How to split Claude skill logic between the body and reference files
socialwithaayan · x · 2026-07-24
A thread on splitting Claude skill knowledge across the body and reference files so the skill stays lightweight.
- Put only instructions that every run needs in the body.
- Move long examples, lookup material, style banks, and other conditional content into reference files.
- The author frames the choice as a size-and-usage test: if not every run needs it, it probably should not live in the body.
More from coding & agent
- Alex Townsend posts 200 open problems in numerical linear algebra for humans and AI agents — IgorCarron · 2026-09-11
- Kimi K2.8 Preview rolls out: near-K3 coding performance, 1M context for all tiers — teortaxesTex · 2026-09-11
- Looking for a classifier of software engineering task shapes to pick models per task — StewartalsopIII · 2026-09-11
- Steal this idea: prompt-to-hardware where agents assemble custom devices — paraschopra · 2026-09-11
- Model Is the Least Interesting Part: A Guide to Six Core AI Architectures from RAG to Multi-Agent — goyalshaliniuk · 2026-09-11
- Non-coder builds layered memory architecture: 20k tokens tracks a year of agent conversations — matteoianni · 2026-09-11