Expert task distributor specializing in intelligent work allocation, load balancing, and queue management.
Map tasks to specialist agents. Use when choosing which agent for a job, comparing agent capabilities, or routing to React/Next.js/Playwright/docs/code-quality experts.
Shape ambiguous or frontier-agent work into a bounded agent task with outcome, scope, context, tools, autonomy level, and verification evidence.
Produces a peer-voiced teaching document (learning guide, letter, reflection, or protocol) that transfers a skill or insight without creating an expert-to-student dynamic.
에이전트 팀 구성 및 조율 스킬. 여러 Claude Code 인스턴스를 팀으로 구성하여 병렬 작업을 수행한다. 공유 태스크 목록, 에이전트 간 메시징, 파일 소유권 분리, 계획 승인 워크플로우를 지원한다.
Designs and deploys custom agent teams for specific business workflows. Interactive discovery of business processes, then generates complete team configurations with specialized…
Codex CLI로 병렬 구현할 때 사용. multi_agent 기능으로 default/explorer/worker를 조합해 실행. zephermine 섹션 모드와 자유 모드 지원. /agent-team, /poseidon, /agent-team-codex로 실행.
Use when executing a team-format implementation plan (produced by writing-plans-for-teams) — orchestrates a team of persistent specialist agents working in parallel with two-stage…
Orchestrate full-stack development with Agent Teams for parallel implementation. Use when the user says "build with a team", "develop in parallel", "spin up an Agent Team", or…
Agent Teams スキルを設計・構築するためのベストプラクティスガイド。 サブエージェント定義、SendMessage 通信プロトコル、タスク依存管理、 PostToolUse Hook によるログ、MCP ツール統合、コンテキストファイル設計を網羅。 7つの実績あるチームスキル（app-naming, ui-review, logo-design,…
Framework for self-sustaining AI agent teams with self-service work queues, role ownership, continuous discovery, and proactive operation via heartbeat loops.
Service-level skill for agent-team operational commands. Use for run hygiene, message inspection, event history, schema export, audits, and tooling. Load agent-team-shared first.
Orchestrate multi-agent teams with defined roles, task lifecycles, handoff protocols, and review workflows.
Claude Code のエージェントチーム構成を設計するスキルです。 品質向上（別セッションでの再鑑・多角的レビュー）を主目的としたチーム構成を対話形式で提案します。 次のような場面で積極的に使ってください： - エージェントチームやマルチエージェントの話題が出たとき - 実装・設計の品質を別の視点でチェックしたいとき -…
Shared runtime procedure for the agent-team CLI. Use for daemonless state, global flags, JSON input/output, state directory rules, error handling, and shell usage conventions.
Claude Code Agent Teams - default team-based development with strict TDD pipeline enforcement
Ender's Game approach to commanding Claude Code Agent Teams. Strategic multi-agent orchestration with Karpathy Agentic Engineering principles — plan, act, observe, iterate.
Designs and coordinates Claude Code Agent Teams — multi-agent collaboration where teammate sessions work in parallel with direct communication, task claiming via file locks, and…
Generate custom agent from template. Use when creating a new subagent from scratch, or scaffolding an agent file with correct frontmatter.
Agent-to-Agent (A2A) communication protocol. Connect two or more Claude agents that pass messages, share context, delegate tasks, and collaborate.
Define tools for the support agent. Use when adding new capabilities like refund processing, license transfer, knowledge lookup, or any agent action.
Tools are how AI agents interact with the world. A well-designed tool is the difference between an agent that works and one that hallucinates, fails silently, or costs 10x more…
Design et implémentation de systèmes de tool calling pour agents IA. Function calling, API wrapping, schema design.
Designs agent tools and builds MCP servers (tool schemas, naming, error shapes, auth, context-efficient results) when exposing capabilities to an LLM agent or scaffolding a Model…
Use this agent when you need complete, production-ready scaffolding for new components or systems. Invoke proactively when starting net-new features that require architectural…
Run 150+ AI apps via inference.sh CLI - image generation, video creation, LLMs, search, 3D, Twitter automation.
Run 250+ AI apps via inference.sh CLI - image generation, video creation, LLMs, search, 3D, Twitter automation.
Run 150+ AI apps via inference.sh CLI - image generation, video creation, LLMs, search, 3D, Twitter automation.
Run 150+ AI apps via inference.sh CLI - image generation, video creation, LLMs, search, 3D, Twitter automation.
Run 150+ AI apps via inference.sh CLI - image generation, video creation, LLMs, search, 3D, Twitter automation.
Run 150+ AI apps via inference.sh CLI - image generation, video creation, LLMs, search, 3D, Twitter automation.
Run 150+ AI apps via inference.sh CLI - image generation, video creation, LLMs, search, 3D, Twitter automation.
Run 150+ AI apps via inference.sh CLI - image generation, video creation, LLMs, search, 3D, Twitter automation.
Run 250+ AI apps via inference.sh CLI - image generation, video creation, LLMs, search, 3D, Twitter automation.
Run 250+ AI apps via inference.sh CLI - image generation, video creation, LLMs, search, 3D, Twitter automation.
Run 150+ AI apps via inference.sh CLI - image generation, video creation, LLMs, search, 3D, Twitter automation.
Run 250+ AI apps via inference.sh CLI - image generation, video creation, LLMs, search, 3D, Twitter automation.
Run 250+ AI apps via inference.sh CLI - image generation, video creation, LLMs, search, 3D, Twitter automation.
Run 250+ AI apps via inference.sh CLI - image generation, video creation, LLMs, search, 3D, Twitter automation.
Run 250+ AI apps via inference.sh CLI - image generation, video creation, LLMs, search, 3D, Twitter automation.
Use when designing or reviewing Agentforce topic structure, including topic boundaries, instruction quality, handoff rules, out-of-scope behavior, and topic-selector strategy.
Use when an agent trace, prompt, tool call, screenshot, retrieval result, or model output may become a log, memory item, eval case, ticket, incident note, training example, or…
Use when the user asks to "map a session", "show me the tree", "agent-tree", "/agent-tree", "resume from a node", "fork from this session", or wants to navigate / restart from a…
Expert trend analyst specializing in identifying emerging patterns, forecasting future developments, and strategic foresight.
Use this agent to capture and categorize incoming issues, bugs, and feature requests during rapid development.
Analyze type design for encapsulation, invariant expression, usefulness, and enforcement.
Batteries-included agent component for React/Next.js from ui.inference.sh. One component with runtime, tools, streaming, approvals, and widgets built in.
Batteries-included agent component for React/Next.js from ui.inference.sh. One component with runtime, tools, streaming, approvals, and widgets built in.
\"Batteries-included agent component for React/Next.js from ui.inference.sh. One component with runtime, tools, streaming, approvals, and widgets built in.
Build or modify Fleet Pi's React Agent Elements UI, including InputBar controls, tool cards, question prompts, resource drawer, model picker, mode selector, and streaming state.
Agent skill for v3-integration-architect - invoke with $agent-v3-integration-architect
Agent skill for v3-performance-engineer - invoke with $agent-v3-performance-engineer
Validate agent YAML frontmatter and configuration. Use before committing agent changes or in CI.
Decide whether a feature should be built as an Agentforce Agent, a Flow, an Apex Trigger, or other mechanism.
Orchestrate a wave of parallel agents over the plan/todo queue in a documentation-led repo — asks how many agents, the budget (items/waves, with hours as a soft cap), and whether…
Construction d'un sous-agent spécialisé dans la collecte de données web pour un agent parent. Crawling, extraction, parsing et retour structuré.
End a session and write back durable knowledge. Use at the end of every work session. Extracts what's worth keeping, proposes wiki updates, and executes after user approval.
Deep audit of the wiki and repo-vs-wiki gap assessment. Use weekly or when things feel stale. Scans every page, finds contradictions, orphans, dead links, unsourced claims, stale…
Mid-session checkpoint. Use when you want to check progress, detect scope drift, capture emerging knowledge, or do a quick wiki health check without ending the session.
Begin an agent-wiki session. Reads the wiki, detects tensions between wiki content and actual state, briefs you, asks socratic questions, and proposes a session plan.