Semantic Compress

Make an LLM-directed document smaller while preserving what it does. Two modes: a local span-level core->pointer pass, and an A/B-validated distill loop that produces the smallest document that behaves the same as the original. Point at core knowledge the model already holds (a concept name activates it); keep project-specific detail explicit and verbatim. TRIGGER when asked to compress, tighten, shorten, or strip a prompt / instruction / system message meant for an LLM; to distill a skill; to compress a whole document; to make this smaller while preserving behaviour; to A/B test a compression or produce a behaviourally-equivalent compression; when an instruction set explains concepts the model already knows from training; or when reducing token cost of an LLM-directed prompt without losing meaning. Not for human-facing prose - that is /deslop.

bjcoombs Updated 32 repo stars
Doc-navigability graph before the action sweep: 254 docs, 30% reachable from the entry point, 43 islands, 15 broken links

File contents

bjcoombs/ai-native-toolkit commit 65625b81b6

Frequently asked questions

npx get-skill add bjcoombs/semantic-compress