orchestrating-skills

Orchestrate complex multi-step tasks through a four-phase pipeline that eliminates redundant context processing and reflexive subagent spawning.

The orchestrator reads the full context once and produces a JSON plan:

No LLM calls. Extracts context subsets using section headers or line ranges, pairs each with the assigned skill's system prompt, builds prompt dicts.

具有上下文路由的技能感知编排。将复杂任务分解为技能类型的子任务，提取目标上下文子集，并行执行子代理并综合结果。自我回答简单的内联查找。无 SDK 依赖性 — 通过 httpx 使用原始 HTTP。当任务需要多个分析视角时、当上下文很大并且子任务只需要部分时或者当编排代理产生太多冗余子代理时使用。 来源：oaustegard/claude-skills。