跳转到主要内容
此内容尚未提供您的语言版本,正在以英文显示。

Do In Parallel

技能 已验证 活跃

Launch multiple sub-agents in parallel to execute tasks across files or targets with intelligent model selection, quality-focused prompting, and meta-judge → LLM-as-a-judge verification

目的

To significantly reduce execution time for batch operations by running tasks concurrently and ensuring high quality through structured verification.

功能

  • Parallel task execution across multiple targets
  • Intelligent requirement grouping (repeatable, shared, independent)
  • Meta-judge for spec generation
  • LLM-as-a-judge verification with retry mechanisms
  • Quality-focused prompting with Zero-shot CoT and self-critique

使用场景

  • Applying the same refactoring across multiple files simultaneously
  • Running code analysis on several modules concurrently
  • Generating documentation for multiple components in parallel
  • Executing independent transformations across a batch of targets

非目标

  • Performing the task execution itself (acts as an orchestrator)
  • Skipping judge verification to save time
  • Sequential execution when parallelization is safe
  • Allowing implementation agents to modify files outside their specified target

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
100 /100
1 day ago 分析

信任信号

最近提交9 days ago
星标993
许可证GPL-3.0
状态
查看源代码