MCP HubMCP Hub
返回技能列表

Meta-Pattern Recognition

Elios-FPT
更新于 Today
14 次查看
1
在 GitHub 上查看
其他ai

关于

This skill identifies recurring patterns across three or more different domains to extract universal principles. It is designed for use when developers notice the same pattern in varied contexts or experience déjà vu in problem-solving. The skill helps abstract these patterns, such as caching or queuing, to apply core principles to new systems.

技能文档

Meta-Pattern Recognition

Overview

When the same pattern appears in 3+ domains, it's probably a universal principle worth extracting.

Core principle: Find patterns in how patterns emerge.

Quick Reference

Pattern Appears InAbstract FormWhere Else?
CPU/DB/HTTP/DNS cachingStore frequently-accessed data closerLLM prompt caching, CDN
Layering (network/storage/compute)Separate concerns into abstraction levelsArchitecture, organization
Queuing (message/task/request)Decouple producer from consumer with bufferEvent systems, async processing
Pooling (connection/thread/object)Reuse expensive resourcesMemory management, resource governance

Process

  1. Spot repetition - See same shape in 3+ places
  2. Extract abstract form - Describe independent of any domain
  3. Identify variations - How does it adapt per domain?
  4. Check applicability - Where else might this help?

Example

Pattern spotted: Rate limiting in API throttling, traffic shaping, circuit breakers, admission control

Abstract form: Bound resource consumption to prevent exhaustion

Variation points: What resource, what limit, what happens when exceeded

New application: LLM token budgets (same pattern - prevent context window exhaustion)

Red Flags You're Missing Meta-Patterns

  • "This problem is unique" (probably not)
  • Multiple teams independently solving "different" problems identically
  • Reinventing wheels across domains
  • "Haven't we done something like this?" (yes, find it)

Remember

  • 3+ domains = likely universal
  • Abstract form reveals new applications
  • Variations show adaptation points
  • Universal patterns are battle-tested

快速安装

/plugin add https://github.com/Elios-FPT/EliosCodePracticeService/tree/main/meta-pattern-recognition

在 Claude Code 中复制并粘贴此命令以安装该技能

GitHub 仓库

Elios-FPT/EliosCodePracticeService
路径: .claude/skills/problem-solving/meta-pattern-recognition

相关推荐技能

llamaguard

其他

LlamaGuard是Meta推出的7-8B参数内容审核模型,专门用于过滤LLM的输入和输出内容。它能检测六大安全风险类别(暴力/仇恨、性内容、武器、违禁品、自残、犯罪计划),准确率达94-95%。开发者可通过HuggingFace、vLLM或Sagemaker快速部署,并能与NeMo Guardrails集成实现自动化安全防护。

查看技能

sglang

SGLang是一个专为LLM设计的高性能推理框架,特别适用于需要结构化输出的场景。它通过RadixAttention前缀缓存技术,在处理JSON、正则表达式、工具调用等具有重复前缀的复杂工作流时,能实现极速生成。如果你正在构建智能体或多轮对话系统,并追求远超vLLM的推理性能,SGLang是理想选择。

查看技能

evaluating-llms-harness

测试

该Skill通过60+个学术基准测试(如MMLU、GSM8K等)评估大语言模型质量,适用于模型对比、学术研究及训练进度追踪。它支持HuggingFace、vLLM和API接口,被EleutherAI等行业领先机构广泛采用。开发者可通过简单命令行快速对模型进行多任务批量评估。

查看技能

langchain

LangChain是一个用于构建LLM应用程序的框架,支持智能体、链和RAG应用开发。它提供多模型提供商支持、500+工具集成、记忆管理和向量检索等核心功能。开发者可用它快速构建聊天机器人、问答系统和自主代理,适用于从原型验证到生产部署的全流程。

查看技能