← Back to Skills Marketplace
zhaozewen0519

Ai Video Generator

by zhaozewen0519 · GitHub ↗ · v1.0.0 · MIT-0
cross-platform ⚠ suspicious
377
Downloads
0
Stars
3
Active Installs
1
Versions
Install in OpenClaw
/install ai-video-generator
Description
AI 视频生成技能，支持 Luma Dream Machine、Runway ML、Kling AI 等多个平台。文生视频、图生视频。
README (SKILL.md)

AI Video Generator - 文生视频技能

使用 AI 生成视频，支持多个平台：

  • Luma Dream Machine - 高质量，5 秒/10 秒视频
  • Runway ML - 专业级，Gen-2/Gen-3
  • Kling AI（可灵） - 国产，效果优秀

命令

生成视频（Luma）

uv run {baseDir}/scripts/generate_video.py --platform luma --prompt "your video description" --filename "output-video.mp4" [--duration 5|10] [--api-key KEY]

生成视频（Runway）

uv run {baseDir}/scripts/generate_video.py --platform runway --prompt "your video description" --filename "output-video.mp4" [--api-key KEY]

生成视频（Kling）

uv run {baseDir}/scripts/generate_video.py --platform kling --prompt "your video description" --filename "output-video.mp4" [--api-key KEY]

图生视频

uv run {baseDir}/scripts/generate_video.py --platform luma --prompt "describe motion" --filename "output-video.mp4" --input-image "path/to/image.png"

API Key 配置

脚本按以下顺序查找 API Key：

  1. --api-key 参数
  2. 环境变量：LUMA_API_KEY / RUNWAY_API_KEY / KLING_API_KEY

平台对比

平台 时长 特点 API 文档
Luma 5s/10s 质量高，速度快 https://docs.lumalabs.ai
Runway 4s/8s 专业级，控制多 https://docs.runwayml.com
Kling 5s/10s 国产，中文友好 https://klingai.com

文件名生成

格式：yyyy-mm-dd-hh-mm-ss-{platform}-{description}.mp4

示例：

  • 2026-03-17-09-30-00-luma-sunset-beach.mp4
  • 2026-03-17-10-15-00-runway-robot-walk.mp4

工作流

  1. 草稿：先用短 prompt 生成 5 秒视频测试
  2. 迭代：调整 prompt 直到满意
  3. 最终：生成 10 秒高清版本

常见错误

  • Error: No API key provided → 设置环境变量或传递 --api-key
  • Error: Quota exceeded → API 额度用尽，等待重置或换平台
  • Error: Invalid prompt → prompt 太短或包含敏感词

示例

# Luma 生成 5 秒视频
uv run ~/.openclaw/workspace/skills/ai-video-generator/scripts/generate_video.py \
  --platform luma \
  --prompt "A drone flying over a sunset beach, cinematic lighting" \
  --filename "2026-03-17-09-30-00-luma-sunset-beach.mp4" \
  --duration 5

# Kling 图生视频
uv run ~/.openclaw/workspace/skills/ai-video-generator/scripts/generate_video.py \
  --platform kling \
  --prompt "The person waves and smiles" \
  --filename "2026-03-17-10-00-00-kling-person-wave.mp4" \
  --input-image "person.png"
Usage Guidance
Before installing: (1) Understand you will need a valid API key for whichever provider you use (Luma/Runway/Kling); the script will send your key to those provider endpoints to create and download videos. (2) The skill metadata unnecessarily lists curl and jq even though the bundled Python script doesn't use them — this mismatch is not by itself malicious but is sloppy and worth asking the publisher to clarify or fixing locally. (3) Review the provider URLs in the script if you need to verify they are official endpoints. (4) Be careful with filenames/paths you pass (the script writes files to disk). (5) If you do not trust the unknown source owner, consider running the script in a sandboxed environment or inspect/modify the code (e.g., remove or correct metadata) before use.
Capability Analysis
Type: OpenClaw Skill Name: ai-video-generator Version: 1.0.0 The skill bundle provides a legitimate tool for generating AI videos using Luma, Runway, and Kling AI platforms. The Python script `scripts/generate_video.py` correctly implements API interactions with official endpoints (e.g., api.lumalabs.ai) and handles file downloads as expected for its stated purpose. No evidence of data exfiltration, malicious code execution, or prompt injection was found.
Capability Assessment
⚠ Purpose & Capability
The script implements Luma, Runway, and Kling video generation and only needs an API key per platform. However, the skill metadata and registry list required binaries 'curl' and 'jq' even though the provided Python script uses urllib and base64 and does not call curl/jq. This mismatch is unnecessary for the stated purpose and suggests sloppy metadata or possible leftover requirements from a different implementation.
✓ Instruction Scope
SKILL.md instructs the agent to run the included Python script and to supply an API key either via --api-key or environment variables. The instructions do not request unrelated system files, other credentials, or exfiltration endpoints; network calls are only to the named provider APIs.
✓ Install Mechanism
There is no install spec (instruction-only skill with a bundled script). Nothing is downloaded at install time and no installers or arbitrary remote archives are referenced. Risk from installation is low.
ℹ Credentials
The code expects per-platform API keys (LUMA_API_KEY, RUNWAY_API_KEY, KLING_API_KEY), which are proportionate to the skill's function. Registry metadata shows no required env vars but SKILL.md lists these as optional — practically, the script will fail unless an API key is provided for the chosen platform, so you must supply those keys. No other credentials are requested.
✓ Persistence & Privilege
The skill is not always-enabled and does not request elevated persistence. It does write output files (videos) to paths you provide, which is expected behavior.
How to Use
  1. Make sure OpenClaw is installed (local or Docker)
  2. Run the install command in chat: /install ai-video-generator
  3. After installation, invoke the skill by name or use /ai-video-generator
  4. Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
Initial release of AI 视频生成技能 (AI Video Generator): - Supports Luma Dream Machine, Runway ML (Gen-2/3), and Kling AI platforms for video generation. - Provides commands for text-to-video and image-to-video workflows. - Flexible API key configuration via parameter or environment variables. - Includes platform comparison table and guidance on file naming. - Documents common errors and recommended usage workflow.
Metadata
Slug ai-video-generator
Version 1.0.0
License MIT-0
All-time Installs 3
Active Installs 3
Total Versions 1
Frequently Asked Questions

What is Ai Video Generator?

AI 视频生成技能，支持 Luma Dream Machine、Runway ML、Kling AI 等多个平台。文生视频、图生视频。 It is an AI Agent Skill for Claude Code / OpenClaw, with 377 downloads so far.

How do I install Ai Video Generator?

Run "/install ai-video-generator" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.

Is Ai Video Generator free?

Yes, Ai Video Generator is completely free, licensed under MIT-0. You can download, install and use it at no cost.

Which platforms does Ai Video Generator support?

Ai Video Generator is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).

Who created Ai Video Generator?

It is built and maintained by zhaozewen0519 (@zhaozewen0519); the current version is v1.0.0.

More 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...
⬇ 463556 · 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.
⬇ 259610 · 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...
⬇ 200551 · 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.
⬇ 191226 · by steipete
ontology
Typed knowledge graph for structured agent memory and composable skills. Use when creating/querying entities (Person, Project, Task, Event, Document), linkin...
⬇ 190235 · by oswalpalash

💬 Comments