Act

Overview Act runs GitHub Actions workflows locally using Docker. Test and debug CI pipelines without pushing to GitHub. Supports most GitHub Actions features.

Overview

The Act skill, sourced from the TerminalSkills/skills repository on GitHub, allows AI agents to execute GitHub Actions workflows in a local environment. By utilizing Docker containers to simulate GitHub runners, this tool enables developers to test and debug CI/CD pipelines without the need for frequent commits or remote execution. It supports a broad array of standard GitHub Actions features, providing a reliable way to validate automation logic and syntax. This skill is compatible with various AI agents, including Claude and Gemini, facilitating a more efficient DevOps workflow by offering immediate feedback on pipeline configurations within the local development setup.

Use Cases

Local debugging of GitHub Actions workflows to identify and fix syntax errors.
Testing CI/CD pipeline modifications without triggering remote GitHub runners.
Validating automation scripts within a controlled Docker-based environment.

Install Notes

# Review source first
open https://github.com/TerminalSkills/skills/blob/main/skills/act/SKILL.md

Copy or clone the skill folder into your agent skills directory after reviewing its instructions and scripts.

Security Notes

The Act skill requires a functional Docker installation on the host machine to manage containerized workflow execution. Users must manage local secrets and environment variables carefully, as the tool interacts directly with the local container runtime to replicate GitHub's infrastructure.

Related Skills

Core

vercel-labs/agent-browser

DevOps

Core agent-browser usage guide. Read this before running any agent-browser commands. Covers the snapshot-and-ref workflow, navigating pages, interacting with elements (click, fill, type, select), extracting text and data, taking screenshots, managing tabs, handling forms and auth, waiting for content, running multiple

CodexClaude
reacttesting
37,057 starsSource linked

Agent Browser

vercel-labs/agent-browser

DevOps

Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to "open a website", "fill out a form", "click a button",

CodexClaude Code
testingbrowser
37,057 starsSource linked

Agentcore

vercel-labs/agent-browser

DevOps

Run agent-browser on AWS Bedrock AgentCore cloud browsers. Use when the user wants to use AgentCore, run browser automation on AWS, use a cloud browser with AWS credentials, or needs a managed browser session backed by AWS infrastructure. Triggers include "use agentcore", "run on AWS", "cloud browser with AWS", "bedroc

CodexClaude
browserautomation
37,057 starsSource linked

LangChain Middleware

langchain-ai/langchain-skills

DevOps

INVOKE THIS SKILL when you need human-in-the-loop approval, custom middleware, or structured output. Covers HumanInTheLoopMiddleware for human approval of dangerous tool calls, creating custom middleware with hooks, Command resume patterns, and structured output with Pydantic/Zod.

Claude
typescriptpython
817 starsSource linked

Deep Agents Core

langchain-ai/langchain-skills

DevOps

INVOKE THIS SKILL when building ANY Deep Agents application. Covers create_deep_agent(), harness architecture, SKILL.md format, and configuration options.

Claude
typescriptpython
817 starsSource linked

LangGraph Persistence

langchain-ai/langchain-skills

DevOps

INVOKE THIS SKILL when your LangGraph needs to persist state, remember conversations, travel through history, or configure subgraph checkpointer scoping. Covers checkpointers, thread_id, time travel, Store, and subgraph persistence modes.

CodexClaude
typescriptpython
817 starsSource linked