Cli Anything Macrocli logo

Cli Anything Macrocli

OrganizationPopular
HKUDS
cli-anything-macrocli

Use when the agent wants to define, list, inspect, or execute GUI macros via the MacroCLI CLI. Macros are parameterized, CLI-callable workflows — the agent invokes `macro run <name>` and the system handles backend routing (plugin, file transform, accessibility, compiled GUI replay).

Overview

PublisherHKUDS
RepositoryCLI-Anything
Skill namecli-anything-macrocli
Stars
49.5K
Forks
4.6K
Bundled files
Instructions only
LicenseApache-2.0
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by HKUDS on GitHub. Read the source before you install it.

Installation

Install the Cli Anything Macrocli AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/HKUDS/CLI-Anything.git /tmp/CLI-Anything
mkdir -p .claude/skills
cp -r /tmp/CLI-Anything/macrocli/agent-harness/cli_anything/macrocli/skills .claude/skills/cli-anything-macrocli
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Cli Anything Macrocli in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Cli Anything Macrocli on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Cli Anything Macrocli is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

MacroCLI CLI

What It Is

The MacroCLI converts valuable GUI workflows into parameterized, CLI-callable macros. Agents never touch the GUI directly — they call macros through this stable CLI, and the runtime routes execution to the best available backend (native plugin/API, file transformation, semantic UI control, or precompiled GUI macro replay).

Installation

bash
cd macrocli/agent-harness
pip install -e .

Requirements: Python 3.10+, PyYAML, click, prompt-toolkit.

Quick Start (for agents)

bash
# 1. See what macros are available
cli-anything-macrocli macro list --json

# 2. Inspect a macro's parameters
cli-anything-macrocli macro info export_file --json

# 3. Dry-run to check params without side effects
cli-anything-macrocli --dry-run macro run export_file \
    --param output=/tmp/test.txt --json

# 4. Execute a macro
cli-anything-macrocli macro run export_file \
    --param output=/tmp/result.txt --json

# 5. See what backends are available
cli-anything-macrocli backends --json

Command Reference

Global Flags

FlagDescription
--jsonMachine-readable JSON output on stdout
--dry-runSimulate all steps, skip side effects
--session-id <id>Resume or create a named session

macro group

CommandDescription
macro listList all available macros
macro info <name>Show macro schema (parameters, steps, conditions)
macro run <name> --param k=vExecute a macro
macro dry-run <name> --param k=vSimulate without side effects
macro validate [name]Structural validation
macro define <name>Scaffold a new macro YAML

session group

CommandDescription
session statusShow session statistics
session historyShow recent run history
session savePersist session to disk
session listList all saved sessions

backends

bash
cli-anything-macrocli backends --json
# Shows: native_api, file_transform, semantic_ui, gui_macro, recovery
# and whether each is available in the current environment.

Macro Parameters

Pass parameters with --param key=value. Repeat for multiple:

bash
cli-anything-macrocli macro run transform_json \
    --param file=/path/to/data.json \
    --param key=settings.theme \
    --param value=dark \
    --json

Output Format (--json)

All commands output JSON when --json is set:

json
{
  "success": true,
  "macro_name": "export_file",
  "output": {
    "exported_file": "/tmp/result.txt"
  },
  "error": "",
  "telemetry": {
    "duration_ms": 312,
    "steps_total": 2,
    "steps_run": 2,
    "backends_used": ["native_api"],
    "dry_run": false
  }
}

On failure ("success": false), read the "error" field for the reason. Exit code is 1 on failure.

Execution Backends

Backends are selected automatically based on the macro step definition:

BackendTriggered byUse case
native_apibackend: native_apiSubprocess / shell command
file_transformbackend: file_transformXML, JSON, text file editing
semantic_uibackend: semantic_uiAccessibility / keyboard shortcuts
gui_macrobackend: gui_macroPrecompiled coordinate replay
recoverybackend: recoveryRetry / fallback orchestration

Writing Macros

Macros are YAML files in cli_anything/macrocli/macro_definitions/. Scaffold one with:

bash
cli-anything-macrocli macro define my_macro --output \
    cli_anything/macrocli/macro_definitions/examples/my_macro.yaml

Minimal schema:

yaml
name: my_macro
version: "1.0"
description: What this macro does.

parameters:
  output:
    type: string
    required: true
    description: Where to write results.
    example: /tmp/result.txt

preconditions:
  - file_exists: /path/to/input

steps:
  - id: step1
    backend: native_api
    action: run_command
    params:
      command: [my-app, --export, "${output}"]
    timeout_ms: 30000
    on_failure: fail  # or: skip, continue

postconditions:
  - file_exists: ${output}
  - file_size_gt: [${output}, 100]

outputs:
  - name: result_file
    path: ${output}

agent_hints:
  danger_level: safe  # safe | moderate | dangerous
  side_effects: [creates_file]
  reversible: true

Agent Usage Rules

  1. Always use --json for programmatic output.
  2. Use --dry-run to validate params before executing side-effectful macros.
  3. Check success field — do not assume success from exit code alone.
  4. Read error field when success is false — it explains what failed.
  5. Use macro info <name> to discover params before calling macro run.
  6. Use absolute paths for all file parameters.

Example Workflow

bash
# Step 1: What's available?
cli-anything-macrocli macro list --json

# Step 2: What params does transform_json need?
cli-anything-macrocli macro info transform_json --json

# Step 3: Test safely
cli-anything-macrocli --dry-run macro run transform_json \
    --param file=/tmp/config.json \
    --param key=theme \
    --param value=dark --json

# Step 4: Execute for real
cli-anything-macrocli macro run transform_json \
    --param file=/tmp/config.json \
    --param key=theme \
    --param value=dark --json

Version

1.0.0

Frequently asked questions

What does the Cli Anything Macrocli AI skill do?

Use when the agent wants to define, list, inspect, or execute GUI macros via the MacroCLI CLI. Macros are parameterized, CLI-callable workflows — the agent invokes `macro run <name>` and the system handles backend routing (plugin, file transform, accessibility, compiled GUI replay).

Why use Cli Anything Macrocli on TypingMind?

Because you install it once and use it with any model. Cli Anything Macrocli is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Cli Anything Macrocli in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/HKUDS/CLI-Anything/tree/main/macrocli/agent-harness/cli_anything/macrocli/skills. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Cli Anything Macrocli?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Cli Anything Macrocli?

As many as you like. As long as a model supports skills, you can use Cli Anything Macrocli with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Cli Anything Macrocli AI skill free?

Yes. It is published on GitHub by HKUDS under the Apache-2.0 license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇