scenario-labs/skills
❌ 实测失败serverPythonMIT★ 3649
Get production-ready images, video, audio, and 3D from any AI agent: skills that pick the right model, price before spending, and keep characters and brands consistent through the Scenario MCP, plus expert teams that drive Blender, Maya, ZBrush, Unreal, and Unity.
实测结果
失败
沙箱内启动/握手失败，下方给出失败阶段与原始报错。失败阶段：initialize，错误类型：runtime_error。这类信息对判断“是不是我这边的环境问题”很有用，原始报错见下。
error_type: runtime_error
███████╗ ██╔════╝██║ ██╔╝██║██║ ██║ ██╔════╝ ███████╗█████╔╝ ██║██║ ██║ ███████╗ ╚════██║██╔═██╗ ██║██║ ██║ ╚════██║ ███████║██║ ██╗██║███████╗███████╗███████║ ╚══════╝╚═╝ ╚═╝╚═╝╚══════╝╚══════╝╚══════╝ The open agent skills ecosystem $ npx skills add <package> Add a new skill $ npx skills use <package>@<skill> Use a skill without installing $ npx skills remove Remove installed skills $ npx skills list List installed skills $ npx skills find [query] Search for skills $ npx skills update Update installed skills $ npx skills experimental_install Restore from skills-lock.json $ npx skills init [name] Create a new skill $ npx skills experimental_sync Sync skills from node_modules try: npx skills add vercel-labs/agent-skills Discover more skills at https://skills.sh/
- 安装方式
- npx
- 包名
- skills
- 解析依据
- npm registry match (has bin)
- 沙箱
- docker
- 总耗时
- 11781 ms
- 安装耗时
- 10555 ms
- 工作目录
- 7 MB
- 探针版本
- 1.0.0
- 实测时间
- 2026-11-11 12:49:53
如何使用
1安装 / 启动命令npm / npx
npx -y skills
2客户端配置Claude Desktop / Cursor
{
"mcpServers": {
"scenario-labs-skills": {
"command": "npx",
"args": [
"-y",
"skills"
]
}
}
}整段粘进 claude_desktop_config.json 的 mcpServers 里（Cursor 用 ~/.cursor/mcp.json），保存后重启客户端。
安装方式来源：npm registry match (has bin)，沙箱实测未通过。
仓库信息
- 全名
- scenario-labs/skills
- 分类
- server
- Stars
- 3649
- Forks
- 319
- 主要语言
- Python
- License
- MIT
- 最近推送
- 2026-11-09
- 仓库创建
- 2026-08-12
- 首次收录
- 2026-11-10
- 最近抓取
- 2026-11-10
#3d-models#agent-skills#ai-agents#ai-art#blender#claude-code#claude-skills#codex#game-assets#game-development#generative-ai#image-generation