以下为本文档的中文说明agent-sona-learning-optimizer 是 ruvnet 推出的一款基于 SONASelf-Optimizing Neural Architecture自优化神经架构的学习优化智能体技能。它的核心理念是“持续自我进化”——每次任务执行都会积累经验并自动优化性能声称可以实现 55% 的质量提升而学习开销低于毫秒级别。功能用途上该技能集成了多种先进的学习机制第一自适应学习Adaptive Learning从每次任务执行中学习持续改进输出质量第二模式发现Pattern Discovery检索相似的过往模式每秒 761 次决策的检索速度将已学策略应用于新任务逐步构建模式库第三LoRA 微调LoRA Fine-Tuning仅更新 1% 的参数即可实现模型微调训练速度提升 10-100 倍内存占用极小第四LLM 路由LLM Routing根据任务特性自动选择最合适的底层模型。使用场景包括需要不断优化输出质量的自动化工作流对响应速度和质量有苛刻要求的实时系统长期运行的 AI 服务需要避免模型退化希望用最少计算资源获得最佳性能的场景。核心特点第一EWC弹性权重巩固增强版持续学习技术在吸收新知识的同时不会灾难性遗忘旧知识第二子毫秒学习开销几乎不影响实时响应速度第三LoRA 技术实现极低参数量的模型适配大幅降低硬件门槛第四模式库积累机制经验越丰富效果越好形成正向飞轮第五自动模型选择根据任务复杂度动态切换不同规模的 LLM兼顾质量与成本。这使得该技能非常适合需要长期运行且持续优化的 AI 应用场景。SONA Learning OptimizerOverviewI am aself-optimizing agentpowered by SONA (Self-Optimizing Neural Architecture) that continuously learns from every task execution. I use LoRA fine-tuning, EWC continual learning, and pattern-based optimization to achieve55% quality improvementwithsub-millisecond learning overhead.Core Capabilities1. Adaptive LearningLearn from every task executionImprove quality over time (55% maximum)No catastrophic forgetting (EWC)2. Pattern DiscoveryRetrieve k3 similar patterns (761 decisions$sec)Apply learned strategies to new tasksBuild pattern library over time3. LoRA Fine-Tuning99% parameter reduction10-100x faster trainingMinimal memory footprint4. LLM RoutingAutomatic model selection60% cost savingsQuality-aware routingPerformance CharacteristicsBased on vibecast test-ruvector-sona benchmarks:Throughput2211 ops$sec(target)0.447msper-vector (Micro-LoRA)18.07mstotal overhead (40 layers)Quality Improvements by DomainCode: 5.0%Creative: 4.3%Reasoning: 3.6%Chat: 2.1%Math: 1.2%HooksPre-task and post-task hooks for SONA learning are available via:# Pre-task: Initialize trajectorynpx claude-flowalpha hooks pre-task--description$TASK# Post-task: Record outcomenpx claude-flowalpha hooks post-task --task-id$ID--successtrueReferencesPackage: ruvector$sona0.1.1Integration Guide: docs/RUVECTOR_SONA_INTEGRATION.md3e:[“,,,L41”,null,{“content”:“$42”,“frontMatter”:{“name”:“agent-sona-learning-optimizer”,“description”:“Agent skill for sona-learning-optimizer - invoke with $agent-sona-learning-optimizer”}}]3f:[“KaTeX parse error: Expected }, got EOF at end of input: …,children:[[”,“div”,null,{“className”:“flex items-center justify-between border-b border-border bg-muted/30 px-4 py-2.5”,“children”:[[“KaTeX parse error: Expected }, got EOF at end of input: …,children:[”,“span”,null,{“className”:“truncate text-xs font-medium text-muted-foreground”,“children”:“同仓库更多 Skills”}]}],[“KaTeX parse error: Expected EOF, got } at position 88: …ldren:同仓库}]]}̲],[”,“div”,null,{“className”:“p-4 sm:p-5”,“children”:[[“,h2,null,id:related−skills−heading,className:text−2xlfont−semiboldtracking−normaltext−foreground,children:同仓库更多Skills],[,h2,null,{id:related-skills-heading,className:text-2xl font-semibold tracking-normal text-foreground,children:同仓库更多 Skills}],[,h2,null,id:related−skills−heading,className:text−2xlfont−semiboldtracking−normaltext−foreground,children:同仓库更多Skills],[”,“div”,null,{“className”:“mt-4 grid gap-3 sm:grid-cols-2”,“children”:[“L43,L43,L43,L44”,“L45,L45,L45,L46”,“L47,L47,L47,L48”]}]]}]]}]49:I[206516,[“/_next/static/chunks/051aanbhrv4br.js”,“/_next/static/chunks/0mizr60h7ayzt.js”,“/_next/static/chunks/0v9lm1dmbdoo-.js”,“/_next/static/chunks/0rxr1j1j3j-.r.js”,“/_next/static/chunks/02ftybezfvqjd.js”,“/_next/static/chunks/0.v9ksvnnj8ia.js”,“/_next/static/chunks/0bn6id96nx3k.js,“/_next/static/chunks/13ybnhn37c.tc.js”,“/_next/static/chunks/0_fnrdtruz8uf.js”,“/_next/static/chunks/0r6l15utt1mwb.js”,“/_next/static/chunks/0dm9a5into854.js”,/_next/static/chunks/07k6hqoibtcn.js”,“/next/static/chunks/0b4cao.4y…j.js”,“/_next/static/chunks/02i-n28z7kjd0.js”],“default”]