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.

Related event: Developer shares local multi-model orchestration with rule-based skill assignment(2 posts)→

Original post →

More from coding & agent

coding & agent channel →