storyboard → AI illustrations → English TTS narration → subtitles → MP4.

## What's different from the Chinese version

| Area | Chinese version | This version (`book-video-generator-en`) |
|------|-----------------|------------------------------------------|
| Review script / storyboard prompts | Chinese (`references/prompts.md`) | **English** |
| On-screen text (subtitles, chapter titles, cover) | Chinese | **English** |
| TTS narration | Chinese voices (`zh_female_zhixingnv…` / `zh-CN-XiaoxiaoNeural`) | **English voices** (`en_us_amy` / `en-US-AriaNeural`) |
| Cover brand text | "3 分钟精读一本书" | "3-MINUTE BOOK DIGEST" |
| Fonts | Microsoft YaHei / PingFang / Noto CJK | Arial / Helvetica / DejaVu Sans |
| Subtitle line length | ~16 chars/line | ~42 chars/line, word-boundary wrapping |
| Output file | `{book}_三分钟精读书.mp4` | `{book}_3min_digest.mp4` |

## Workflow

1. **Stage 1** — LLM writes a ~1000-word English review script (web-search backed).
2. **Stage 2** — LLM splits it into 8–50 storyboard shots (caption + visual + image prompt).
3. **Stage 3** — LLM derives 4 ≤6-word section titles for the progress bar.
4. **Stage 4** — generate illustrations (ImageGen / Volcano / Gemini / Agnes), English TTS audio, and the opening cover.
5. **Stage 5** — `compose_video.py` composites everything into the final MP4.

See `SKILL.md` for the full guide, and `references/CROSS_PLATFORM.md` for
install + tool-adaptation steps on OpenClaw, Codex CLI, TRAE Work, Claude Code, etc.

## Requirements

```bash
pip install edge-tts imageio-ffmpeg pillow
```

- TTS: edge-tts works out of the box (no key). Set `VOLC_TTS_API_KEY` to use Volcano Engine TTS instead.
- Image generation: WorkBuddy uses the built-in `ImageGen` by default; CLI platforms use `scripts/generate_image.py` with `IMAGE_API`.
- Background music / transition SFX in `assets/` are optional.

## Troubleshooting

- **Stage 5 `compose_video.py` exits 1 with no traceback (silent kill).** The
  full ~3-minute 1080p re-encode is memory/CPU heavy and gets killed by the
  Bash sandbox. Run it with the sandbox bypassed (local ffmpeg only, no network
  needed): `python scripts/compose_video.py < segments.json` executed outside the
  sandbox. Or raise the sandbox resource limits before running.
- **Two image generations failed with `RequestLimitExceeded.JobNumExceed`.**
  The image provider caps concurrent jobs; just retry the failed shots after a
  moment. Order them into `scene_NNN.png` afterward.
- **TTS uses edge-tts (English) by default** because no `VOLC_TTS_API_KEY` is
  set. Set the key to switch to Volcano Engine TTS (`en_us_amy`).

## Files

- `SKILL.md` — skill spec and full workflow
- `references/prompts.md` — all LLM prompts (English)
- `references/CROSS_PLATFORM.md` — install/adapt for OpenClaw,

_meta.json

{
  "ownerId": "kn7eq2qd3rr9x7qsqf30dbt3b58120ra",
  "slug": "book-video-generator-en",
  "version": "0.1.0",
  "publishedAt": 1785380117397
}

references/CROSS_PLATFORM.md

# 跨平台适配指南（English Edition）

本文件说明 `book-video-generator-en`（三分钟精读一本书 · 英文版）技能在各 AI Agent 平台上的安装与工具适配方法。

技能遵循 [Agent Skills 开放标准](https://agentskills.io)，核心组件（`SKILL.md` 格式、LLM 提示词、Python 脚本）**跨平台通用**，仅需适配平台专有工具（主要是图像生成）。

---

## 平台兼容性总览

| 组件 | WorkBuddy | OpenClaw | Codex CLI | TRAE Work | Claude Code |
|------|-----------|----------|-----------|-----------|-------------|
| SKILL.md 格式 | 原生 | 兼容 | 兼容 | 兼容 | 兼容 |
| LLM 提示词（英文） | 直接用 | 直接用 | 直接用 | 直接用 | 直接用 |
| Python 脚本 | 直接用 | 直接用 | 直接用 | 直接用 | 直接用 |
| 联网搜索 | WebSearch | 内置 | Shell/MCP | 内置 | 内置 |
| 图像生成 | ImageGen（内置） | 插件 / generate_image.py | generate_image.py | MCP / generate_image.py | 内置 / generate_image.py |
| 英文 TTS | edge-tts（默认） | edge-tts | edge-tts | edge-tts | edge-tts |
| 技能目录 | ~/.workbuddy/skills/ | ~/.openclaw/skills/ | ~/.codex/skills/ | ~/.trae/skills/ | ~/.claude/skills/ |

> 核心脚本**无任何平台硬编码路径**，统一使用 `os.path.join` / `pathlib.Path` 与 `sys.executable`，在 Windows / macOS / Linux 均可直接运行。

---

## 1. WorkBuddy（当前平台）

无需额外配置，技能已安装。

- 联网搜索：内置 `WebSearch` 工具
- 图像生成：内置 `ImageGen` 延迟工具（通过 ToolSearch + DeferExecuteTool 调用，Tencent Hunyuan）
- 英文 TTS：`generate_audio.py` 默认 `en-US-AriaNeural`（edge-tts，免费、无需 Key）
- Python 运行：托管 Python `C:/Users/chenjun/.workbuddy/binaries/python/versions/3.13.12/python.exe`

---

## 2. OpenClaw

### 安装

```bash
# 方式一：直接复制
cp -r ~/.workbuddy/skills/book-video-generator-en ~/.openclaw/skills/

# 方式二：通过 ClawHub 安装（需先发布）
openclaw skills install book-video-generator-en

# 方式三：从 Git 仓库安装
openclaw skills install git:yourname/book-video-generator-en
```

### 工具适配

OpenClaw 支持在 `SKILL.md` frontmatter 中声明 `tools`。如需原生图像生成，可声明一个指向 `scripts/generate_image.py` 的 handler；否则 CLI 阶段直接调用该脚本即可。

联网搜索：OpenClaw 内置 web search，无需配置。

图像生成：

```bash
# 任选一种 API（需对应 Key）
export GEMINI_API_KEY="..."      # 或 AGNES_API_KEY / OPENAI_API_KEY / ARK_API_KEY
python3 scripts/generate_image.py --prompt "flat illustration ..." --output images/scene_000.png --api gemini
# 批量（从 storyboard.json）
python3 scripts/generate_image.py --batch storyboard.json --output-dir images/ --api gemini
```

### 验证

```bash
openclaw skills verify book-video-generator-en
```

---

## 3. Codex CLI（OpenAI）

### 安装

```bash
# 1. 开启 Skills 功能（config.toml）
cat >> ~/.codex/config.toml << 'EOF'
[features]
skills = true
EOF

# 2. 复制技能目录
cp -r ~/.workbuddy/skills/book-video-generator-en ~/.codex/skills/

# 3. 重启 Codex CLI
# 4. 验证：在 Codex CLI 输入 /skills，确认 book-video-generator-en 出现
```

### 工具适配

**联网搜索**：Codex CLI 无内置搜索，两种方案：

方案 A — Shell 命令搜索（免安装）：
```bash
curl -s "https://www.google.com/search?q=book+title+author+summary" | python3 -c "..."
```
方案 B — 安装搜索 MCP 插件。

**图像生成**：Codex CLI 无内置图像生成，使用 `scripts/generate_image.py`（见上方 OpenClaw 示例）。`IMAGE_API` 环境变量可设默认 API（默认 `gemini`）。

**英文 TTS**：`generate_audio.py` 默认走 edge-tts，免费且无需 Key，联网即用。

### 注意事项

- Codex CLI 的 `SKILL.md` frontmatter 支持 `metadata.short-description`
- 技能也可放在项目级 `.codex/skills/` 或仓库根 `.agents/skills/`
- 渐进式披露：启动时仅加载 name + description

---

## 4. TRAE

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.

MCPOPENCLAW

Github ReposUpdated 6mo 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 7mo agoRank 70

CopilotKit

The Frontend for Agents & Generative UI. React + Angular

OPENCLAW

Machine-readable data

The same record, as JSON, for agents and crawlers.

{
  "facts": [
    {
      "factKey": "vendor",
      "category": "vendor",
      "label": "Vendor",
      "value": "Clawhub",
      "href": "https://clawhub.ai/chenjun198711/skills/book-video-generator-en",
      "sourceUrl": "https://clawhub.ai/chenjun198711/skills/book-video-generator-en",
      "sourceType": "profile",
      "confidence": "medium",
      "observedAt": "2026-10-09T11:38:35.164Z",
      "isPublic": true
    },
    {
      "factKey": "protocols",
      "category": "compatibility",
      "label": "Protocol compatibility",
      "value": "OpenClaw",
      "href": "https://www.xpersona.co/api/v1/agents/clawhub-chenjun198711-book-video-generator-en/contract",
      "sourceUrl": "https://www.xpersona.co/api/v1/agents/clawhub-chenjun198711-book-video-generator-en/contract",
      "sourceType": "contract",
      "confidence": "medium",
      "observedAt": "2026-10-09T11:38:35.164Z",
      "isPublic": true
    },
    {
      "factKey": "traction",
      "category": "adoption",
      "label": "Adoption signal",
      "value": "2.8K downloads",
      "href": "https://clawhub.ai/chenjun198711/book-video-generator-en",
      "sourceUrl": "https://clawhub.ai/chenjun198711/book-video-generator-en",
      "sourceType": "profile",
      "confidence": "medium",
      "observedAt": "2026-10-09T11:38:35.164Z",
      "isPublic": true
    },
    {
      "factKey": "latest_release",
      "category": "release",
      "label": "Latest release",
      "value": "0.1.0",
      "href": "https://clawhub.ai/chenjun198711/book-video-generator-en",
      "sourceUrl": "https://clawhub.ai/chenjun198711/book-video-generator-en",
      "sourceType": "release",
      "confidence": "medium",
      "observedAt": "2026-07-30T02:55:17.397Z",
      "isPublic": true
    },
    {
      "factKey": "handshake_status",
      "category": "security",
      "label": "Handshake status",
      "value": "UNKNOWN",
      "href": "https://www.xpersona.co/api/v1/agents/clawhub-chenjun198711-book-video-generator-en/trust",
      "sourceUrl": "https://www.xpersona.co/api/v1/agents/clawhub-chenjun198711-book-video-generator-en/trust",
      "sourceType": "trust",
      "confidence": "medium",
      "observedAt": null,
      "isPublic": true
    }
  ],
  "events": [
    {
      "eventType": "release",
      "title": "Release 0.1.0",
      "description": "- Initial public release of the English 3-minute book digest video generator. - Automatically generates a 3-minute book review video from book title and author: script, storyboard, AI illustrations, English TTS narration, subtitles, and final MP4. - Supports multiple platforms and AI/image generation models; switchable via environment variables. - Includes default and alternative engines for image generation (Tencent Hunyuan, Volcano Seedream, Google Gemini, Agnes) and TTS (Volcano Engine, edge-tts). - Fully automated workflow with clear environment setup and cross-platform compatibility (WorkBuddy, OpenClaw, Codex CLI, TRAE Work).",
      "href": "https://clawhub.ai/chenjun198711/book-video-generator-en",
      "sourceUrl": "https://clawhub.ai/chenjun198711/book-video-generator-en",
      "sourceType": "release",
      "confidence": "medium",
      "observedAt": "2026-07-30T02:55:17.397Z",
      "isPublic": true
    }
  ]
}

Record generated Oct 9, 2026.

About

Avoid when

Public facts

Install and run

Documentation

Extracted files

SKILL.md

assets/README.md

README.md

_meta.json

references/CROSS_PLATFORM.md

Related agents

activepieces

cherry-studio

AionUi

CopilotKit

Machine-readable data