semantic-compression
Aggressively prune grammatical scaffolding and filler text from inputs to optimize LLM token usage while retaining core semantic content.
Discover reusable agent skills, browse implementation details, and find the right skill for your workflow.
285 skills found
Aggressively prune grammatical scaffolding and filler text from inputs to optimize LLM token usage while retaining core semantic content.
Automate the generation of high-quality, HiDPI marketing screenshots for web applications using Playwright.
Optimize agent performance and token usage through advanced context compression, structured summarization, and task-oriented state management for long-running sessions.
Build distinctive, high-end React Native Expo interfaces using liquid glass design and iOS Human Interface Guidelines for production-grade mobile apps.
Evidence-first literature collector for automated research pipelines. Scales paper pools to 1200+ with metadata normalization, provenance tracking, and multi-source ingestion.
Architect production-grade LLM applications using LangChain 1.x and LangGraph. Implement stateful AI agents, multi-step workflows, and custom memory systems for complex conversational and automation tasks.
A local RAG semantic memory system using Qdrant and Ollama. Ideal for recalling workspace files, notes, project decisions, and user preferences with high-relevance vector search.
Synthesize research on system internals and adversary tradecraft into a concrete, testable hunt hypothesis.
A comprehensive configuration suite for Claude Code, featuring production-grade agents, skills, hooks, and automated workflows optimized for high-intensity development.
Tutorial for identifying and resolving CUDA runtime crashes using FlashInfer's API logging framework.
A versatile data analysis assistant for loading datasets, performing statistical calculations, visualizing trends, and generating professional summary reports.
Fetch and aggregate the latest Posit news, blog posts, podcast episodes, video content, and event announcements using automated sub-agents.