Skill orchestration: assign each local model its own skill set instead of chasing generality
gnukeith · x · 2026-11-17
Developer gnukeith describes his multi-model orchestration in more detail: when several open-weight models (e.g. Qwen, DeepSeek, GLM variants) run locally, his orchestration skill applies rules per model, assigning each a specialty — one handles deep-research and documentation skills, another focuses on physics/science/math.
He also shares his take on the skills ecosystem: GitHub is full of skills; use the ones you like, tweak them if something's missing — skills are meant to help you get concrete work done, not to be generalized tools.
More from coding & agent
- Voice agent passes 15 metrics but customers still complain — what's not being measured? — georgeamine · 2026-11-17
- Google's modern-web-guidance lifts coding agents' best-practice pass rate from 52% to 92% — victor_explore · 2026-11-17
- Open-source Irrigator adds crash recovery and observability to coding agent swarms — volatilityfund · 2026-11-17
- Orchestrating local LLMs: assign skills per model, let a third one debate and verify — gnukeith · 2026-11-17
- 435K LOC deep dive: a hands-on manual for LangChain 1.5, LangGraph 1.2 and Deep Agents — ghumare64 · 2026-11-17
- rauchjulian: traces are the essential new primitive of software development — your intelligence — HamelHusain · 2026-11-17