Loading...
Loading...
Found 28 Skills
Manage your team — create roles, assign tasks, spawn workers, and monitor progress
Run an autonomous, spec-driven development "saga" for medium-to-large features using an orchestrator agent and a fleet of worker subagents. Use this skill whenever the user invokes /saga, asks to autonomously build a sizable feature end-to-end with minimal human intervention, wants a comprehensive spec broken into milestones and tasks with airtight validation criteria before parallelized implementation, or wants an orchestrator to delegate implementation to worker agents while preserving its own context window. Trigger on phrases like "run a saga", "autonomously implement this feature", "spec it out then build it with subagents", "orchestrate this big feature end-to-end", or "build this with workers and validate each step". Also use this skill when asked to continue, resume, or pick up an existing saga from its saga directory (e.g. under ~/.sagas).
Activated when the user mentions LiteFlow (a lightweight Java rule engine/business orchestration framework). Coverage includes: components, EL rules (THEN/WHEN/IF/SWITCH/FOR/WHILE/ITERATOR, etc.), context, script components, rule configuration sources, configuration items, executors, AI Agent orchestration (ReAct Agent / liteflow-react-agent), testing and debugging, source code details.
PeachSolution 신규 모듈 개발을 조율하는 통합 팀 스킬. 준비된 DB 스키마와 Spec, ui-proto 기반 표준 모드 + Spec만 모드 + 자연어 prompt 모드를 지원. "팀으로 만들어줘", "풀스택 개발", "팀 개발", "백엔드+UI 전체 생성", "버그 수정해줘", "이 화면에 X 추가해줘", "API와 화면 같이 만들어줘", "백엔드만 만들어줘", "API만 만들어줘", "UI만 추가" 키워드로 트리거. mode=backend(API+Store) | ui(UI만) | fullstack(전체) 지원하며, mode/proto 없이 자연어 입력만으로도 즉흥적 버그 수정·기능 추가 가능. 대규모 작업은 기능 큐와 Contract Gate로 1차 완성도를 높이는 방향을 따른다. peach-team-e2e와 함께 하나의 개발-검증 납품 흐름을 이루되, E2E 검증 독립성은 유지한다. 팀 실행 방식은 요청 범위와 런타임 도구 가용성을 분석해 single-agent / role-queue / agent-team 중 선택한다. 기존 팀 개발 스킬의 개발 조율 역할을 대체하며, DB 생성은 peach-gen-db 선행 단계로 분리한다.
Build resumable multi-agent workflows with durable execution, tool loops, and automatic stream recovery on client reconnection.
Deep research powered by Exa. Use for lead generation, literature reviews, deep dives, competitive analysis, or any query where one search falls short, including phrases like 'research this', 'find everything about', 'find me all', or 'deep dive on'.
Claude Code Agent Teams - default team-based development with strict TDD pipeline enforcement
Expertise in using open-multi-agent, a TypeScript framework for building production-grade multi-agent AI teams with task scheduling, dependency graphs, and inter-agent communication.
Build production-ready LLM applications, advanced RAG systems, and intelligent agents. Implements vector search, multimodal AI, agent orchestration, and enterprise AI integrations. Use PROACTIVELY for LLM features, chatbots, AI agents, or AI-powered applications.
Multi-model consensus council for validation, research, and brainstorming. Spawns parallel judges with configurable perspectives and optional explorer sub-agents using runtime-native backends (Codex sub-agents or Claude teams). Modes: validate, brainstorm, research. Triggers: council, validate, brainstorm, critique, research, analyze, multi-model, consensus.
Orchestrate the full ToolUniverse self-improvement cycle: discover APIs, create tools, test with researcher personas, fix issues, optimize skills, and push via git. References and dispatches to all other devtu skills. Use when asked to: run the self-improvement loop, do a debug/test round, expand tool coverage, improve tool quality, or evolve ToolUniverse.
Analyze a task, pick the right fleet type, and generate a ready-to-launch fleet (fleet.json + prompt.md files). Discovers available fleet skills dynamically. Use when the user wants to run work in parallel, asks to "plan a fleet", or says "fleet-plan".