← 返回 Skills 市场
emergencescience

Emergence Video Producer

作者 emergencescience · GitHub ↗ · v0.1.1 · MIT-0
cross-platform ⚠ suspicious
31
总下载
0
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install emergence-video-producer
功能描述
Automated video production pipeline for product demos and academic tutorials. Uses WebReel for browser recording, DashScope/Edge-TTS for narration, and FFmpe...
使用说明 (SKILL.md)

Skill: Emergence Video Producer 🎬

This skill transforms a Markdown "Video Script" into a polished tutorial video. It is designed for headless operation on cloud VMs, enabling agents to produce visual documentation autonomously.

1. Prerequisites

Ensure the following tools are in the path:

  • webreel (for browser recording)
  • ffmpeg (for assembly)
  • edge-tts or dashscope credentials (for narration)
  • Pillow (for frame extraction if WebP conversion is needed)

2. Interaction Model: The Interview

Unlike rigid CLIs, this skill starts with a Human-in-the-Loop Interview.

The Discovery Phase

The agent must proactively ask the following:

  1. Objective: "What is the primary goal of this video? (e.g., Feature Launch, Academic Summary, Onboarding)"
  2. Mode: "Should this be a Browser Walkthrough (WebReel) or a PPT-style Presentation (Slidev)?"
  3. Tone: "What is the desired persona? (e.g., Professional, Hype, Scientific)"
  4. Target URL/Content: "Which website are we recording, or what are the key slides?"

3. Workflow Phases

Phase 1: Ideation & Storyboarding

Based on the interview, the agent drafts a storyboard.md. This is a negotiated artifact.

  • DO NOT ask the human to write the Markdown.
  • DO ask the human to "Review and Approve" the draft.

Phase 2: Configuration & Asset Prep

Once approved, the agent automatically generates:

  1. For Browser Mode: A webreel.config.json with precise selectors and timings.
  2. For Slide Mode: A slides.md for Slidev rendering.
  3. Audio: Narration text synthesized into high-quality TTS.

Phase 3: Production (The Engine)

The agent executes the headless recording and assembly. It handles:

  • Browser automation (WebReel)
  • Slide rendering (Slidev)
  • Frame extraction and FFmpeg merging

Phase 4: Taste Gate & Distribution

The agent presents the video for final "Taste Gate" approval before publishing to ClawHub or social platforms.

4. Usage Example

# Generate a video for the current project
hermes run emergence-video-producer --script video-script.md --output tutorial.mp4

5. Development Notes

  • Framerate Sync: The assembly script automatically adjusts the framerate: FPS = TOTAL_FRAMES / AUDIO_DURATION.
  • Browser State: Ensure the product is accessible via URL or a local dev server before recording.
安全使用建议
Review before installing. Use a sandbox or clean project directory without unrelated .env secrets, install the required media/browser tools from trusted sources, use only scoped TTS credentials, and confirm the storyboard, target URL, generated config, and final video before publishing.
功能分析
Type: OpenClaw Skill Name: emergence-video-producer Version: 0.1.1 The skill bundle provides a legitimate automated video production pipeline using FFmpeg, Edge-TTS, and WebReel. The Python scripts (scripts/assemble_video.py and scripts/generate_audio.py) use safe subprocess execution (passing arguments as lists rather than shell strings) to handle media processing, and the instructions in SKILL.md are strictly aligned with the stated purpose of generating tutorials and demos without any evidence of malicious intent, prompt injection attacks, or data exfiltration.
能力评估
ℹ Purpose & Capability
The browser recording, narration, and FFmpeg assembly capabilities are coherent for an automated video-production skill, including final approval before publishing.
✓ Instruction Scope
The workflow includes a human interview, storyboard approval, and a final Taste Gate before distribution, which helps keep the automation user-directed.
ℹ Install Mechanism
There is no install spec and the registry declares no required binaries or env vars, even though the skill expects external tools and Python packages.
ℹ Credentials
Use of WebReel, Edge-TTS/DashScope, Pillow, ffmpeg, and ffprobe is purpose-aligned, but users should verify trusted installations and avoid sensitive recording targets.
⚠ Persistence & Privilege
scripts/generate_audio.py unconditionally calls load_dotenv(), which can load unrelated local .env secrets into the process and its child command despite no declared credential contract.
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 emergence-video-producer
  3. 安装完成后，直接呼叫该 Skill 的名称或使用 /emergence-video-producer 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
v0.1.1
Emergence Video Producer 0.1.1 - Introduced an automated pipeline that converts a Markdown "Video Script" into a polished tutorial video. - Human-in-the-loop interview process added for goal, mode, tone, and content discovery. - Workflow divided into ideation, configuration, production, and final approval phases. - Supports both browser walkthroughs (WebReel) and PPT-style presentations (Slidev). - Integrates narration (Edge-TTS or DashScope) and video assembly (FFmpeg). - Designed for headless operation on cloud VMs for autonomous agent use.
元数据
Slug emergence-video-producer
版本 0.1.1
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

Emergence Video Producer 是什么？

Automated video production pipeline for product demos and academic tutorials. Uses WebReel for browser recording, DashScope/Edge-TTS for narration, and FFmpe... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 31 次。

如何安装 Emergence Video Producer？

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

Emergence Video Producer 是免费的吗？

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

Emergence Video Producer 支持哪些平台？

Emergence Video Producer 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 Emergence Video Producer？

由 emergencescience（@emergencescience）开发并维护，当前版本 v0.1.1。

推荐 Skills
self-improving agent
Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Clau...
⬇ 463815 · by pskoett
Skill Vetter
Security-first skill vetting for AI agents. Use before installing any skill from ClawdHub, GitHub, or other sources. Checks for red flags, permission scope, and suspicious patterns.
⬇ 259802 · by spclaudehome
Polymarket
Query Polymarket prediction markets. Check odds, find trending markets, search events, track price movements.
⬇ 232503 · by joelchance
Self-Improving + Proactive Agent
Self-reflection + Self-criticism + Self-learning + Self-organizing memory. Agent evaluates its own work, catches mistakes, and improves permanently. Use when...
⬇ 200680 · by ivangdavila
Github
Interact with GitHub using the `gh` CLI. Use `gh issue`, `gh pr`, `gh run`, and `gh api` for issues, PRs, CI runs, and advanced queries.
⬇ 191345 · by steipete
ontology
Typed knowledge graph for structured agent memory and composable skills. Use when creating/querying entities (Person, Project, Task, Event, Document), linkin...
⬇ 190333 · by oswalpalash

💬 留言讨论