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.

Skill-aware orchestration with context routing. Decomposes complex tasks into skill-typed subtasks, extracts targeted context subsets, executes subagents in parallel, and synthesizes results. Self-answers trivial lookups inline. No SDK dependency — uses raw HTTP via httpx. Use when tasks require multiple analytical perspectives, when context is large and subtasks only need portions, or when orchestrating-agents spawns too many redundant subagents. Source: oaustegard/claude-skills.