Agent Skills Hub

context-detection

Systematic project technology stack detection, framework-specific skill auto-loading, and multi-stack analysis for fullstack projects like React + Go.

context-fundamentals

Foundational guidelines for context engineering: optimizing token budgets, attention mechanics, and system architecture for AI agents.

k0ntext

RPI Plan Phase: Create chunk-based, dependency-aware implementation plans from research documents for structured, atomic development.

context7

Retrieve real-time library documentation, code examples, and technical guidance using the Context7 API for frameworks like React, FastAPI, and Next.js.

context-optimization

Optimize agent context windows through KV-caching, observation masking, summarization-based compaction, and context partitioning to reduce costs and latency.

context-driven-development

Standardizes project context by managing artifacts (product, tech-stack, workflow, tracks) in a conductor/ directory. Supports project scaffolding, artifact synchronization, and AI alignment for greenfield and brownfield projects.

context-cascade

A nested plugin architecture for Claude Code that optimizes context by dynamically loading playbooks, skills, and agents to save over 90% in token usage.

context-compression

Optimize agent performance and token usage through advanced context compression, structured summarization, and task-oriented state management for long-running sessions.

context-management

Proactive context window management for AI agents via intelligent token monitoring, snapshot creation, and selective state rehydration to maintain continuity during long sessions.

context-degradation

Diagnose, isolate, and mitigate LLM context failures like lost-in-middle, poisoning, distraction, and context clash to improve agent reliability.

context-driven-testing

Apply context-driven testing principles to adapt testing strategies based on project goals, risks, and constraints rather than relying on universal best practices.

semantic-compression

Aggressively prune grammatical scaffolding and filler text from inputs to optimize LLM token usage while retaining core semantic content.