semantic-compress

SKILLWorkflowcommunity
v0.0.0bjcoombsApache-2.0Updated 23d agoSource →

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 activate

Community-submitted skill. Not yet reviewed by the Forge team. Full prompt content may not be available.Request review →
30Repo stars
1Clients
1Formats
23d agoLast update
Skill
Authorbjcoombs
Version0.0.0
LicenseApache-2.0
CategoryWorkflow
Formatsskill.md
PromptNot published
Compatibility
Claude✓ Supported
Cursor
Copilot
ChatGPT
Gemini
About

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,

Keywords
skillclaude