S

skills

by @vargHQv1.0.0
3.5(0)

vargHQ 的 `skills` 仓库提供一系列强大的 AI 代理技能,专为视频、图像、语音和音乐生成设计。它整合了 Kling、Flux、ElevenLabs、Sora 等前沿 AI 模型,让用户无需编写代码,仅通过简单的提示词即可轻松创作多媒体内容。该技能集兼容 Claude Code、Cursor 等主流 AI 编程助手,极大地简化了 AI 创作流程,提升效率。

AI Agent SkillsGenerative AIMultimedia GenerationNo-code AIPrompt EngineeringGitHub
安装方式
npx skills add vargHQ/skills
compare_arrows

Before / After 效果对比

1
使用前

在使用 varg skills 之前,开发者或创作者需要分别学习和集成 Kling、ElevenLabs 等多个 AI 模型,涉及复杂的 API 调用和代码编写,导致工作流程碎片化,耗时且门槛高。

使用后

现在,通过 varg skills,只需一个统一的 AI 代理技能,即可通过简单的提示词访问所有集成模型。无需代码,极大地简化了多媒体内容生成流程,显著提升了创作效率和可访问性。

description SKILL.md

varg — AI Agent Skills for Video, Image, Speech & Music Generation

A collection of Agent Skills for AI video, image, speech, and music generation using the varg platform. One skill to access Kling, Flux, ElevenLabs, Sora, and more — zero code, just prompt.

Works with Claude Code, Cursor, Windsurf, OpenCode, ClawHub, and any tool that supports the Agent Skills standard.

Installation

ClawHub (recommended)

# Install a specific skill
npx clawhub@latest install vargai

# Or install all skills from this repo
npx clawhub@latest install vargai

Claude Code

# Clone into personal skills directory (available in all projects)
git clone https://github.com/vargHQ/skills.git ~/.claude/skills/varg

# Or symlink individual skills
ln -s /path/to/skills/varg-ai ~/.claude/skills/varg-ai

OpenCode

# Clone into any supported skills directory
git clone https://github.com/vargHQ/skills.git ~/.opencode/skills/varg

# Also works with:
#   ~/.agents/skills/
#   .opencode/skills/ (project-level)

Agent Skills CLI

npx skills add vargHQ/skills --yes

Available Skills

SkillDescriptionClawHub Slug
varg-aiAI video, image, speech, and music generationvargai

Requirements

  • VARG_API_KEY (get at varg.ai) -- required for all skills
  • Cloud mode: curl only (zero dependencies)
  • Local mode: bun runtime + ffmpeg

Skill Structure

Each skill follows the Agent Skills specification:

skill-name/
├── SKILL.md            # Core instructions (required)
├── references/         # On-demand reference docs
│   ├── models.md       # Model catalog, pricing
│   ├── components.md   # Component reference
│   └── ...
├── scripts/            # Executable setup/helper scripts
│   └── setup.sh
└── assets/             # Static resources (optional)

Adding a New Skill

  1. Create a directory at the repo root with your skill name (lowercase, hyphens only):
mkdir my-new-skill
  1. Create my-new-skill/SKILL.md with cross-compatible frontmatter:
---
name: my-new-skill
description: >-
  What this skill does and when to use it.
  Include trigger keywords for auto-discovery.
license: MIT
metadata:
  author: vargHQ
  version: "1.0.0"
  openclaw:
    requires:
      env:
        - VARG_API_KEY
      anyBins:
        - curl
        - bun
    primaryEnv: VARG_API_KEY
    homepage: https://varg.ai
compatibility: >-
  Describe environment requirements here.
allowed-tools: Bash(bun:*) Bash(curl:*) Read Write Edit
---

Your skill instructions here...
  1. Add reference docs in my-new-skill/references/ (keep SKILL.md under 500 lines).

  2. Push to main -- the GitHub Actions workflow auto-publishes all changed skills to ClawHub via clawhub sync.

Frontmatter Field Reference

FieldStandardPurpose
nameAgent SkillsSkill identifier (must match directory name)
descriptionAgent SkillsWhat + when (used for discovery in all tools)
licenseAgent SkillsLicense (MIT for ClawHub)
metadata.authorAgent SkillsAuthor identifier
metadata.versionAgent SkillsSemver version string
metadata.openclawClawHubRuntime requirements, env vars, binaries
compatibilityAgent SkillsHuman-readable requirements description
allowed-toolsClaude Code / OpenCodePre-approved tools (experimental in OpenCode)

All fields are cross-compatible -- tools ignore fields they don't recognize.

Quick Start

# 1. Install the skill
npx clawhub@latest install vargai

# 2. Set your API key
export VARG_API_KEY=varg_xxx

# 3. Run setup to verify environment
bash varg-ai/scripts/setup.sh

# 4. Render your first video
bunx vargai render hello.tsx --preview    # Free preview
bunx vargai render hello.tsx --verbose    # Full render

Documentation

License

MIT

forum用户评价 (0)

发表评价

效果
易用性
文档
兼容性

暂无评价

统计数据

安装量17
评分3.5 / 5.0
版本1.0.0
更新日期2026年4月6日
对比案例1 组

用户评分

3.5(0)
5
0%
4
0%
3
0%
2
0%
1
0%

为此 Skill 评分

0.0

兼容平台

🔧Claude Code

时间线

创建2026年4月6日
最后更新2026年4月6日