Menu
CLI-Anything 插件 —— 为任何 GUI 软件自动生成 Agent-Native 的命令行接口。当用户需要让 AI Agent 控制专业软件（如 GIMP、Blender、LibreOffice 等）时使用。
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Based on SOC occupation classification
| name | cli-anything |
| description | CLI-Anything 插件 —— 为任何 GUI 软件自动生成 Agent-Native 的命令行接口。当用户需要让 AI Agent 控制专业软件（如 GIMP、Blender、LibreOffice 等）时使用。 |
| triggers | ["为软件生成 CLI","让 Agent 控制软件","cli-anything","agent-native","自动化软件操作","生成命令行接口"] |
让任何软件都能被 AI Agent 通过命令行控制。
现在的软件都是给人用的（GUI 界面、鼠标点击），但 AI Agent 用着很痛苦。CLI-Anything 就是把这个 gap bridged 掉。
| 软件 | 领域 | 生成的 CLI |
|---|---|---|
| GIMP | 图像编辑 | cli-anything-gimp |
| Blender | 3D 建模 | cli-anything-blender |
| LibreOffice | 办公套件 | cli-anything-libreoffice |
| OBS Studio | 直播录制 | cli-anything-obs-studio |
| Audacity | 音频处理 | cli-anything-audacity |
| Kdenlive/Shotcut | 视频编辑 | cli-anything-kdenlive |
| Inkscape | 矢量图形 | cli-anything-inkscape |
| Draw.io | 流程图 | cli-anything-drawio |
/mnt/workspace/.copaw/active_skills/cli-anything/plugin/
# 插件已安装在 active_skills/cli-anything/plugin/
# 在 Claude Code 中使用时：
/cli-anything <software-path-or-repo>
# 为本地软件生成 CLI
/cli-anything /home/user/gimp
# 为 GitHub 仓库生成 CLI
/cli-anything https://github.com/blender/blender
# 细化现有 CLI
/cli-anything:refine /home/user/gimp
# 运行测试
/cli-anything:test /home/user/gimp
# 验证质量
/cli-anything:validate /home/user/gimp
# 进入 REPL 模式
cli-anything-blender
# Agent 控制示例
blender> scene new --name ProductShot
blender> object add-mesh --type cube
blender> render execute --output render.png
✅ 适合：
❌ 不适合：
/mnt/workspace/.copaw/external_skills/CLI-Anything/pip install 到系统 PATHWord文档处理：创建、编辑、读取.docx文件。用户提到"Word"、"文档"、".docx"、"报告"、"信函"时使用。
使用腾讯云 API 密钥调用腾讯云各种服务，包括翻译、CVM、COS等。
图片识别与图文理解，基于 PaddleOCR-VL 模型，支持识别图片中的文字、场景、物体等信息。支持109种语言，可输出JSON或Markdown格式。
You MUST use this for gathering contexts before any work. This is a Knowledge management for AI agents. Use `brv` to store and retrieve project patterns, decisions, and architectural rules in .brv/context-tree. Uses a configured LLM provider (default: ByteRover, no API key needed) for query and curate operations.
Typed knowledge graph for structured agent memory and composable skills. Use when creating/querying entities (Person, Project, Task, Event, Document), linking related objects, enforcing constraints, planning multi-step actions as graph transformations, or when skills need to share state. Trigger on "remember", "what do I know about", "link X to Y", "show dependencies", entity CRUD, or cross-skill data access.
Transform AI agents from task-followers into proactive partners that anticipate needs and continuously improve. Now with WAL Protocol, Working Buffer, Autonomous Crons, and battle-tested patterns. Part of the Hal Stack 🦞