$ npx claude-code-templates@latest --command="automation/act" --yesRequires Claude Code. The command adds this command to your project's .claudedirectory — nothing runs on ToolZip's servers.
What's inside this command
Component source
Act - GitHub Actions Local Execution
Execute GitHub Actions workflows locally using act: $ARGUMENTS
Current Workflows
- Available workflows: !
find .github/workflows -name ".yml" -o -name ".yaml" | head -10 - Act configuration: @.actrc (if exists)
- Docker status: !
docker --version
Task
Execute GitHub Actions workflow locally:
- Setup Verification
act --version
- Verify Docker is running
- Check available workflows in .github/workflows/
- Workflow Selection
$ARGUMENTS
- If no workflow: List all available workflows
- Check workflow triggers and events
- Local Execution
- Use secrets from .env or .secrets
- Handle platform-specific runners
- Monitor execution and logs
- Debugging Support
--verbose for detailed output
- Use --dry-run for testing
- Use --list to show available actions
Example Commands
# List all workflows
act --list
# Run specific workflow
act workflow_dispatch -W .github/workflows/$ARGUMENTS.yml
# Run with secrets
act --secret-file .env
# Debug mode
act --verbose --dry-runRelated Claude Code Commands
Workflow Orchestrator
Orchestrate complex automation workflows with task dependencies, scheduling, and cross-platform execution
Ci Pipeline
Manage and automate CI/CD pipeline configuration with GitHub Actions, multi-environment support, and deployment strategies
Husky
Run comprehensive CI checks and fix issues until repository is in working state
Szamlazz
Issue, cancel, and fetch Hungarian invoices via the szamlazz.hu Agent API — with NAV taxpayer lookup and automatic partner cache
Generate Tests
Generate a complete test file for a specified source file or component. Use when the user explicitly asks to write, create, or generate tests for a specific file.
Ultra Think
Multi-framework structured analysis: surfaces hidden assumptions, generates competing solutions, stress-tests each with adversarial reasoning, and delivers confidence-calibrated recommendations
Catalog data and component content are sourced from the open-source davila7/claude-code-templates project (MIT license). ToolZip curates the listing and writes original descriptions; every component links back to its original source. Claude Code is a product of Anthropic. ToolZip is an independent catalog and is not affiliated with or endorsed by Anthropic.