context-compression
Optimize agent performance and token usage through advanced context compression, structured summarization, and task-oriented state management for long-running sessions.
Discover reusable agent skills, browse implementation details, and find the right skill for your workflow.
497 skills found
Optimize agent performance and token usage through advanced context compression, structured summarization, and task-oriented state management for long-running sessions.
A modular data processing tool for cleaning, validating, and analyzing CSV files with support for custom transformations and automated dependency management.
Anima is a TypeScript animation engine for creating programmatic mathematical visualizations. Use it to script geometric animations, graphs, and complex movements with a fluent, Manim-inspired API.
A collection of design patterns for the Langroid multi-agent framework, covering agent configuration, tool handling, task orchestration, and external integrations.
Process massive files and large codebases (10M+ tokens) by recursively chunking, sub-querying, and aggregating results to overcome LLM context limits.
Build, audit, and iterate high-converting landing pages using React, Vite, TypeScript, Tailwind, and shadcn/ui. Expert in CRO, hero structures, and conversion-focused design with Iconify icons.
Initiates automated reverse engineering by discovering codebase architecture, layers, and technology stacks to facilitate system modernization or documentation.
Expert guide for WebGL 1.0/2.0 development: shaders (GLSL), 3D graphics, GPU programming, rendering pipelines, buffers, and performance optimization for web canvas.
Unified API for LLM function calling and tool use across OpenAI, Anthropic, Google, and Ollama with standardized schema definitions and execution patterns.
Standardize, validate, and manage Netresearch AI agent skill repositories with automated structure enforcement, distribution workflows, and licensing compliance tools.
Dialectical reasoning and adversarial coding agent for MCP-enabled editors, forcing LLMs to resolve internal contradictions for higher quality outputs.
Create interactive, custom data visualizations using d3.js — including charts, graphs, and network diagrams. Ideal for when you need fine-grained control over visual elements, transitions, and interactions.