Token导航 LogoToken导航

Agent Skill · 研究检索

cli-anything(CLI anything 搜索)

cli-anything 用于查找、检索和筛选相关信息,适合在 Codex、Claude、Cursor、Gemini CLI 中需要根据关键词、任务场景或来源线索快速定位候选结果时使用。可结合来源仓库、安装命令和原始 README 继续核验具体用法。安装前建议确认权限范围、维护状态,以及是否会触发联网、命令执行或文件读写。

cli-anything 是研究检索类 Agent Skill,可用宿主为 Codex、Claude、Cursor、Gemini CLI,通过GitHub 仓库获取,权限为接触敏感数据;许可证信息还不明确,第三方扫描有提醒项,按安装量在研究检索类的 73,674 个 Skill 里排第 44,915。

总安装 881周安装 36GitHub Stars 38下载 285核验 2026-05-01

安装说明

本站只整理中文说明,不托管安装包,也不代用户安装。
GitHub
许可证
unknown

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手,先确认命令和权限,再让它执行。

请帮我安装这个 Agent Skill:cli-anything(CLI anything 搜索)
来源仓库:https://github.com/terrylica/cc-skills
仓库路径:skills/cli-anything
安装命令:
npx skills add https://github.com/terrylica/cc-skills --skill cli-anything
安装前请先检查当前环境是否支持对应 CLI,并向我确认将要执行的命令、安装目录、联网范围和文件读写权限;确认后再执行。

命令行安装

复制命令到本机终端执行。该命令会通过 npx skills 从第三方来源获取 Skill;本站只展示命令,不托管安装包,也不自动执行。

skills.shnpx skills
npx skills add https://github.com/terrylica/cc-skills --skill cli-anything

这个 Skill 是做什么的

研究检索类 Skill 主要解决「找资料、核对事实、把来源整理清楚」的问题,通常会让助手先检索再总结。

cli-anything 用于查找、检索和筛选相关信息,支持基于关键词快速定位。它适用于需要根据任务场景或来源线索筛选信息的场景。可在 Codex、Claude、Cursor、Gemini CLI 中使用。建议确认权限范围和维护状态,避免触发不必要操作。

适用宿主包括 Codex、Claude、Cursor、Gemini CLI,接入前应确认版本、权限和运行环境要求。

来源仓库内路径:skills/cli-anything

上手步骤

4 步
  1. 1

    确认自己的宿主工具

    公开资料标注支持 Codex、Claude、Cursor、Gemini CLI;先确认自己用的是其中之一,再按对应工具的 Skills 目录放置。

  2. 2

    拿到安装命令

    可以直接复制的命令是 npx skills add https://github.com/terrylica/cc-skills --skill cli-anything;命令里的占位符换成自己的路径或密钥再执行。

  3. 3

    安装后重启宿主

    命令执行完要完全退出宿主工具再打开,让新装的 Skill 被重新扫描到,否则列表里可能看不到。

  4. 4

    按最小权限试用

    它需要接触敏感数据,先在测试目录或测试账号里跑,确认没问题再放到正式项目。

常见问题

6 条

cli-anything 怎么安装?

在终端执行 npx skills add https://github.com/terrylica/cc-skills --skill cli-anything。装完完全退出宿主工具再打开,让它重新扫描本地 Skill。

cli-anything 支持哪些 AI 工具?

公开资料标注支持 Codex、Claude、Cursor、Gemini CLI。其他工具只要能读取本地 Skill 目录,一般也能手动放进去,但要自己确认触发方式是否一致。

cli-anything 需要什么权限?

权限级别是接触敏感数据。该 Skill 可能接触密钥、Token、环境变量或敏感配置,应进入高风险复核队列,默认不自动发布。

cli-anything 是免费的吗?

公开资料没有标注明确许可证,收费和商用限制都无法确认。正式使用前请到来源仓库核对授权说明。

cli-anything 用的人多吗?

公开数据是累计安装 881 次,近一周安装 36 次,下载 285 次,GitHub 38 星。这些数字来自第三方目录统计,只能当作热度参考,不代表质量或安全性。

cli-anything 安全吗?

第三方扫描有提醒项,说明存在需要人工确认的行为。安装前请打开源码看清它读了什么、联网到哪里。

值得选的地方和要先想清楚的地方

值得选的地方

  • 同时适配 4 种工具,换客户端不用重新找替代品。

先想清楚的地方

  • 需要接触敏感数据,装到常用环境前要先评估影响面。
  • 许可证没有明确标注,能不能商用、能不能再分发都不确定。
  • 第三方扫描存在提醒项或未通过项,需要人工逐条确认。
  • 第三方目录整理,版本更新和行为细节以来源仓库为准。

适不适合你

更适合

  • 已经在用 Codex,想直接扩展它能力的人。
  • 需要处理研究检索类任务、又不想每次都手写提示词的人。

不太适合

  • 环境里有大量密钥、凭证,不方便给第三方 Skill 读取的人。
  • 需要明确授权才能用到公司项目里的场景。
  • 需要厂商级技术支持和 SLA 的生产系统。

研究检索类 Skill 对比

6 个同类
Skill总安装GitHub 星权限许可证扫描
find-skills

寻找技能 · Codex、Claude

31,199,81316,486操作浏览器MIT有提醒
self-improving-agent

自我改进 Agent · OpenClaw

16,464,0023,396接触敏感数据MIT-0通过
soultrace

灵魂追踪 · Codex、Claude

7,588,94412需要联网未明确有提醒
self-improving

自我完善 · OpenClaw

6,829,2841,046需要联网MIT-0通过
microsoft-foundry

微软代工厂 · Codex、Claude

6,614,144764调用外部服务未明确有提醒
cli-anything

CLI anything 搜索 · 本页

88138接触敏感数据未明确有提醒

按安装量取同分类前几名;数字来自第三方目录统计,只作热度参考,不代表质量结论。

SKILL.md 原文

CLI-Anything Reference

Auto-generates production-ready, agent-controllable CLI interfaces for any GUI application with accessible source code. A 7-phase pipeline maps GUI actions to backend APIs and emits Click-based harnesses with --json output mode, interactive REPL, and pytest test suites.

Source: https://github.com/HKUDS/CLI-Anything License: MIT | Python: 3.10+ | Tests: 1,508 passing across 11 apps


Self-Evolving Skill: This skill improves through use. If instructions are wrong, parameters drifted, or a workaround was needed — fix this file immediately, don't defer. Only update for real, reproducible issues.

Installation

Method 1: Claude Code Marketplace (recommended)

/plugin marketplace add HKUDS/CLI-Anything
/plugin install cli-anything

Method 2: Manual Claude Code

git clone https://github.com/HKUDS/CLI-Anything.git
cp -r CLI-Anything/cli-anything-plugin ~/.claude/plugins/cli-anything
# Reload in Claude Code:
/reload-plugins

Method 3: OpenCode — global

git clone https://github.com/HKUDS/CLI-Anything.git
cp CLI-Anything/opencode-commands/*.md ~/.config/opencode/commands/
cp CLI-Anything/cli-anything-plugin/HARNESS.md ~/.config/opencode/commands/

Method 4: OpenCode — project-level

cp CLI-Anything/opencode-commands/*.md .opencode/commands/
cp CLI-Anything/cli-anything-plugin/HARNESS.md .opencode/commands/

Generating a New CLI Harness

# From local source path
/cli-anything ./gimp

# From GitHub URL (auto-cloned)
/cli-anything https://github.com/blender/blender

# Claude Code variant (plugin command)
/cli-anything ./inkscape

# OpenCode variant
/cli-anything ./libreoffice

All Commands

CommandPlatformPurpose
/cli-anything <path-or-url>Claude CodeBuild full 7-phase harness
/cli-anything:refine <path> [focus]Claude CodeExpand with gap analysis
/cli-anything:test <path-or-url>Claude CodeRun tests + update TEST.md
/cli-anything:validate <path-or-url>Claude CodeVerify HARNESS.md standards
/cli-anything:list [--path dir] [--depth n] [--json]Claude CodeDiscover installed CLI-Anything tools
/cli-anything./gimpOpenCodeBuild harness
/cli-anything-refine./gimpOpenCodeRefine harness
/cli-anything-test./gimpOpenCodeRun tests
/cli-anything-validate./gimpOpenCodeValidate standards
/cli-anything-listOpenCodeList installed tools

Refinement with Focus

# Broad gap analysis
/cli-anything:refine ./gimp

# Targeted domain expansion
/cli-anything:refine ./gimp "batch processing and filters"
/cli-anything:refine ./blender "rendering pipeline and animations"
/cli-anything:refine ./libreoffice "spreadsheet formulas and macros"

Installing a Generated CLI

cd <software>/agent-harness
pip install -e .

# Verify PATH entry created
which cli-anything-gimp
cli-anything-gimp --help

Using Generated CLIs

All generated CLIs share a consistent interface pattern.

GIMP Example

# Help
cli-anything-gimp --help

# Create project
cli-anything-gimp project new --width 1920 --height 1080 -o poster.json

# Machine-readable JSON output (for agent consumption)
cli-anything-gimp --json layer add -n "Background" --type solid --color "#1a1a2e"

# Interactive REPL
cli-anything-gimp

# Stateful workflow with --project flag
cli-anything-gimp --project poster.json layer add -n "Logo" --type group
cli-anything-gimp --project poster.json export render output.png --format png

LibreOffice Example

# New document
cli-anything-libreoffice document new -o report.json --type writer

# Populate document
cli-anything-libreoffice --project report.json writer add-heading -t "Q1 Report" --level 1
cli-anything-libreoffice --project report.json writer add-table --rows 4 --cols 3

# Export
cli-anything-libreoffice --project report.json export render output.pdf -p pdf --overwrite

# JSON output
cli-anything-libreoffice --json document info --project report.json

Blender Example

cli-anything-blender scene new -o scene.json
cli-anything-blender --project scene.json object add --type mesh --mesh-type CUBE
cli-anything-blender --project scene.json render image output.png --engine CYCLES
cli-anything-blender --json scene info --project scene.json

Inkscape Example

cli-anything-inkscape document new --width 800 --height 600 -o design.json
cli-anything-inkscape --project design.json shape add rect --x 10 --y 10 --w 200 --h 100
cli-anything-inkscape --project design.json export render output.svg
cli-anything-inkscape --json document info --project design.json

Output Modes

Every command supports two output modes:

ModeUsageAudience
Human-readable (default)cli-anything-gimp layer add...Terminal / humans
Machine-readable JSONcli-anything-gimp --json layer add...AI agents, scripts

The --json flag is always the first argument, before any subcommands.


Interactive REPL

Enter by running the CLI with no subcommands:

cli-anything-gimp
cli-anything-blender
cli-anything-libreoffice

REPL features:

  • 50-level undo/redo stack
  • Persistent command history
  • ANSI 256-color output (software-specific accent colors)
  • Table rendering, progress indicators
  • All subcommands available interactively

Running Tests

# Standard pytest run
cd <software>/agent-harness
python3 -m pytest cli_anything/<software>/tests/ -v

# Validate the installed binary is invoked (not just the module)
CLI_ANYTHING_FORCE_INSTALLED=1 python3 -m pytest cli_anything/<software>/tests/ -v -s

# Coverage
python3 -m pytest cli_anything/<software>/tests/ --cov=cli_anything/<software>

# Per-software examples
cd gimp/agent-harness && python3 -m pytest cli_anything/gimp/tests/ -v
cd blender/agent-harness && python3 -m pytest cli_anything/blender/tests/ -v
cd libreoffice/agent-harness && python3 -m pytest cli_anything/libreoffice/tests/ -v

Environment Variables

VariablePurpose
CLI_ANYTHING_FORCE_INSTALLED=1Forces tests to use the real installed binary (validates which cli-anything-<software> resolves correctly, not just module import)

Supported Applications (11 total, 1,508 tests)

ApplicationCategoryEntry Point
GIMPCreative (raster)cli-anything-gimp
BlenderCreative (3D)cli-anything-blender
InkscapeCreative (vector)cli-anything-inkscape
AudacityMedia (audio)cli-anything-audacity
LibreOfficeProductivitycli-anything-libreoffice
OBS StudioMedia (streaming)cli-anything-obs-studio
KdenliveMedia (video)cli-anything-kdenlive
ShotcutMedia (video)cli-anything-shotcut
ZoomCommunicationcli-anything-zoom
Draw.ioDiagrammingcli-anything-drawio
AnyGenAI Contentcli-anything-anygen

The 7-Phase Pipeline (HARNESS.md)

What /cli-anything triggers under the hood:

PhaseNameWhat happens
1Source AcquisitionAccept local path or GitHub URL; clone if needed
2Codebase AnalysisMap GUI actions → backend APIs; inventory existing CLI tools; document data model
3CLI Architecture DesignChoose interaction model (stateful REPL + subcommand); define command groups; plan --json output
4ImplementationBuild Click-based CLI with cli_anything.<software> namespace; implement REPL via shared ReplSkin
5Test PlanningWrite TEST.md with planned test inventory before code
6Test ImplementationUnit tests (synthetic data) + E2E tests (real software output) + subprocess tests
7PyPI Publishingsetup.py with find_namespace_packages(); console_scripts entry points

Fundamental Rule: The CLI MUST delegate rendering to the real software — never reimplement functionality in Python. The target software is a hard dependency.


Generated Harness Structure

Each generated CLI follows this layout (PEP 420 namespace packages):

<software>/agent-harness/
├── setup.py                          # find_namespace_packages(), entry_points
├── <SOFTWARE>.md                     # Software-specific SOP
└── cli_anything/                     # NO __init__.py (namespace package)
    └── <software>/
        ├── __init__.py
        ├── __main__.py
        ├── <software>_cli.py         # Main Click entry point
        ├── core/                     # Domain modules (project, session, export, ...)
        ├── utils/
        │   └── repl_skin.py          # Shared REPL UI (copied from plugin)
        └── tests/
            ├── TEST.md               # Test inventory (written in phase 5)
            ├── test_core.py          # Unit tests
            └── test_full_e2e.py      # E2E + subprocess tests

Why namespace packages: cli_anything/ has no __init__.py, enabling multiple separately-installed CLIs to coexist under the same cli_anything.* namespace without conflict.


Output Verification Standards

Tests verify real output using magic bytes and content analysis:

Output TypeVerification
PDF%PDF- magic bytes + non-zero size
OOXML (.docx,.xlsx)ZIP structure validation
CSVData row count + column check
ImagesPillow pixel value analysis
AudioRMS level check (non-silent)

Prerequisites Checklist

Before running /cli-anything <path>:

  • Python 3.10+ installed
  • Target software installed (hard dependency — it will be called for rendering)
  • Source code accessible (local path or public GitHub URL)
  • click>=8.0.0 available (installed via pip install -e.)
  • Pillow>=10.0.0, prompt-toolkit>=3.0.0 available
  • pytest available for running tests

Key Files Reference

FilePurpose
cli-anything-plugin/HARNESS.mdComplete methodology document (30K chars)
cli-anything-plugin/QUICKSTART.mdQuick start guide
cli-anything-plugin/repl_skin.pyShared REPL UI class (18K, ANSI 256-color)
cli-anything-plugin/commands/cli-anything.md/cli-anything slash command definition
cli-anything-plugin/commands/refine.md/cli-anything:refine command
cli-anything-plugin/commands/test.md/cli-anything:test command
cli-anything-plugin/commands/validate.md/cli-anything:validate command
cli-anything-plugin/commands/list.md/cli-anything:list command

Post-Execution Reflection

After this skill completes, check before closing:

  1. Did the command succeed? — If not, fix the instruction or error table that caused the failure.
  2. Did parameters or output change? — If the underlying tool's interface drifted, update Usage examples and Parameters table to match.
  3. Was a workaround needed? — If you had to improvise (different flags, extra steps), update this SKILL.md so the next invocation doesn't need the same workaround.

Only update if the issue is real and reproducible — not speculative.

平台分布

Codex

36.43%
按下载量换算104

Claude

29.97%
按下载量换算85

Cursor

16.2%
按下载量换算46

Gemini CLI

9.27%
按下载量换算26

安全审计

Gen Agent Trust Hub

通过

Socket

通过

Snyk

可疑

权限和风险

接触敏感数据

该 Skill 可能接触密钥、Token、环境变量或敏感配置,应进入高风险复核队列,默认不自动发布。

安装前确认

本站仅展示第三方公开信息,不托管安装包,不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。来源安全扫描存在提醒或未通过项,安装前请自行复核。目前只有一个公开来源,建议同时核对源仓库。

继续浏览同类 Skills