Hebrew Terminal Launcher

VerifiedSafe

Launch Claude Code in Git Bash with proper Hebrew/RTL text rendering.

Sby Skills Guide Bot
DevelopmentBeginner
7/23/2026
Claude Code
#hebrew#rtl#terminal#git-bash#claude-code

Recommended for

Automated summary

Launches Claude Code in a Git Bash (mintty) terminal with full Hebrew and RTL text support.

Strengths

  • Fixes Hebrew and RTL rendering issues common in PowerShell and VS Code integrated terminal.
  • Leverages mintty's native Unicode bidirectional support.
  • Optional Chrome browser automation mode for extended capabilities.

Limitations

  • Requires Git for Windows to be installed and accessible.
  • Opens a separate terminal window, which may disrupt workflow.
  • Windows-only (Git Bash).
When to use it

When you need to use Hebrew or other RTL scripts in Claude Code and your current terminal (PowerShell, VS Code) displays them incorrectly.

When not to use it

If you already use a terminal with proper bidirectional Unicode support (e.g., Windows Terminal, Linux/macOS terminals).

Security analysis

Safe
Quality score85/100

The skill only instructs running a local bash script from a fixed path inside the skill's own directory. There is no obfuscation, no remote execution, no destructive commands, and no data exfiltration risk. The script itself would need to be audited for safety, but the skill does not present inherent security threats.

No concerns found

How this analysis is made

Examples

Launch with Chrome automation
Open Claude Code in Hebrew-compatible terminal with Chrome browser automation.
Standard launch
Start Claude Code in a Git Bash terminal with full RTL support.

name: hebrew-terminal description: Launch Claude Code in Git Bash (mintty) with full Hebrew/RTL support. Use when Hebrew text displays incorrectly in PowerShell or VS Code terminal.

Hebrew Terminal Launcher

This skill launches Claude Code in a new Git Bash (mintty) terminal with proper Hebrew/RTL text rendering.

Why?

PowerShell and VS Code's integrated terminal don't properly support bidirectional (RTL) text rendering. Git Bash's mintty terminal has full Unicode bidirectional support.

Instructions

When the user invokes this skill:

  1. Ask if they want Chrome browser automation mode:

    • Option 1: Standard mode
    • Option 2: With Chrome (browser automation)
  2. Run the launch script with the appropriate mode:

    # For standard mode:
    bash ~/.claude/skills/hebrew-terminal/launch.sh
    
    # For Chrome mode:
    bash ~/.claude/skills/hebrew-terminal/launch.sh --chrome
    
  3. Tell the user a new terminal window will open with Claude Code.

Requirements

  • Git for Windows (https://git-scm.com/download/win)
  • Claude Code installed and in PATH

From the file to a first result

The download contains exactly the content displayed on this page. This copy may differ from the latest version in the source repository.

View the source and supporting files

This download contains SKILL.md only. Any scripts, references, templates and dependencies are not included. Get the required files from the source, preserving their directory structure, before continuing.

1. Download the file

Download SKILL.md

From the root of a test project, save the file as .skill-downloads/hebrew-terminal-launcher-mrwakc1i/SKILL.md, or use the command below. This folder is for inspecting the skill before installation.

Command for macOS/Linux or WSL: requires a POSIX shell and curl. On Windows without WSL, use the download button and create the folder manually.

mkdir -p '.skill-downloads/hebrew-terminal-launcher-mrwakc1i' && curl --fail --show-error --location 'https://skills-guides.com/api/skills/hebrew-terminal-launcher-mrwakc1i/download' --output '.skill-downloads/hebrew-terminal-launcher-mrwakc1i/SKILL.md.part' && mv '.skill-downloads/hebrew-terminal-launcher-mrwakc1i/SKILL.md.part' '.skill-downloads/hebrew-terminal-launcher-mrwakc1i/SKILL.md'

2. Check prerequisites

Read SKILL.md before using it. If it references scripts or external services, inspect them and prepare the required access in your test environment.

Original excerpt: Requirements

The platforms on this page are catalog indications. The paths below follow tool documentation; they do not prove this skill has been run in those tools. No minimum tool version is confirmed for this listing.

3. Load the skill

After inspection, copy the complete folder into your project using one of the commands below, then open a new tool session. The command stops if a folder with the same name already exists: compare the files before replacing it.

Claude Code
test -f '.skill-downloads/hebrew-terminal-launcher-mrwakc1i/SKILL.md' && test -s '.skill-downloads/hebrew-terminal-launcher-mrwakc1i/SKILL.md' && mkdir -p '.claude/skills' && test ! -e '.claude/skills/hebrew-terminal' && cp -R '.skill-downloads/hebrew-terminal-launcher-mrwakc1i' '.claude/skills/hebrew-terminal'

OpenSkills

OpenSkills must already be installed. The local install/read procedure is checked with OpenSkills 1.5.0, which requires Node.js ≥ 20.6.0. Catalog slugs are not resolved automatically.

Official OpenSkills installation
openskills install './.skill-downloads/hebrew-terminal-launcher-mrwakc1i'

openskills read 'hebrew-terminal-launcher-mrwakc1i'

Reading should display the installed file content and its base directory. It does not run the skill or install its dependencies.

For an agent that reads AGENTS.md, then sync the index. This command changes AGENTS.md: review the diff before using it.

openskills sync

Manual method or another tool: attach SKILL.md to a conversation, or open it in an agent that can read files. Include any required supporting resources. No universal folder is recognized by every tool.

4. Try a first task

Use a short, synthetic input: an API endpoint, a small document or an interface brief. In a new conversation, attach the file or give the agent its path, then adapt this request:

Read .skill-downloads/hebrew-terminal-launcher-mrwakc1i/SKILL.md and apply its instructions to this example: [describe a test input]. Identify any missing files, dependencies or access. Produce the result requested by the skill without inventing data or running unreviewed scripts.

Expected result: output matching the skill instructions, or a precise list of missing prerequisites. A read confirmation alone does not validate a first use. If an external resource is unavailable, that path remains untested.

Related skills