免费在 GitHub 公开

context-engineering

Master context engineering for AI agent systems. Use when designing agent architectures, debugging context failures, optimizing token usage, implementing memory systems, building multi-agent coordination, evaluating agent performance, or developing LLM-powered pipelines. Covers context fundamentals, degradation patterns, optimization techniques (compaction, masking, caching), compression strategies, memory architectures, multi-agent patterns, LLM-as-Judge evaluation, tool design, and project development.

中文简介正在准备中。当前显示原文说明。

mrgoonie/claudekit-skills

查看安装方法

包含的文件（17）

SKILL.md3.9 KB
references/context-compression.md2.3 KB
references/context-degradation.md3.0 KB
references/context-fundamentals.md2.7 KB
references/context-optimization.md2.3 KB
references/evaluation.md2.2 KB
references/memory-systems.md2.5 KB
references/multi-agent-patterns.md2.3 KB
references/project-development.md2.1 KB
references/tool-design.md2.0 KB
scripts/compression_evaluator.py10.7 KB
scripts/context_analyzer.py10.1 KB
tests/01-basic-context-optimization.md632 B
tests/02-debug-lost-in-middle.md640 B
tests/03-multi-agent-coordination.md748 B
tests/04-edge-case-context-poisoning.md724 B
tests/05-advanced-memory-architecture.md816 B

SKILL.md（原文）

安装前可以查看交给 AI 代理的指令内容。

Context Engineering

Context engineering curates the smallest high-signal token set for LLM tasks. The goal: maximize reasoning quality while minimizing token usage.

When to Activate

Designing/debugging agent systems
Context limits constrain performance
Optimizing cost/latency
Building multi-agent coordination
Implementing memory systems
Evaluating agent performance
Developing LLM-powered pipelines

Core Principles

Context quality > quantity - High-signal tokens beat exhaustive content
Attention is finite - U-shaped curve favors beginning/end positions
Progressive disclosure - Load information just-in-time
Isolation prevents degradation - Partition work across sub-agents
Measure before optimizing - Know your baseline

Quick Reference

Topic	When to Use	Reference
Fundamentals	Understanding context anatomy, attention mechanics	context-fundamentals.md
Degradation	Debugging failures, lost-in-middle, poisoning	context-degradation.md
Optimization	Compaction, masking, caching, partitioning	context-optimization.md
Compression	Long sessions, summarization strategies	context-compression.md
Memory	Cross-session persistence, knowledge graphs	memory-systems.md
Multi-Agent	Coordination patterns, context isolation	multi-agent-patterns.md
Evaluation	Testing agents, LLM-as-Judge, metrics	evaluation.md
Tool Design	Tool consolidation, description engineering	tool-design.md
Pipelines	Project development, batch processing	project-development.md

Key Metrics

Token utilization: Warning at 70%, trigger optimization at 80%
Token variance: Explains 80% of agent performance variance
Multi-agent cost: ~15x single agent baseline
Compaction target: 50-70% reduction, <5% quality loss
Cache hit target: 70%+ for stable workloads

Four-Bucket Strategy

Write: Save context externally (scratchpads, files)
Select: Pull only relevant context (retrieval, filtering)
Compress: Reduce tokens while preserving info (summarization)
Isolate: Split across sub-agents (partitioning)

Anti-Patterns

Exhaustive context over curated context
Critical info in middle positions
No compaction triggers before limits
Single agent for parallelizable tasks
Tools without clear descriptions

Guidelines

Place critical info at beginning/end of context
Implement compaction at 70-80% utilization
Use sub-agents for context isolation, not role-play
Design tools with 4-question framework (what, when, inputs, returns)
Optimize for tokens-per-task, not tokens-per-request
Validate with probe-based evaluation
Monitor KV-cache hit rates in production
Start minimal, add complexity only when proven necessary

Scripts

context_analyzer.py - Context health analysis, degradation detection
compression_evaluator.py - Compression quality evaluation

评价

还没有评价。欢迎分享你的使用感受。

无需登录即可发表。欢迎分享使用感受、提问，或说明在哪些环境下无法运行。

还没有评论。来写第一条吧。

同一仓库的技能

aesthetic

免费

Create aesthetically beautiful interfaces following proven design principles. Use when building UI/UX, analyzing designs from inspiration sites, generating design images with ai-multimodal, implementing visual hierarchy and color theory, adding micro-interactions, or creating design documentation. Includes workflows for capturing and analyzing inspiration screenshots with chrome-devtools and ai-multimodal, iterative design image generation until aesthetic standards are met, and comprehensive design system guidance covering BEAUTIFUL (aesthetic principles), RIGHT (functionality/accessibility), SATISFYING (micro-interactions), and PEAK (storytelling) stages. Integrates with chrome-devtools, ai-multimodal, media-processing, ui-styling, and web-frameworks skills.

中文简介正在准备中。当前显示原文说明。