Hyva Exec Shell Cmd logo

Hyva Exec Shell Cmd

Organization
hyva-themes
hyva-exec-shell-cmd

Utility skill to detect Magento development environment and determine command wrapper. This skill should be used by other skills that need to execute shell commands in the Magento environment. It detects Warden, docker-magento, DDEV, and local environments and provides the appropriate command wrapper.

Overview

Publisherhyva-themes
Repositoryhyva-ai-tools
Skill namehyva-exec-shell-cmd
Stars
84
Forks
16
Bundled files
1
LicenseOSL-3.0
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.

  • 1 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by hyva-themes on GitHub. Read the source before you install it.

Installation

Install the Hyva Exec Shell Cmd 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/hyva-themes/hyva-ai-tools.git /tmp/hyva-ai-tools
mkdir -p .claude/skills
cp -r /tmp/hyva-ai-tools/skills/hyva-exec-shell-cmd .claude/skills/hyva-exec-shell-cmd
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Hyva Exec Shell Cmd 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 Hyva Exec Shell Cmd 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 Hyva Exec Shell Cmd 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.

Execute Shell Commands in Magento Environment

This utility skill detects the Magento development environment and provides the appropriate command wrapper for executing shell commands.

Usage

Other skills should reference this skill when they need to execute commands in the Magento environment. The detected wrapper ensures commands run in the correct context (container or local).

Step 1: Detect Environment

Important: Execute this script from the Magento project root directory, or provide the path as an argument.

Run this detection once at the start of any skill that needs to execute shell commands:

bash
<skill_path>/scripts/detect_env.sh [magento_root_path]

Where <skill_path> is the directory containing this SKILL.md file (e.g., .claude/skills/hyva-exec-shell-cmd).

The optional magento_root_path argument specifies the Magento installation directory. If omitted, the script uses the current working directory.

Output: warden, docker-magento, ddev, or local

Step 2: Apply Command Wrapper

Based on detected environment, wrap commands as follows:

EnvironmentCommand WrapperDescription
Wardenwarden env exec -T php-fpm bash -c "<command>"Docker environment managed by Warden
docker-magentobin/clinotty bash -c "<command>"Mark Shust's docker-magento setup
DDEVddev exec <command>DDEV containerized environment
LocalRun <command> directlyNative environment without containers

Examples

Single command

bash
# Warden
warden env exec -T php-fpm bash -c "bin/magento cache:clean"

# docker-magento
bin/clinotty bash -c "bin/magento cache:clean"

# DDEV
ddev exec bin/magento cache:clean

# Local
bin/magento cache:clean

Command with directory change

bash
# Warden
warden env exec -T php-fpm bash -c "cd vendor/hyva-themes/magento2-default-theme/web/tailwind && npm run build"

# docker-magento
bin/clinotty bash -c "cd vendor/hyva-themes/magento2-default-theme/web/tailwind && npm run build"

# DDEV
ddev exec bash -c "vendor/hyva-themes/magento2-default-theme/web/tailwind && npm run build"

# Local
cd vendor/hyva-themes/magento2-default-theme/web/tailwind && npm run build

Commands That Do NOT Require Wrapping

Some commands run on the host system and should NOT be wrapped:

  • composer commands (runs on host, not in container)
  • git commands
  • File operations on the host filesystem (ls, find, cp for files accessible from host)
  • warden CLI commands
  • ddev CLI commands

Integration Pattern

Skills that need to execute commands should:

  1. Reference this skill: "Use the hyva-exec-shell-cmd skill to determine the command wrapper"
  2. Detect environment once using Step 1
  3. Store the wrapper pattern for use throughout the skill
  4. Apply the wrapper to all container commands per Step 2

Running a Bundled Skill Script Inside the Environment

Some skills ship a helper script (e.g. a PHP script under scripts/) that must run through a PHP/Node interpreter. On a hardened host there is no local interpreter, and a skill installed at user level (~/.../skills/...) is not inside the project, so the container can't see it. Do not copy the script into the project tree: how files reach the container differs across environments (bind mounts, Mutagen, named volumes) and some paths are not synced at all (e.g. Warden serves var/, generated/, pub/static, pub/media from separate volumes, so a host-written file there never appears in the container).

Instead, stream the script into the interpreter over stdin — this is independent of the mount/sync strategy, needs no temp file, and needs no cleanup:

  1. Detect the environment (Step 1) and resolve the wrapper (Step 2).

  2. Containerized env — pipe the script to php /dev/stdin through the wrapper (use the non-TTY -T exec so stdin is forwarded). <skill_path> is the directory containing the calling skill's SKILL.md:

    bash
    # Warden
    cat "<skill_path>/scripts/<script>.php" | warden env exec -T php-fpm bash -c "php /dev/stdin [args]"
    
    # docker-magento
    cat "<skill_path>/scripts/<script>.php" | bin/clinotty bash -c "php /dev/stdin [args]"
    
    # DDEV
    cat "<skill_path>/scripts/<script>.php" | ddev exec bash -c "php /dev/stdin [args]"

    The script runs with the container's working directory at the project root, so a script that locates the project via getcwd() works unchanged. Capture stdout for the result.

    Script constraints for this method: the script must not also read from stdin (stdin carries the script itself), and must not rely on __FILE__/__DIR__ (it is /dev/stdin) — locate project files via getcwd() instead.

  3. local env: the host has no interpreter (removed during hardening). Do not attempt to run the script directly — report that a containerized dev environment (or a local interpreter) is required for this step.

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Hyva Exec Shell Cmd AI skill do?

Utility skill to detect Magento development environment and determine command wrapper. This skill should be used by other skills that need to execute shell commands in the Magento environment. It detects Warden, docker-magento, DDEV, and local environments and provides the appropriate command wrapper.

Why use Hyva Exec Shell Cmd on TypingMind?

Because you install it once and use it with any model. Hyva Exec Shell Cmd 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 Hyva Exec Shell Cmd in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/hyva-themes/hyva-ai-tools/tree/main/skills/hyva-exec-shell-cmd. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Hyva Exec Shell Cmd?

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 Hyva Exec Shell Cmd?

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

Is the Hyva Exec Shell Cmd AI skill free?

Yes. It is published on GitHub by hyva-themes under the OSL-3.0 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 👇