Claude Skills by greyok00

Tighten user prompts before they reach a model — strip conversational filler, drop fragments, dedupe sentences, rank by relevance, and compose a short, declarative system prompt that doesn't waste context. CPU-only, deterministic, dependency-free. Use it whenever a request is long, rambling, or covered in pleasantries that obscure the actual ask, and especially before a model call in a script or batch pipeline.

Shrink LLM prompts before sending them — collapse duplicate tool results, distill old turns, minify tool schemas and system prompts, prune to a token budget, and (opt-in) prune large HTML tool results. On the output side, the proxy can cap/truncate streamed completions and strip lead-in filler. Lossy by default (distill + tool-result compression) for the most context headroom; disable any stage via the SLIMTOKEN_* env knobs. Works with any local or cloud model via the slimtoken CLI or MCP ser...