This guide documents specialized agents and when to use them for maximum efficiency.

This project uses multiple LLM/AI systems for development. **ALL agent-specific documentation must be synchronized across systems** - this includes commands, workflows, slash commands, skills, and any

import { defineConfig } from 'vitest/config';

This document defines the specialized subagents used by the TaskPilot Blueprint skill to generate production-ready task management applications.

Quand une tache passe en **TESTING** dans ClickUp, les agents suivants interviennent dans l'ordre. La tache ne peut passer en **TERMINE** qu'apres validation complete.

Subagents run in isolated context windows — they do NOT inherit the parent's tools, middleware, system_prompt, or skills. Everything must be specified explicitly.

Use these specialized agents when working on different aspects of the project. Each agent has specific expertise and follows the project rules.

**Purpose**: Understanding how agents work in OpenAgents Control

Complete reference for all 30 specialized agents in the oh-my-claudecode system.

This supplements the root `AGENTS.md` with Codex-specific guidance.

Documentation for the Trellis agent system - specialized AI agents for different development phases.

> Create and use specialized AI subagents in Claude Code for task-specific workflows and improved context management.

Complete reference for creating and managing specialized agents in Claude Code.

cfn-optimize-agents

Agente especializado em Agentes (Daemons, Workers, Background Jobs, LLM Agents)

Elite app development agent that uses /serena command for token-efficient, structured problem-solving. Specializes in creating applications, implementing components, APIs, systems, and tests with maximum efficiency. Examples: <example>Context: User needs to create a new React component. user: 'I need to implement a data table with sorting and filtering' assistant: 'I'll use /serena to efficiently design and implement this component with all features' <commentary>Component creation benefits from /serena's structured approach for clean, maintainable code.</commentary></example> <example>Context: User is building a new API endpoint. user: 'Help me create a REST API for user management' assistant: 'Let me use /serena to architect this API with proper patterns and security' <commentary>API development requires systematic design that /serena provides efficiently.</commentary></example>

**Project:** B3 AI Analysis Platform

This document covers sophisticated RAG patterns including agents, query engines, multi-agent systems, and advanced architectural patterns for production deployments.

Create project-specific specialist agents from global templates.

This guide provides comprehensive instructions for creating research-driven, high-quality subagents that extend Claude's capabilities in specific domains.

Subagents let you delegate specific subtasks to specialized agents. They're isolated—separate conversations with independent context. This keeps main threads focused while letting parallel agents hand

> Create and use specialized AI subagents in Claude Code for task-specific workflows and improved context management.

- Multi-step tasks requiring specialized expertise

> Rules and conventions are in `/CLAUDE.md`. This file is for Claude-specific agent orchestration.

All agents run via Claude Code CLI and use skills in `.claude/skills/`.

TypeScript agents for specialized workflows. Uses Claude Agent SDK for context-aware reasoning.

This project includes six specialized subagents located in `.claude/agents/`. Each agent is invoked via the Agent tool or by Claude Code automatically when the task matches the agent's description.

Tested Jan 8-9, 2025. Consolidated for autonomous workflow.

You are the primary coding agent for this workspace.

Complete specifications for all 37 specialized agent types in the Loki Mode multi-agent system.

<!-- slot:neutral-body -->

**CRITICAL PARADIGM SHIFT**: You are a hands-on implementer who makes heavy use

Total agents discovered: 57

You are Claude Code's **Agent Generator** - focused exclusively on analyzing the project and creating specialized AI agents.

This repository uses specialized Claude Code subagents to handle specific workflows. Each agent has minimal tool permissions following least-privilege principles.

| Agent | Model | Best For | Key Trait |

This project uses **uv** as the package manager for all Python operations.

'Create agent placeholder/spec files'

Use agent-browser CLI to automate browser testing and verification of web applications.

**Non-Claude agents**: Import `../CLAUDE.md` for full context, or specific `SKILL.md` files here.

Specialized subagents for Weave workflow. Use via the Agent tool with the appropriate

This project uses pytest for unit testing.

This document provides specialized guidance for AI agents (autonomous task executors) working on the streamlit-lightweight-charts-pro codebase.

> **Cerebro En Las Nubes** - Sistema Multi-Agente para Restobar

**Version:** 1.0.0

**Responsibilities:**

<!-- Parent: sf-ai-agentforce-testing/SKILL.md -->

Define and invoke subagents to isolate context, run tasks in parallel, and apply specialized instructions in your Claude Agent SDK applications.

Claude can spawn parallel workers (subagents) to handle tasks simultaneously. You don't need to do anything special -- skills invoke this automatically when it helps.

Five specialized agents collaborate to ship features with production quality.