Episteme Compaction

Lossless compaction of epistemes: prose ↔ compact typed-slot notation (F4-F5, ~65% token savings) with a source-claims vs [bracketed] split and reconstruction back to source. Use for AI-agent or FPF-literate-human output needing token economy and auditability. NOT narrativization. Depends on fpf-core.

dimonier Updated

File contents

dimonier/skills/tree/main/skills/episteme-compaction commit c55071f922

Frequently asked questions

npx skillmds@latest add dimonier/episteme-compaction