Launch Sub Agent
技能 已验证 活跃Launch an intelligent sub-agent with automatic model selection based on task complexity, specialized agent matching, Zero-shot CoT reasoning, and mandatory self-critique verification
To improve task execution quality and efficiency by autonomously configuring and dispatching focused sub-agents with optimal models and reasoning strategies.
功能
- Intelligent sub-agent deployment
- Automatic model selection (Opus, Sonnet, Haiku)
- Specialized agent matching
- Zero-shot CoT reasoning enforcement
- Mandatory self-critique verification loop
使用场景
- Launching complex architecture design tasks
- Initiating in-depth research on technical topics
- Automating code implementation for well-defined features
- Delegating documentation updates and technical writing
非目标
- Performing tasks that do not benefit from structured sub-agent execution
- Replacing direct user interaction for trivial, single-step commands
- Handling general conversation flow outside of task delegation
安装
请先添加 Marketplace
/plugin marketplace add NeoLabHQ/context-engineering-kit/plugin install sadd@context-engineering-kit质量评分
已验证类似扩展
Agent Worker Specialist
100Agent skill for worker-specialist - invoke with $agent-worker-specialist
Autopilot Loop
99Run an autonomous /loop iteration -- check progress, work on next task, schedule next wake
Team Skill
99N coordinated agents on shared task list using Claude Code native teams
Learner Skill
99Extract a learned skill from the current conversation
Ralplan
99Consensus planning entrypoint that auto-gates vague ralph/autopilot/team requests before execution
Deep Dive
992-stage pipeline: trace (causal investigation) -> deep-interview (requirements crystallization) with 3-point injection