Analyze agent performance, identify capability gaps, and propose improvements using the Evolution System.
Skills(SKILL.md)は、AIエージェント(Claude Code、Cursor、Codexなど)に特定の能力を追加するための設定ファイルです。
詳しく見る →Analyze agent performance, identify capability gaps, and propose improvements using the Evolution System.
Run this command to automatically spawn parallel subagents to fix skipped/failing tests.
Run this command to automatically spawn parallel subagents to optimize the slowest validators.
List all agents in a plan with their status, features, and clickable links. Helps you find and select which specific agent to run.
> ## Documentation Index
This guide explains how to create new agents in the agent system that handle full workflow execution and artifact creation.
Dynamic agent instantiation based on task requirements with role assignment, context isolation, permission scoping, and resource allocation
This project implements a sophisticated 3-tier agentic framework specifically designed for Claude Code, providing hierarchical specialization and intelligent task delegation across full-stack developm
You can generate agents using a specialized agent that acts as a generator. This agent will help you scaffold new agents.
Subagents are specialized AI assistants with their own context window, custom system prompts, and configurable tool access. They're invoked automatically or explicitly for task-specific workflows.
**Analysis of which specialized agents would improve development efficiency**
<file_format>
> Source: https://code.claude.com/docs/en/sub-agents
loadout has three agents for automated workflows:
**Command:** `/utility:trinity-agents`
Generate specialized agent prompts for the new workflow (Step 4).
Orchestrate FrankX.AI agents for website content creation and strategy
**ALWAYS** use the appropriate specialized sub-agent for the task at hand.
**9 intelligent specialists** with automatic activation for ATDD workflows.
Policy
This file defines 25 specialized AI agents for Specification Driven Development across all platforms.
<core_challenges>
**この reference を読むタイミング**: skill を新規作成 / 編集するとき、デプロイ前に pressure 下でも動作するか / rationalization に耐えるか検証するために参照する。
When working with AI agents in the `agents/` directory:
Agent delegation system for Claude Code GoDev framework using native Task tool integration.
These notes orient future agents working on this repository—especially ongoing multi-tenancy hardening—so changes stay consistent and low-disruption.
- In all interactions and commit messages, be extremely concise and sacrifice grammar for the sake of concision.
Agents are specialized subprocesses that handle specific tasks with isolation and tool restrictions.
**Portfolio Project:** omer-akben AI-powered portfolio
Show available workers and their capabilities
This directory contains **extended documentation** for specialized agents. The actual executable agents are in `.claude/agents/`.
A comprehensive guide to how the 26 specialized agents work together as a high-performance team across 5 guilds.
This repository is for Indek, a COD-native courier operations platform. Agents working here should preserve the product framing and keep code and docs aligned.
Detect this project's tech stack and deploy specialized subagents. Use when starting a new project or when the tech stack has changed.
This document covers **forked-context primitives** (Tasks) and the **Agent component** that uses them for building specialized workers with persistent personas and bundled capabilities.
MedAssist AI runs **7 specialized AI agents** coordinated by an **Agent Orchestrator**. Every agent extends `BaseAgent`, uses OpenAI function calling, and accesses data exclusively through a tool laye
Deploy MANE agents using systematic batch protocol with user testing
This document describes the specialized subagents used by the Render deployment skill to automate backend deployment to Render.com.
**Humans steer, agents execute.** Read this fully at session start.
*Reference for **[workflow-discussion-process](../SKILL.md)***
Índice de todos los agentes especializados disponibles en este proyecto.
Orchestrate sub-agents with specialized personas to work on tasks in parallel: $ARGUMENTS
This document describes your five specialized agents and how they work together in a coordinated development workflow. Each agent has a specific role and expertise; combined, they form a complete pipe
**Version 1.0.0**
Specialized agents that do heavy work and return concise summaries to preserve
All agents in this system. Every agent has a defined role, owns specific skills, and follows strict financial and architectural rules.
<!-- Snapshot: 2026-03-27 | Source: https://code.claude.com/docs/en/sub-agents.md -->
*Simple principles for creating effective specialized AI assistants*
This file defines specialized agents for common tasks in this repository.
This document provides comprehensive guidelines for using Claude Code's Task tool to delegate complex, multi-step tasks to specialized agents during ToddleToy development.