ck:context-engineering

Community

Optimize token usage and monitor LLM context limits

AuthorJoseMas68
Version1.0.0
Installs0

System Documentation

What problem does it solve?

LLM agents often exceed context windows, leading to token overruns, degraded performance, and hidden failures. This Skill continuously monitors usage limits, identifies degradation patterns, and suggests compression or partitioning strategies.

Core Features & Use Cases

  • Usage Monitoring: Retrieves real‑time quota data from Anthropic and tracks context window percentages.
  • Health Analysis: Evaluates token utilization, lost‑in‑middle risks, and poisoning patterns with detailed recommendations.
  • Optimization Scripts: Provides context_analyzer.py for budgeting and compression_evaluator.py for assessing compression quality.
  • Quick Reference: Tables linking topics to reference markdown files for deeper guidance. Ideal for developers building multi‑agent pipelines, memory systems, or any AI workflow where context efficiency is critical.

Quick Start

Run the context analyzer on your context JSON file to receive a health report with utilization metrics and optimization suggestions.

Dependency Matrix

Required Modules

None required

Components

scriptsreferences

💻 Claude Code Installation

Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.

Please help me install this Skill:
Name: ck:context-engineering
Download link: https://github.com/JoseMas68/CRMDev/archive/main.zip#ck-context-engineering

Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
View Source Repository

Agent Skills Search Helper

Install a tiny helper to your Agent, search and equip skill from 223,000+ vetted skills library on demand.