All authors
Claude Skills by KathanModh259
github.com/KathanModh2592 skills0 installs0 views
- Latent Gate CompressionCompress images, long prompts, conversations, and RAG documents locally via Ollama before consuming LLM tokens. Reduces token usage by ~80% on images and ~85% on text. Use proactively when: the user uploads images, processes long context, works with multiple RAG sources, or when approaching token limits.Votes: 0GitHub stars: 25
- Token OptimizerRead large logs, JSON/API responses, data exports and long documents through LatentGate's token optimizer instead of reading them raw. Use when a file you only need to understand (not edit) is likely over ~2,000 tokens — log files, stack-trace dumps, pretty-printed JSON, CSV/NDJSON exports, long docs or RAG chunks — or when the user asks to save tokens/context.Votes: 0GitHub stars: 25