← 返回 Skills 市场
zero2ai-hub

AI UGC Video Pipeline

作者 Zero2Ai · GitHub ↗ · v1.2.0
cross-platform ⚠ suspicious
341
总下载
0
收藏
2
当前安装
2
版本数
在 OpenClaw 中安装
/install skill-ugc-pipeline
功能描述
End-to-end AI UGC video pipeline. Product info → GPT-4o-mini script → ElevenLabs voiceover → Aurora talking head (fal-ai/creatify/aurora) → Kling 2.6 Pro pro...
安全使用建议
Do not install or supply API keys to this skill as-is. The SKILL.md expects npm/node scripts and a Python overlay but the package contains only the README — that is a coherence failure. Before proceeding, ask the publisher for the source repository or a packaged release that includes the referenced scripts and a verified install spec. If you must test it: (1) run in an isolated sandbox or VM, (2) use ephemeral or least-privilege API keys (scoped service accounts and low quotas), (3) inspect all scripts for unexpected network calls or filesystem access, and (4) confirm the meaning of the 'uv' binary and any cross-skill dependencies. If the author can't provide code or a trustworthy source URL/homepage, treat the skill as incomplete and avoid handing over real credentials.
功能分析
Type: OpenClaw Skill Name: skill-ugc-pipeline Version: 1.2.0 The skill bundle describes a legitimate end-to-end AI video generation pipeline utilizing GPT-4o, ElevenLabs, and fal.ai APIs. The documentation in SKILL.md and metadata in _meta.json outline a standard workflow for script generation, voiceover, and video post-processing using FFmpeg, with no evidence of malicious intent, data exfiltration, or prompt injection.
能力评估
Purpose & Capability
The described purpose (GPT → ElevenLabs → fal.ai Aurora/Kling → Whisper → ffmpeg) legitimately requires FAL_KEY, ELEVENLABS_API_KEY, OPENAI_API_KEY and binaries like node and ffmpeg; the SKILL.md lists those. However the registry metadata at the top of the submission indicates no required env vars or binaries — a direct inconsistency between what the skill claims to need and what the package declares. The stated purpose itself aligns with the APIs named, but the metadata/manifest mismatch is suspicious.
Instruction Scope
The runtime instructions tell the agent to run npm install and multiple node scripts (generate.js, broll.js, transcribe_captions.js) and a Python overlay.py, and to call external APIs (fal.ai, ElevenLabs, OpenAI). Those calls are expected for this pipeline. Crucially, the skill bundle contains only SKILL.md and no code files or scripts referenced by the instructions — so the instructions cannot be executed as-is from this package. The doc also references a binary named 'uv' (unclear meaning) and a cross-skill dependency (skill-tiktok-ads-video) which are not further explained.
Install Mechanism
There is no install spec in the registry (instruction-only), which normally lowers risk. But SKILL.md instructs running npm install and node scripts as if code were included. Because no code or install artifacts are present in the package, the instructions either assume an external repository or are incomplete/misleading. That mismatch (no install vs. instructions that require package installation) is a red flag.
Credentials
The environment variables required by SKILL.md (FAL_KEY, ELEVENLABS_API_KEY, OPENAI_API_KEY) are proportional to the stated integrations and are reasonable for this task. The concern is that the registry metadata declares no required env vars or primary credential while the SKILL.md explicitly requires three API keys. This disparity means automated permission checks or prompts could be incorrect; users might unknowingly provide keys to an unknown/unsigned skill.
Persistence & Privilege
The skill is not set always:true and does not request system config paths or other skills' credentials. It is user-invocable and allows model invocation (platform defaults). No evidence it requests persistent presence or modifies other skills.
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 skill-ugc-pipeline
  3. 安装完成后,直接呼叫该 Skill 的名称或使用 /skill-ugc-pipeline 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
v1.2.0
skill-ugc-pipeline v1.2.0 - Adds B-roll video splicing: Kling 2.6 Pro generates product shots, inserted into the avatar video at configurable time - Introduces UGC filter: grain and handheld shake apply to avatar segments only, product B-roll remains cinematic - Ensures continuous audio across B-roll splice (no gaps) - New broll.js script for B-roll and UGC filter post-processing - Updated cost estimate and requirements - Documentation expanded with new workflow steps and script options
v1.1.0
skill-ugc-pipeline v1.1.0 - Aurora is now the default and locked avatar model after A/B testing, providing more realistic lip sync and narration. - Updated cost and model comparison details; Aurora is the most cost-effective and highest quality option. - Added clearer Quick Start, batch mode, environment variable setup, and detailed flag explanations. - Whisper-synced captions and overlay support clarified, with instructions for usage. - Requires [skill-tiktok-ads-video] installed for caption overlay. - Improved documentation for avatar guidelines and error handling (Aurora timeout fallback).
元数据
Slug skill-ugc-pipeline
版本 1.2.0
许可证
累计安装 2
当前安装数 2
历史版本数 2
常见问题

AI UGC Video Pipeline 是什么?

End-to-end AI UGC video pipeline. Product info → GPT-4o-mini script → ElevenLabs voiceover → Aurora talking head (fal-ai/creatify/aurora) → Kling 2.6 Pro pro... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 341 次。

如何安装 AI UGC Video Pipeline?

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

AI UGC Video Pipeline 是免费的吗?

是的,AI UGC Video Pipeline 完全免费(开源免费),可自由下载、安装和使用。

AI UGC Video Pipeline 支持哪些平台?

AI UGC Video Pipeline 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 AI UGC Video Pipeline?

由 Zero2Ai(@zero2ai-hub)开发并维护,当前版本 v1.2.0。

💬 留言讨论