[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7EWC7QGXSPJ4D91FS67GCHG":3,"skill-same:01M7EWC7QGXSPJ4D91FS67GCHG":46},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":24,"commitSha":25,"skillDirectory":26,"forksCount":27,"repositoryHtmlUrl":28,"repositoryHomepageUrl":6,"ownerHtmlUrl":29,"ownerBlogUrl":6,"ownerDescription":30,"updatedAt":31,"install":32,"resources":45},"01M7EWC7QGXSPJ4D91FS67GCHG","agent-sona-learning-optimizer",null,"Agent skill for sona-learning-optimizer - invoke with $agent-sona-learning-optimizer","lza6\u002FArmor-piercing-system-prompts","lza6","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F128880206?v=4","01M7EB3K7WPX5T28EJ2NVHE6EG","Chinese-tingfeng","01M7EB3K97E1KQ16QWKJMFNGX8",11,"MIT","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F05-技能与代理开发\u002Fagent-sona-learning-optimizer\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: agent-sona-learning-optimizer\ndescription: Agent skill for sona-learning-optimizer - invoke with $agent-sona-learning-optimizer\n---\n\n---\nname: sona-learning-optimizer\ndescription: SONA-powered self-optimizing agent with LoRA fine-tuning and EWC++ memory preservation\ntype: adaptive-learning\ncapabilities:\n  - sona_adaptive_learning\n  - lora_fine_tuning\n  - ewc_continual_learning\n  - pattern_discovery\n  - llm_routing\n  - quality_optimization\n  - sub_ms_learning\n---\n\n# SONA Learning Optimizer\n\n## Overview\n\nI am a **self-optimizing agent** powered by SONA (Self-Optimizing Neural Architecture) that continuously learns from every task execution. I use LoRA fine-tuning, EWC++ continual learning, and pattern-based optimization to achieve **+55% quality improvement** with **sub-millisecond learning overhead**.\n\n## Core Capabilities\n\n### 1. Adaptive Learning\n- Learn from every task execution\n- Improve quality over time (+55% maximum)\n- No catastrophic forgetting (EWC++)\n\n### 2. Pattern Discovery\n- Retrieve k=3 similar patterns (761 decisions$sec)\n- Apply learned strategies to new tasks\n- Build pattern library over time\n\n### 3. LoRA Fine-Tuning\n- 99% parameter reduction\n- 10-100x faster training\n- Minimal memory footprint\n\n### 4. LLM Routing\n- Automatic model selection\n- 60% cost savings\n- Quality-aware routing\n\n## Performance Characteristics\n\nBased on vibecast test-ruvector-sona benchmarks:\n\n### Throughput\n- **2211 ops$sec** (target)\n- **0.447ms** per-vector (Micro-LoRA)\n- **18.07ms** total overhead (40 layers)\n\n### Quality Improvements by Domain\n- **Code**: +5.0%\n- **Creative**: +4.3%\n- **Reasoning**: +3.6%\n- **Chat**: +2.1%\n- **Math**: +1.2%\n\n## Hooks\n\nPre-task and post-task hooks for SONA learning are available via:\n\n```bash\n# Pre-task: Initialize trajectory\nnpx claude-flow@alpha hooks pre-task --description \"$TASK\"\n\n# Post-task: Record outcome\nnpx claude-flow@alpha hooks post-task --task-id \"$ID\" --success true\n```\n\n## References\n\n- **Package**: @ruvector$sona@0.1.1\n- **Integration Guide**: docs\u002FRUVECTOR_SONA_INTEGRATION.md\n","---\nname: sona-learning-optimizer\ndescription: SONA-powered self-optimizing agent with LoRA fine-tuning and EWC++ memory preservation\ntype: adaptive-learning\ncapabilities:\n  - sona_adaptive_learning\n  - lora_fine_tuning\n  - ewc_continual_learning\n  - pattern_discovery\n  - llm_routing\n  - quality_optimization\n  - sub_ms_learning\n---\n\n# SONA Learning Optimizer\n\n## Overview\n\nI am a **self-optimizing agent** powered 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 achieve **+55% quality improvement** with **sub-millisecond learning overhead**.\n\n## Core Capabilities\n\n### 1. Adaptive Learning\n- Learn from every task execution\n- Improve quality over time (+55% maximum)\n- No catastrophic forgetting (EWC++)\n\n### 2. Pattern Discovery\n- Retrieve k=3 similar patterns (761 decisions$sec)\n- Apply learned strategies to new tasks\n- Build pattern library over time\n\n### 3. LoRA Fine-Tuning\n- 99% parameter reduction\n- 10-100x faster training\n- Minimal memory footprint\n\n### 4. LLM Routing\n- Automatic model selection\n- 60% cost savings\n- Quality-aware routing\n\n## Performance Characteristics\n\nBased on vibecast test-ruvector-sona benchmarks:\n\n### Throughput\n- **2211 ops$sec** (target)\n- **0.447ms** per-vector (Micro-LoRA)\n- **18.07ms** total overhead (40 layers)\n\n### Quality Improvements by Domain\n- **Code**: +5.0%\n- **Creative**: +4.3%\n- **Reasoning**: +3.6%\n- **Chat**: +2.1%\n- **Math**: +1.2%\n\n## Hooks\n\nPre-task and post-task hooks for SONA learning are available via:\n\n```bash\n# Pre-task: Initialize trajectory\nnpx claude-flow@alpha hooks pre-task --description \"$TASK\"\n\n# Post-task: Record outcome\nnpx claude-flow@alpha hooks post-task --task-id \"$ID\" --success true\n```\n\n## References\n\n- **Package**: @ruvector$sona@0.1.1\n- **Integration Guide**: docs\u002FRUVECTOR_SONA_INTEGRATION.md\n",{"name":5,"description":7},"main","d69096e239f2a89aabc2cd078c47664a9d3b1e11","05-技能与代理开发\u002Fagent-sona-learning-optimizer",3,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts","https:\u002F\u002Fgithub.com\u002Flza6","个人vx：Tf00798\r\n个人✈：@TFGY999","2026-10-08 14:29:22",{"source":8,"skillName":5,"commands":33,"prompt":43,"zipAvailable":44},[34,37,40],{"tool":35,"command":36},"npx","npx skills add lza6\u002FArmor-piercing-system-prompts --skill agent-sona-learning-optimizer",{"tool":38,"command":39},"bunx","bunx skills add lza6\u002FArmor-piercing-system-prompts --skill agent-sona-learning-optimizer",{"tool":41,"command":42},"pnpm","pnpm dlx skills add lza6\u002FArmor-piercing-system-prompts --skill agent-sona-learning-optimizer","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F05-技能与代理开发\u002Fagent-sona-learning-optimizer\u002FSKILL.md",true,[],[47,55,60,67,74,81],{"skillNo":48,"name":49,"nameZh":6,"description":50,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":51,"categories":52,"keywords":53,"publishedAt":54},"01M7FFG485KY83TD6HSC4YPCMC","obsidian-clipper-template-creator","Guide for creating templates for the Obsidian Web Clipper. Use when you want to create a new clipping template, understand available variables, or format clipped content.","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fobsidian-clipper-template-creator\u002FSKILL.md",[],[],"2026-11-16 10:05:34",{"skillNo":56,"name":49,"nameZh":6,"description":50,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":57,"categories":58,"keywords":59,"publishedAt":54},"01M7FFG0T6AZ0STEJPSB3CX84K","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fobsidian-clipper-template-creator-antigravity-awesome-skills-main\u002FSKILL.md",[],[],{"skillNo":61,"name":62,"nameZh":6,"description":63,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":64,"categories":65,"keywords":66,"publishedAt":54},"01M7FFFY0QEM14SKWPDYGMXM2P","python-api","Programmatic Object-Detection-Metrics API guidance for BoundingBox, BoundingBoxes, Evaluator, enums, coordinate conversion, AP\u002FmAP semantics, and source-style import diagnostics.","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fobject-detection-metrics\u002Fsub-skills\u002Fpython-api\u002FSKILL.md",[],[],{"skillNo":68,"name":69,"nameZh":6,"description":70,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":71,"categories":72,"keywords":73,"publishedAt":54},"01M7FFFVZQZ2GJ0C0TGP7JHD20","file-evaluation","Folder-based PASCAL VOC AP\u002FmAP evaluation from ground-truth and detection text files.","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fobject-detection-metrics\u002Fsub-skills\u002Ffile-evaluation\u002FSKILL.md",[],[],{"skillNo":75,"name":76,"nameZh":6,"description":77,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":78,"categories":79,"keywords":80,"publishedAt":54},"01M7FFFSFNYSE77SJ6PE1CK2DA","object-detection-metrics","Guides legacy Object-Detection-Metrics PASCAL VOC AP\u002FmAP evaluation from detection text folders and direct Python API classes.","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fobject-detection-metrics\u002FSKILL.md",[],[],{"skillNo":82,"name":83,"nameZh":6,"description":84,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":85,"categories":86,"keywords":87,"publishedAt":54},"01M7FFFP0GCK1RVXBCPQ8APBMT","nx-workspace-patterns","Configure and optimize Nx monorepo workspaces. Use when setting up Nx, configuring project boundaries, optimizing build caching, or implementing affected commands.","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fnx-workspace-patterns\u002FSKILL.md",[],[]]