Loading...
Loading...
Found 50 Skills
Use when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies
Only to be triggered by explicit /parallel-task-spark commands.
Use when user has complex multi-agent workflows, needs to coordinate sequential or parallel agent execution, wants workflow visualization and control, or mentions automating repetitive multi-agent processes - guides discovery and usage of the orchestration system
EXPERIMENTAL: Three-layer parallel meta-cognition analysis. Triggers on: /meta-parallel, 三层分析, parallel analysis, 并行元认知
Main application building orchestrator. Creates full-stack applications from natural language requests. Determines project type, selects tech stack, coordinates agents.
Optimize multi-agent systems with coordinated profiling, workload distribution, and cost-aware orchestration. Use when improving agent performance, throughput, or reliability.
Fully autonomous epic execution. Runs until ALL children are CLOSED. Local mode uses /swarm with runtime-native spawning (Codex sub-agents or Claude teams). Distributed mode uses /swarm --mode=distributed (tmux + Agent Mail) for persistence and coordination. NO human prompts, NO stopping.
Guide for orchestrating Claude Code agent teams — multiple parallel Claude Code sessions coordinated by a team lead. Use this skill when the user mentions agent teams, teammates, parallel agents, multi-agent workflows, spawning agents, coordinating agents, delegate mode, plan approval for teammates, TeammateIdle or TaskCompleted hooks, or wants to break a task into parallel independent work streams. Also trigger on questions about tmux split-pane mode, in-process teammate mode, Shift+Up/Down agent switching, shared task lists, inter-agent messaging, or designing tasks for multi-agent decomposition. This is an experimental feature requiring CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS to be enabled.
Apply safe refactoring patterns to improve code structure without changing behavior. Use when cleaning up code, reducing technical debt, or improving maintainability.
Break down complex tasks into atomic, actionable goals with clear dependencies and success criteria. Use when planning multi-step projects, coordinating agents, or decomposing complex requests.
Manage tasks via Overseer codemode MCP. Use when tracking multi-session work, breaking down implementation, or persisting context for handoffs.
Use when working with performance testing review multi agent review