atac

Name: atac
Availability: InStock
Author: atac-team

Build and execute AI agent workflows with a declarative trajectory CLI.

291|11|Updated Jan 14, 2026

Search Tags:#automation #workflow #cli #bash #mcp #trajectory #atac

Ready to run

npx skills add https://github.com/ATaC-team/ATaC --skill atac

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: atac
Source: https://github.com/ATaC-team/ATaC/tree/main/skills/atac
Command: npx skills add https://github.com/ATaC-team/ATaC --skill atac

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

ATaC provides a unified approach to building, recording, and replaying AI agent trajectories by combining declarative workflows with a CLI, reducing ad-hoc scripting overhead and improving reproducibility.

Core Features & Use Cases

Declarative trajectory DSL for loops, conditionals, and tool calls (MCP and Bash).
CLI commands for init, config, add-input, add-for, add-action, and nested sub-workflows.
Supports modular workflows and reusability via bash://run for sub-workflows; runs in a global working directory with -C/--cwd for context.

Quick Start

Create a new trajectory workspace with atac init demo and build a simple for-loop workflow, then run it with atac run demo.

Frequently Asked Questions about atac

High-intent search queries and answers about installing and using this skill.

FAQPage Schema

How do I orchestrate AI agent workflows with loops and conditionals across Bash and MCP?▼

AI agent workflows can be orchestrated using a declarative trajectory DSL that supports loops, conditionals, and tool calls across Bash and MCP environments. This enables deterministic tool orchestration and reduces ad-hoc scripting overhead.

What is a declarative trajectory language for AI automation?▼

A declarative trajectory language defines AI agent workflows structurally rather than through ad-hoc scripts. It allows you to specify loops, conditionals, and tool calls deterministically, improving the reproducibility of automated tasks.

How do I set up and run an AI workflow from the CLI?▼

To set up an AI workflow from the CLI, create a workspace using the init command, build a loop workflow using add-input, add-for, and add-action commands, then execute it with the run command.

Can I run nested sub-workflows for scalable automation?▼

Yes, you can run nested sub-workflows for scalable automation by invoking bash://run within your trajectory. This enables modular workflows and reusability while operating in a global working directory with context flags.

Does this workflow approach work with both Bash commands and MCP tools?▼

Yes, this workflow approach operates across both Bash commands and MCP tools. The trajectory DSL supports deterministic tool orchestration seamlessly across these environments without requiring separate scripts.

Why use a declarative DSL instead of ad-hoc Bash scripts for AI agent trajectories?▼

Using a declarative DSL for AI agent trajectories reduces ad-hoc scripting overhead and improves reproducibility. Unlike manual Bash scripts, it natively supports loops, conditionals, and modular sub-workflows for deterministic execution.