Agent skill

CLI-Anything Harness Builder

Builds, refines, tests or validates a CLI-Anything harness that wraps a GUI application or source repository as a stateful Click CLI with JSON output and a REPL mode.

Apache-2.0Auto-check passedDevelopment

Install CLI-Anything Harness Builder

skills CLI

$ npx skills add HKUDS/CLI-Anything --skill cli-anything -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI

$ gh skill install HKUDS/CLI-Anything cli-anything --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy

$ git clone --depth 1 https://github.com/HKUDS/CLI-Anything.git skills-src && mkdir -p .claude/skills && cp -r skills-src/macrocli .claude/skills/cli-anything && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Paste into Claude Code

Install the "cli-anything" agent skill from https://github.com/HKUDS/CLI-Anything/tree/main/macrocli into .claude/skills/cli-anything/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "cli-anything", then confirm the skill loads.

Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

$skill-installer

$skill-installer install https://github.com/HKUDS/CLI-Anything/tree/main/macrocli

Type this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.

skills CLI

$ npx skills add HKUDS/CLI-Anything --skill cli-anything -a codex

Project install goes to .agents/skills/; add -g for ~/.codex/skills/.

GitHub CLI

$ gh skill install HKUDS/CLI-Anything cli-anything --agent codex

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/HKUDS/CLI-Anything.git skills-src && mkdir -p .agents/skills && cp -r skills-src/macrocli .agents/skills/cli-anything && rm -rf skills-src

Use ~/.agents/skills/ instead of .agents/skills for a personal install.

Codex skills documentation · loads skills from .agents/skills/

Paste into Codex

Install the "cli-anything" agent skill from https://github.com/HKUDS/CLI-Anything/tree/main/macrocli into .agents/skills/cli-anything/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "cli-anything", then confirm the skill loads.

Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add HKUDS/CLI-Anything --skill cli-anything -a cursor

Project install goes to .agents/skills/; add -g for ~/.cursor/skills/.

GitHub CLI

$ gh skill install HKUDS/CLI-Anything cli-anything --agent cursor

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/HKUDS/CLI-Anything.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/macrocli .cursor/skills/cli-anything && rm -rf skills-src

Use ~/.cursor/skills/ instead of .cursor/skills for a personal install.

Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/

Paste into Cursor

Install the "cli-anything" agent skill from https://github.com/HKUDS/CLI-Anything/tree/main/macrocli into .cursor/skills/cli-anything/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "cli-anything", then confirm the skill loads.

Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

gemini skills install

$ gemini skills install https://github.com/HKUDS/CLI-Anything.git --path macrocli

--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.

skills CLI

$ npx skills add HKUDS/CLI-Anything --skill cli-anything -a gemini-cli

Project install goes to .agents/skills/; add -g for ~/.gemini/skills/.

GitHub CLI

$ gh skill install HKUDS/CLI-Anything cli-anything --agent gemini-cli

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/HKUDS/CLI-Anything.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/macrocli .gemini/skills/cli-anything && rm -rf skills-src

Use ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.

Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/

Paste into Gemini CLI

Install the "cli-anything" agent skill from https://github.com/HKUDS/CLI-Anything/tree/main/macrocli into .gemini/skills/cli-anything/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "cli-anything", then confirm the skill loads.

Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

GitHub CLI

$ gh skill install HKUDS/CLI-Anything cli-anything

Installs for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).

skills CLI

$ npx skills add HKUDS/CLI-Anything --skill cli-anything -a github-copilot

Project install goes to .agents/skills/; add -g for ~/.copilot/skills/.

Manual copy

$ git clone --depth 1 https://github.com/HKUDS/CLI-Anything.git skills-src && mkdir -p .github/skills && cp -r skills-src/macrocli .github/skills/cli-anything && rm -rf skills-src

Use ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.

GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/

Paste into GitHub Copilot

Install the "cli-anything" agent skill from https://github.com/HKUDS/CLI-Anything/tree/main/macrocli into .github/skills/cli-anything/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "cli-anything", then confirm the skill loads.

GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add HKUDS/CLI-Anything --skill cli-anything -a opencode

OpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.

GitHub CLI

$ gh skill install HKUDS/CLI-Anything cli-anything --agent opencode

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/HKUDS/CLI-Anything.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/macrocli .opencode/skills/cli-anything && rm -rf skills-src

Use ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.

OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/

Paste into OpenCode

Install the "cli-anything" agent skill from https://github.com/HKUDS/CLI-Anything/tree/main/macrocli into .opencode/skills/cli-anything/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "cli-anything", then confirm the skill loads.

OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

Facts

Skill name: cli-anything
GitHub stars: 52k
Token cost: ~839 tokens
SKILL.md length: 369 words
Files: 44
Skills in repo: 78
Repo updated: Sep 22, 2026
First seen: Oct 7, 2026
Licence: Apache-2.0

At a glance

Builds, refines, tests or validates a CLI-Anything harness that wraps a GUI application or source repository as a stateful Click CLI with JSON output and a REPL mode.

Works in 7 steps: Acquire the source tree locally. → Analyze architecture, data model,… → Design command groups and state model. → …
Wrapping a GUI application as a scriptable command-line harness
SKILL.md covers Inputs, Modes, Backend Rules and Packaging Rules, plus 2 more sections
Runs Python scripts from its folder; calls pip

What it does

The skill adapts the CLI-Anything methodology to OpenClaw without changing the generated Python harness format. It accepts a local source path or a GitHub repository URL and derives the software's name from its directory. Four modes cover the lifecycle: Build produces a new agent-harness folder with a stateful Click CLI offering one-shot subcommands, a REPL default when no subcommand is given, --json output and undo and redo where the target software supports it.

Refine inventories existing commands and tests, then does gap analysis against the target software, preferring high-impact missing features and wrappers that compose with existing commands, and never removes commands unless a breaking change is requested. Test plans tests before writing them, keeping test_core.py for unit coverage and test_full_e2e.py for workflow checks, preferring to invoke the installed command through subprocess rather than only module imports. Validate checks the namespace package layout, an installable entry point, JSON output, the REPL default and documentation.

Backend rules prefer wrapping the real software's executable or scripting interface over reimplementing it, and packaging rules keep cli_anything as a namespace package exposing a cli-anything-<software> console script. If the skill runs inside the CLI-Anything repository itself, it reads HARNESS.md as the full methodology source of truth before falling back to the condensed rules.

When your agent uses it

Wrapping a GUI application as a scriptable command-line harness
Adding missing commands to an existing CLI-Anything harness
Writing unit and end-to-end tests for a generated harness
Validating that a harness follows the CLI-Anything packaging layout

Example prompts

“Build a CLI-Anything harness for the GIMP installation at ./gimp.”
“Refine the existing harness for this repo to add the missing export command.”
“Validate that my harness follows the cli_anything namespace package layout.”

Requirements

Python, for the generated Click-based harness

Workflow steps

7 steps, taken from the first numbered list in SKILL.md.

Acquire the source tree locally.
Analyze architecture, data model, existing CLIs, and GUI-to-API mappings.
Design command groups and state model.
Implement the harness.
Write TEST.md, then tests, then run them.
Update README usage docs.
Verify local installation with pip install -e .

What it can do on your machine

Read from SKILL.md and the folder at commit 34f5195. It shows what the files ask for, not the result of running them.

Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
Ships script files (Python, from the files we listed), which the agent can run.
Shell commands in SKILL.md call:
- pip
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md. Its commands use pip, which can reach the network depending on how they are called.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

CLI-Anything Harness Builder loads about 839 tokens when it runs. Until then it costs about 63 tokens; SKILL.md has 369 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it: ~63
When it runs · the whole SKILL.md, loaded when a task matches: ~839

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from HKUDS/CLI-Anything at commit 34f5195, republished under its Apache-2.0 licence (© HKUDS). 369 words, ~839 tokens.

Download SKILL.mdSave it as .claude/skills/cli-anything/SKILL.md (or your agent's skills folder). This skill also uses 43 other files; get the full folder from GitHub.

name: cli-anything
description: Use when the user wants OpenClaw to build, refine, test, or validate a CLI-Anything harness for a GUI application or source repository. Adapts the CLI-Anything methodology to OpenClaw without changing the generated Python harness format.

CLI-Anything for OpenClaw

Use this skill when the user wants OpenClaw to act like the CLI-Anything builder.

If this skill is being used from inside the CLI-Anything repository, read ../cli-anything-plugin/HARNESS.md before implementation. That file is the full methodology source of truth. If it is not available, follow the condensed rules below.

Inputs

Accept either:

A local source path such as ./gimp or /path/to/software
A GitHub repository URL

Derive the software name from the local directory name after cloning if needed.

Modes

Build

Use when the user wants a new harness.

Produce this structure:

text

<software>/
└── agent-harness/
    ├── <SOFTWARE>.md
    ├── setup.py
    └── cli_anything/
        └── <software>/
            ├── README.md
            ├── __init__.py
            ├── __main__.py
            ├── <software>_cli.py
            ├── core/
            ├── utils/
            └── tests/

Implement a stateful Click CLI with:

one-shot subcommands
REPL mode as the default when no subcommand is given
--json machine-readable output
session state with undo/redo where the target software supports it

Refine

Use when the harness already exists.

First inventory current commands and tests, then do gap analysis against the target software. Prefer:

high-impact missing features
easy wrappers around existing backend APIs or CLIs
additions that compose well with existing commands

Do not remove existing commands unless the user explicitly asks for a breaking change.

Test

Plan tests before writing them. Keep both:

test_core.py for unit coverage
test_full_e2e.py for workflow and backend validation

When possible, test the installed command via subprocess using cli-anything-<software> rather than only module imports.

Show full SKILL.md (158 more words)Show less

Validate

Check that the harness:

uses the cli_anything.<software> namespace package layout
has an installable setup.py entry point
supports JSON output
has a REPL default path
documents usage and tests

Backend Rules

Prefer the real software backend over reimplementation. Wrap the actual executable or scripting interface in utils/<software>_backend.py when possible. Use synthetic reimplementation only when the project explicitly requires it or no viable native backend exists.

Packaging Rules

Use find_namespace_packages(include=["cli_anything.*"])
Keep cli_anything/ as a namespace package without a top-level __init__.py
Expose cli-anything-<software> through console_scripts

Workflow

Acquire the source tree locally.
Analyze architecture, data model, existing CLIs, and GUI-to-API mappings.
Design command groups and state model.
Implement the harness.
Write TEST.md, then tests, then run them.
Update README usage docs.
Verify local installation with pip install -e .

Output Expectations

When reporting progress or final results, include:

target software and source path
files added or changed
validation commands run
open risks or backend limitations

Files

SKILL.md and 43 other files in macrocli of HKUDS/CLI-Anything.

SKILL.md
agent-harness/DEMO.md
agent-harness/MACROCLI.md
agent-harness/cli_anything/macrocli/README.md
agent-harness/cli_anything/macrocli/__init__.py
agent-harness/cli_anything/macrocli/__main__.py
agent-harness/cli_anything/macrocli/backends/__init__.py
agent-harness/cli_anything/macrocli/backends/base.py
agent-harness/cli_anything/macrocli/backends/file_transform.py
agent-harness/cli_anything/macrocli/backends/gui_agent.py
agent-harness/cli_anything/macrocli/backends/gui_macro.py
agent-harness/cli_anything/macrocli/backends/native_api.py
agent-harness/cli_anything/macrocli/backends/recovery.py
agent-harness/cli_anything/macrocli/backends/semantic_ui.py
agent-harness/cli_anything/macrocli/backends/visual_anchor.py
agent-harness/cli_anything/macrocli/core/__init__.py
… and 28 more

Open the folder on GitHubat commit 34f5195

Compare with similar skills

CLI-Anything Harness Builder next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

CLI-Anything Harness Builder compared with similar skills
Skill	Stars	Used in	Tokens	Auto-check	Licence	Repo updated
CLI-Anything Harness Builder this skillHKUDS/CLI-Anything	52k	—	~839	Automated safety check: Pass	Apache-2.0	16 days ago
Langgraph Testing Evaluationsoba-labs/langchain-agent-skills	107	—	~2.3k	Automated safety check: Pass	MIT	1 mo ago
Mirage VFS Adapter Authoringstrukto-ai/mirage	3.7k	—	~2.5k	Automated safety check: Pass	Apache-2.0	today
README and DESIGN Generatorfengshao1227/ccg-workflow	5.9k	—	~410	Automated safety check: Notes	MIT	23 days ago
Project Scaffolderpretend1111/claude-desktop-app	494	1 repos	~498	Automated safety check: Pass	Custom licence	5 mo ago
Compare Codegenhw-native-sys/pypto	126	—	~1.4k	Automated safety check: Pass	Custom licence	8 days ago

Similar skills

Langgraph Testing Evaluation
soba-labs/langchain-agent-skills
A skill your agent uses when you need to test or evaluate LangGraph/LangChain agents: writing unit or integration tests, generating test scaffolds, mocking LLM/tool behavior, running trajectory…
107 GitHub stars~2.3k tokensUpdated 1 mo ago
AI & LLM EngineeringAuto-check passed
Mirage VFS Adapter Authoring
strukto-ai/mirage
Builds or extends a custom Mirage virtual filesystem adapter for an API, database, object store or app data, with a working mount configuration and filesystem tests.
3.7k GitHub stars~2.5k tokensUpdated today
DevelopmentAuto-check passed
README and DESIGN Generator
fengshao1227/ccg-workflow
Generates README.md and DESIGN.md skeletons for a module by scanning its structure with a Node script, then lists what to fill in by hand.
5.9k GitHub stars~410 tokensUpdated 23 days ago
DevelopmentAuto-check: notes
Project Scaffolder
pretend1111/claude-desktop-app
Scaffolds a complete, runnable project from scratch, covering web, Python and Node.js projects, with a working entry point and no placeholder code.
494 GitHub starsUsed in 1 repo~498 tokens
DevelopmentAuto-check passed
Compare Codegen
hw-native-sys/pypto
Compare codegen output (.pto files and pass dumps) between origin/main and the current branch for a given test case.
126 GitHub stars~1.4k tokensUpdated 8 days ago
DevelopmentAuto-check passed
Core PR Helper
calimero-network/core
Suggests one appropriate branch name and a PR description in the project template (title, Description, Test plan, Documentation update) for Calimero core.
171 GitHub stars~614 tokensUpdated yesterday
DevelopmentAuto-check passed

Questions about CLI-Anything Harness Builder

What does CLI-Anything Harness Builder do?

Builds, refines, tests or validates a CLI-Anything harness that wraps a GUI application or source repository as a stateful Click CLI with JSON output and a REPL mode. The skill adapts the CLI-Anything methodology to OpenClaw without changing the generated Python harness format. It accepts a local source path or a GitHub repository URL and derives the software's name from its directory.

When should I use CLI-Anything Harness Builder?

CLI-Anything Harness Builder fits situations like: wrapping a GUI application as a scriptable command-line harness; adding missing commands to an existing CLI-Anything harness; writing unit and end-to-end tests for a generated harness; validating that a harness follows the CLI-Anything packaging layout.

How do I install CLI-Anything Harness Builder in Claude Code?

Run `npx skills add HKUDS/CLI-Anything --skill cli-anything -a claude-code`. Or copy the skill folder (macrocli in HKUDS/CLI-Anything) into .claude/skills/cli-anything in your project. Claude Code loads it when a task matches its description.

How do I install CLI-Anything Harness Builder in Codex?

Run `npx skills add HKUDS/CLI-Anything --skill cli-anything -a codex`. Or copy the skill folder (macrocli in HKUDS/CLI-Anything) into .agents/skills/cli-anything in your project. Codex loads it when a task matches its description.

Can I use CLI-Anything Harness Builder in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add HKUDS/CLI-Anything --skill cli-anything -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/cli-anything, .gemini/skills/cli-anything, .github/skills/cli-anything and .opencode/skills/cli-anything in your project.

What does CLI-Anything Harness Builder need to run?

Going by SKILL.md and its folder, CLI-Anything Harness Builder needs Python for the scripts in its folder and the command-line tools its instructions call (pip). Our summary lists: Python, for the generated Click-based harness.

Does CLI-Anything Harness Builder access the network?

SKILL.md contains no URLs. Its commands use pip, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is CLI-Anything Harness Builder safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does CLI-Anything Harness Builder use?

CLI-Anything Harness Builder is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does CLI-Anything Harness Builder use?

About 839 tokens (SKILL.md is roughly 3.4k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to CLI-Anything Harness Builder?

Skills that share tags, products or a category with CLI-Anything Harness Builder: Langgraph Testing Evaluation (soba-labs/langchain-agent-skills, 107 stars), Mirage VFS Adapter Authoring (strukto-ai/mirage, 3.7k stars), README and DESIGN Generator (fengshao1227/ccg-workflow, 5.9k stars) and Project Scaffolder (pretend1111/claude-desktop-app, 494 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains CLI-Anything Harness Builder?

HKUDS (a GitHub organization) maintains it in HKUDS/CLI-Anything, which has 51,696 GitHub stars. The repository holds 78 skills in this directory. The repository was last updated on September 22, 2026.

Source: HKUDS/CLI-Anything on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.

Install CLI-Anything Harness Builder

Facts

At a glance

What it does

When your agent uses it

Example prompts

Requirements

Workflow steps

What it can do on your machine

Tool permissions

Runs code

Network

Credentials

Context cost

Safety

SKILL.md

CLI-Anything for OpenClaw

Inputs

Modes

Build

Refine

Test

Validate

Backend Rules

Packaging Rules

Workflow

Output Expectations

Files

Compare with similar skills

Similar skills

More from HKUDS/CLI-Anything

Related

Questions about CLI-Anything Harness Builder