← 返回 Skills 市场
709
总下载
4
收藏
2
当前安装
3
版本数
在 OpenClaw 中安装
/install cli-anything-xingyue
功能描述
基于 HKUDS/CLI-Anything 仓库重构的 OpenClaw Skill。为任意软件生成 CLI 工具,让 AI Agent 可以控制它。通过分析软件源代码,自动生成可被 AI 调用的命令行接口。支持 GIMP、Blender、LibreOffice、OBS 等软件。
使用说明 (SKILL.md)
CLI-Anything for OpenClaw
🔧 基于 HKUDS/CLI-Anything 仓库重构
让任意软件都能被 AI Agent 驱动。
什么是 CLI-Anything?
今天的软件为人而生,明天的用户是 Agent。
CLI-Anything 连接 AI Agent 与全世界软件的桥梁,通过一行命令让任意软件变成 Agent 可控的工具。
核心特性
- 🌍 通用性 - 任何软件都可以变成 CLI 工具
- 📦 开箱即用 - 11+ 预生成的 CLI(GIMP, Blender, LibreOffice 等)
- 🔗 无缝集成 - 无需 API、无需 GUI 重建
- 📝 自描述 -
--help自动生成文档 - 🤖 Agent 优先 - 结构化 JSON 输出
快速命令
查看可用 CLI
/cli-list
当前可用的 CLI:
- gimp - 图像编辑
- blender - 3D 建模/渲染
- libreoffice - 办公套件
- obs-studio - 屏幕录制/直播
- kdenlive - 视频编辑
- shotcut - 视频编辑
- audacity - 音频编辑
- inkscape - 矢量图形
- drawio - 流程图
- zoom - 视频会议
- anygen - AI 内容生成
安装 CLI
/cli-install gimp
/cli-install blender
安装后即可使用:
cli-anything-gimp --help
cli-anything-blender --help
构建新 CLI(高级)
/cli-build ./my-software
/cli-build https://github.com/user/repo
⚠️ 完整构建需要在 Claude Code 或 Codex 环境中进行。
优化 CLI
/cli-refine ./gimp
/cli-refine ./gimp "添加图像批处理功能"
验证 CLI
/cli-validate ./gimp
使用示例
GIMP 图像编辑
# 查看帮助
cli-anything-gimp --help
# 创建新项目
cli-anything-gimp project new --width 1920 --height 1080 -o poster.json
# 添加图层
cli-anything-gimp --json layer add -n "Background" --type solid --color "#1a1a2e"
# 导出
cli-anything-gimp export png -o output.png
# 交互式 REPL
cli-anything-gimp
Blender 3D
# 创建场景
cli-anything-blender scene new -o scene.json
# 添加立方体
cli-anything-blender object add cube --location 0 0 0
# 渲染
cli-anything-blender render output.png --samples 128
LibreOffice 文档
# 打开文档
cli-anything-libreoffice document open report.odt
# 添加内容
cli-anything-libreoffice text add "Hello World"
# 导出 PDF
cli-anything-libreoffice export pdf -o report.pdf
工作原理
CLI-Anything 自动执行 7 阶段流水线:
- 🔍 分析 — 扫描源码,将 GUI 操作映射到 API
- 📐 设计 — 规划命令分组、状态模型
- 🔨 实现 — 构建 Click CLI(REPL、JSON、撤销/重做)
- 📋 规划测试 — 生成测试计划
- 🧪 编写测试 — 实现测试套件
- 📝 文档 — 更新使用文档
- 📦 发布 — 生成 setup.py
注意事项
- 首次使用
/cli-list会自动克隆 CLI-Anything 仓库 - 预生成的 CLI 无需额外配置,安装后可直接使用
- 构建新软件 CLI 需要 Claude Code 或 Codex 环境
- 已安装的 CLI 可通过
pip uninstall卸载
安全使用建议
This skill appears to do what it says (generate and install CLI wrappers) and uses a GitHub repo as its source. Before installing or running build/install flows: 1) Review the cloned repository contents in ~/.openclaw/cli-anything (or clone it yourself) — do not blindly run pip install on unreviewed code. 2) Prefer running builds/installations inside an isolated environment (virtualenv, container, or VM) to avoid modifying your system Python or exposing sensitive files. 3) Be careful when passing local paths to /cli-build; the scripts walk directories and will run operations relative to those paths. 4) Note the SKILL metadata omits the fact it writes to ~/.openclaw — expect disk writes. 5) The skill mentions using external LLM environments (Claude Code/Codex) for full generation; do not send sensitive source code to external services without reviewing privacy implications. If you want higher assurance, ask the publisher for a reproducible release (tagged GitHub release or checksum) and inspect the harness code before running pip install.
功能分析
Type: OpenClaw Skill
Name: cli-anything-xingyue
Version: 1.0.2
The skill is a legitimate wrapper for the HKUDS/CLI-Anything project, which aims to provide CLI interfaces for GUI-based software to be controlled by AI agents. The code performs standard operations such as cloning the official repository from GitHub (https://github.com/HKUDS/CLI-Anything.git) and installing generated packages using 'pip install -e .'. There is no evidence of data exfiltration, malicious execution, or prompt injection; the logic is consistent with the stated purpose of the tool.
能力评估
Purpose & Capability
Name/description ask to generate CLI tools for arbitrary software; required binaries (git, python3, pip) and the included scripts that clone a GitHub repo and install harness packages align with that purpose.
Instruction Scope
Runtime instructions and scripts clone the CLI-Anything GitHub repo, inspect user-supplied paths or repos, list/validate harness directories, and call `pip install -e` on generated harnesses. These actions are consistent with building/installing CLIs but involve executing third-party code and walking the filesystem; review inputs/paths and the cloned repository before running builds or installs.
Install Mechanism
There is no opaque download/install host: the code clones https://github.com/HKUDS/CLI-Anything.git (a standard GitHub URL). No URL shorteners or unknown personal servers are used. The skill is instruction- and script-based rather than using a binary installer.
Credentials
The skill requests no credentials or environment variables, which matches expectations. However it writes to and uses a local path (~/.openclaw/cli-anything) even though 'required config paths' in the metadata are empty — a minor metadata inconsistency. The scripts will also run pip installs which affect the user environment.
Persistence & Privilege
always:false and autonomous invocation is allowed (platform default). The skill creates persistent files in the user's home (~/.openclaw/cli-anything) and can install console commands via `pip install -e` — this grants it the ability to persist executables on the system, so exercise caution and review code before installing.
如何使用
- 确保已安装 OpenClaw(本地或 Docker 部署)
- 在对话框中输入安装命令:
/install cli-anything-xingyue - 安装完成后,直接呼叫该 Skill 的名称或使用
/cli-anything-xingyue触发 - 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
v1.0.2
优化描述,去除冗余信息
v1.0.1
添加原作者信息
v1.0.0
基于 HKUDS/CLI-Anything 仓库重构的 OpenClaw Skill
元数据
常见问题
Cli Anything 是什么?
基于 HKUDS/CLI-Anything 仓库重构的 OpenClaw Skill。为任意软件生成 CLI 工具,让 AI Agent 可以控制它。通过分析软件源代码,自动生成可被 AI 调用的命令行接口。支持 GIMP、Blender、LibreOffice、OBS 等软件。 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 709 次。
如何安装 Cli Anything?
在 OpenClaw 或 Claude Code 对话框中运行命令「/install cli-anything-xingyue」即可一键安装,无需额外配置。
Cli Anything 是免费的吗?
是的,Cli Anything 完全免费,采用 MIT-0 许可证,可自由下载、安装和使用。
Cli Anything 支持哪些平台?
Cli Anything 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 Cli Anything?
由 kay(@yikai123456)开发并维护,当前版本 v1.0.2。
推荐 Skills