ace

Coordinate multiple AI agents in parallel with persistent state and atomic commits.

22|11|Updated Jan 11, 2026
One-click install
npx skills add https://github.com/AgriciDaniel/ace-claude-code --skill ace
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: ace
Source: https://github.com/AgriciDaniel/ace-claude-code/tree/main/.ace
Command: npx skills add https://github.com/AgriciDaniel/ace-claude-code --skill ace

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) components.

What problem does it solve?

Ace coordinates multiple AI agents to orchestrate tasks in parallel while preserving state across sessions, enabling reliable multi-phase workflows with traceability.

Core Features & Use Cases

  • Deterministic parallel execution with Team Leads and unlimited mini-agents
  • Persistent state across sessions, handoffs, and checkpoints
  • Atomic per-task commits for full traceability and auditability
  • Use Case: orchestrate a complex project from planning to verification with clear provenance and state management

Quick Start

Activate Ace and define a project, set ROADMAP and STATE, then execute plans in parallel while preserving context and commit history.

Frequently Asked Questions about ace

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

FAQPage Schema
How do I coordinate multiple AI agents to run tasks in parallel?

You can coordinate multiple AI agents for parallel execution by using a Team Lead structure with mini-agents, defining a project roadmap and state, then executing plans in parallel while preserving context across sessions.

What is persistent state management for AI agents and when do I need it?

Persistent state management for AI agents preserves execution context across sessions and checkpoints. You need it for complex multi-phase projects requiring reliable handoffs, traceability, and continuous workflow orchestration without losing progress.

How do I ensure full traceability when orchestrating complex multi-phase projects?

To ensure full traceability in multi-phase project orchestration, you enforce atomic per-task git commits for each completed operation, providing a deterministic audit trail of changes made by every mini-agent during parallel execution.

Can I preserve AI agent state across sessions and handoffs without losing context?

Yes, you can preserve AI agent state across sessions and handoffs by leveraging planning and execution templates that maintain persistent state, ensuring context survives checkpoints and session restarts during complex workflows.

What's the best way to structure parallel execution for AI agents working on the same project?

The best way to structure parallel AI agent execution is assigning a Team Lead to orchestrate unlimited mini-agents, setting a clear roadmap and state, and executing tasks concurrently with atomic commits for deterministic results.

Do I need specific dependencies to orchestrate AI agents with persistent state?

No specific external dependencies are required to orchestrate AI agents with persistent state. The coordination capability operates using internal planning templates, execution scripts, and state management references without external libraries.