[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7AWAXNGQ3C751Q5VTPD9ATN":3,"skill-same:01M7AWAXNGQ3C751Q5VTPD9ATN":91},{"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":33,"commitSha":34,"skillDirectory":35,"forksCount":36,"repositoryHtmlUrl":37,"repositoryHomepageUrl":6,"ownerHtmlUrl":38,"ownerBlogUrl":39,"ownerDescription":40,"updatedAt":41,"install":42,"resources":54},"01M7AWAXNGQ3C751Q5VTPD9ATN","dspy-ruby",null,"This skill should be used when working with DSPy.rb, a Ruby framework for building type-safe, composable LLM applications. Use this when implementing predictable AI features, creating LLM signatures and modules, configuring language model providers (OpenAI, Anthropic, Gemini, Ollama), building agent systems with tools, optimizing prompts, or testing LLM-powered functionality in Ruby applications.","barkleesanders\u002Fclaude-code-starter","barkleesanders","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F30680901?v=4","01M7AW019CGBYWDA8MFJEN1JXC","Barklee Sanders","01M7AW01A5H994ASJ2QZPW67AV",4,"MIT","https:\u002F\u002Fgithub.com\u002Fbarkleesanders\u002Fclaude-code-starter\u002Fblob\u002Fmain\u002Fskills\u002Fdspy-ruby\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: dspy-ruby\nuser-invocable: true\ndescription: This skill should be used when working with DSPy.rb, a Ruby framework for building type-safe, composable LLM applications. Use this when implementing predictable AI features, creating LLM signatures and modules, configuring language model providers (OpenAI, Anthropic, Gemini, Ollama), building agent systems with tools, optimizing prompts, or testing LLM-powered functionality in Ruby applications.\nallowed-tools:\n  - Bash\n  - Read\n  - Write\n  - Edit\n  - Grep\n  - Glob\nmodel: inherit\n---\n\n# DSPy.rb Expert\n\n## Overview\n\nDSPy.rb is a Ruby framework that enables developers to **program LLMs, not prompt them**. Instead of manually crafting prompts, define application requirements through type-safe, composable modules that can be tested, optimized, and version-controlled like regular code.\n\n## Mode Detection\n\nDetermine what the user needs, then read ONLY the relevant reference files before proceeding.\n\n| User Intent | Reference Files to Read |\n|-------------|------------------------|\n| Signatures, modules, predictors, type safety | `core-concepts.md` |\n| LLM provider setup, API keys, configuration | `providers.md` |\n| Testing, optimization, observability | `optimization.md` |\n| Getting started, Rails integration | `quickstart.md` |\n| Common patterns, agents, pipelines, vision | `patterns.md` |\n\nAll reference files are in `~\u002F.claude\u002Fskills\u002Fdspy-ruby\u002Freferences\u002F`.\n\n---\n\n## Core Capabilities (Quick Reference)\n\n### 1. Type-Safe Signatures\n\n```ruby\nclass EmailClassificationSignature \u003C DSPy::Signature\n  description \"Classify customer support emails\"\n\n  input do\n    const :email_subject, String\n    const :email_body, String\n  end\n\n  output do\n    const :category, T.enum([\"Technical\", \"Billing\", \"General\"])\n    const :priority, T.enum([\"Low\", \"Medium\", \"High\"])\n  end\nend\n```\n\n**Best practices**: Clear descriptions, enums for constrained outputs, `desc:` parameter for fields, specific types over generic String. Full docs: `core-concepts.md`.\n\n### 2. Composable Modules\n\n```ruby\nclass EmailProcessor \u003C DSPy::Module\n  def initialize\n    super\n    @classifier = DSPy::Predict.new(EmailClassificationSignature)\n  end\n\n  def forward(email_subject:, email_body:)\n    @classifier.forward(email_subject: email_subject, email_body: email_body)\n  end\nend\n```\n\nChain modules for complex workflows. Full docs: `core-concepts.md`.\n\n### 3. Predictor Types\n\n| Predictor | Use For | Key Feature |\n|-----------|---------|-------------|\n| **Predict** | Simple tasks, classification, extraction | Basic type-safe inference |\n| **ChainOfThought** | Complex reasoning, analysis | Automatic reasoning step |\n| **ReAct** | Tasks requiring external tools | Iterative tool-using agent |\n| **CodeAct** | Tasks best solved with code | Dynamic code generation (`dspy-code_act` gem) |\n\nFull docs: `core-concepts.md`.\n\n### 4. LLM Provider Configuration\n\n```ruby\n# OpenAI\nDSPy.configure { |c| c.lm = DSPy::LM.new('openai\u002Fgpt-4o-mini', api_key: ENV['OPENAI_API_KEY']) }\n\n# Anthropic Claude\nDSPy.configure { |c| c.lm = DSPy::LM.new('anthropic\u002Fclaude-3-5-sonnet-20241022', api_key: ENV['ANTHROPIC_API_KEY']) }\n\n# Google Gemini\nDSPy.configure { |c| c.lm = DSPy::LM.new('gemini\u002Fgemini-1.5-pro', api_key: ENV['GOOGLE_API_KEY']) }\n\n# Local Ollama (free, private)\nDSPy.configure { |c| c.lm = DSPy::LM.new('ollama\u002Fllama3.1') }\n```\n\n**Provider compatibility matrix**:\n\n| Feature | OpenAI | Anthropic | Gemini | Ollama |\n|---------|--------|-----------|--------|--------|\n| Structured Output | yes | yes | yes | yes |\n| Vision (Images) | yes | yes | yes | limited |\n| Image URLs | yes | no | no | no |\n| Tool Calling | yes | yes | yes | varies |\n\n**Cost optimization**: Dev = Ollama\u002Fgpt-4o-mini, Test = gpt-4o-mini (temp=0), Prod simple = gpt-4o-mini\u002Fhaiku\u002Fflash, Prod complex = gpt-4o\u002Fsonnet\u002Fpro. Full docs: `providers.md`.\n\n### 5. Testing\n\n```ruby\nRSpec.describe EmailClassifier do\n  before do\n    DSPy.configure { |c| c.lm = DSPy::LM.new('openai\u002Fgpt-4o-mini', api_key: ENV['OPENAI_API_KEY']) }\n  end\n\n  it 'classifies technical emails correctly' do\n    result = EmailClassifier.new.forward(email_subject: \"Can't log in\", email_body: \"Unable to access account\")\n    expect(result[:category]).to eq('Technical')\n  end\nend\n```\n\nFull docs: `optimization.md`.\n\n---\n\n## Reference Files Index\n\n| File | Content |\n|------|---------|\n| `core-concepts.md` | Signatures, modules, predictors, multimodal support, best practices |\n| `providers.md` | All LLM provider configs, compatibility matrix, cost optimization, troubleshooting |\n| `optimization.md` | Testing patterns, MIPROv2 optimization, observability, monitoring |\n| `quickstart.md` | Step-by-step new project setup, Rails integration |\n| `patterns.md` | Multi-step pipelines, agents with tools, conditional routing, retry\u002Ffallback, vision, observability |\n\n### Assets (templates for quick starts)\n\n- `assets\u002Fsignature-template.rb` -- Examples of signatures including basic, vision, sentiment, code gen\n- `assets\u002Fmodule-template.rb` -- Module patterns including pipelines, agents, error handling, caching\n- `assets\u002Fconfig-template.rb` -- Configuration for all providers, environments, observability, production\n\n## When to Use This Skill\n\n- Implementing LLM-powered features in Ruby applications\n- Creating type-safe interfaces for AI operations\n- Building agent systems with tool usage\n- Setting up or troubleshooting LLM providers\n- Optimizing prompts and improving accuracy\n- Testing LLM functionality\n- Adding observability to AI applications\n- Converting from manual prompt engineering to programmatic approach\n- Debugging DSPy.rb code or configuration issues\n","# DSPy.rb Expert\n\n## Overview\n\nDSPy.rb is a Ruby framework that enables developers to **program LLMs, not prompt them**. Instead of manually crafting prompts, define application requirements through type-safe, composable modules that can be tested, optimized, and version-controlled like regular code.\n\n## Mode Detection\n\nDetermine what the user needs, then read ONLY the relevant reference files before proceeding.\n\n| User Intent | Reference Files to Read |\n|-------------|------------------------|\n| Signatures, modules, predictors, type safety | `core-concepts.md` |\n| LLM provider setup, API keys, configuration | `providers.md` |\n| Testing, optimization, observability | `optimization.md` |\n| Getting started, Rails integration | `quickstart.md` |\n| Common patterns, agents, pipelines, vision | `patterns.md` |\n\nAll reference files are in `~\u002F.claude\u002Fskills\u002Fdspy-ruby\u002Freferences\u002F`.\n\n---\n\n## Core Capabilities (Quick Reference)\n\n### 1. Type-Safe Signatures\n\n```ruby\nclass EmailClassificationSignature \u003C DSPy::Signature\n  description \"Classify customer support emails\"\n\n  input do\n    const :email_subject, String\n    const :email_body, String\n  end\n\n  output do\n    const :category, T.enum([\"Technical\", \"Billing\", \"General\"])\n    const :priority, T.enum([\"Low\", \"Medium\", \"High\"])\n  end\nend\n```\n\n**Best practices**: Clear descriptions, enums for constrained outputs, `desc:` parameter for fields, specific types over generic String. Full docs: `core-concepts.md`.\n\n### 2. Composable Modules\n\n```ruby\nclass EmailProcessor \u003C DSPy::Module\n  def initialize\n    super\n    @classifier = DSPy::Predict.new(EmailClassificationSignature)\n  end\n\n  def forward(email_subject:, email_body:)\n    @classifier.forward(email_subject: email_subject, email_body: email_body)\n  end\nend\n```\n\nChain modules for complex workflows. Full docs: `core-concepts.md`.\n\n### 3. Predictor Types\n\n| Predictor | Use For | Key Feature |\n|-----------|---------|-------------|\n| **Predict** | Simple tasks, classification, extraction | Basic type-safe inference |\n| **ChainOfThought** | Complex reasoning, analysis | Automatic reasoning step |\n| **ReAct** | Tasks requiring external tools | Iterative tool-using agent |\n| **CodeAct** | Tasks best solved with code | Dynamic code generation (`dspy-code_act` gem) |\n\nFull docs: `core-concepts.md`.\n\n### 4. LLM Provider Configuration\n\n```ruby\n# OpenAI\nDSPy.configure { |c| c.lm = DSPy::LM.new('openai\u002Fgpt-4o-mini', api_key: ENV['OPENAI_API_KEY']) }\n\n# Anthropic Claude\nDSPy.configure { |c| c.lm = DSPy::LM.new('anthropic\u002Fclaude-3-5-sonnet-20241022', api_key: ENV['ANTHROPIC_API_KEY']) }\n\n# Google Gemini\nDSPy.configure { |c| c.lm = DSPy::LM.new('gemini\u002Fgemini-1.5-pro', api_key: ENV['GOOGLE_API_KEY']) }\n\n# Local Ollama (free, private)\nDSPy.configure { |c| c.lm = DSPy::LM.new('ollama\u002Fllama3.1') }\n```\n\n**Provider compatibility matrix**:\n\n| Feature | OpenAI | Anthropic | Gemini | Ollama |\n|---------|--------|-----------|--------|--------|\n| Structured Output | yes | yes | yes | yes |\n| Vision (Images) | yes | yes | yes | limited |\n| Image URLs | yes | no | no | no |\n| Tool Calling | yes | yes | yes | varies |\n\n**Cost optimization**: Dev = Ollama\u002Fgpt-4o-mini, Test = gpt-4o-mini (temp=0), Prod simple = gpt-4o-mini\u002Fhaiku\u002Fflash, Prod complex = gpt-4o\u002Fsonnet\u002Fpro. Full docs: `providers.md`.\n\n### 5. Testing\n\n```ruby\nRSpec.describe EmailClassifier do\n  before do\n    DSPy.configure { |c| c.lm = DSPy::LM.new('openai\u002Fgpt-4o-mini', api_key: ENV['OPENAI_API_KEY']) }\n  end\n\n  it 'classifies technical emails correctly' do\n    result = EmailClassifier.new.forward(email_subject: \"Can't log in\", email_body: \"Unable to access account\")\n    expect(result[:category]).to eq('Technical')\n  end\nend\n```\n\nFull docs: `optimization.md`.\n\n---\n\n## Reference Files Index\n\n| File | Content |\n|------|---------|\n| `core-concepts.md` | Signatures, modules, predictors, multimodal support, best practices |\n| `providers.md` | All LLM provider configs, compatibility matrix, cost optimization, troubleshooting |\n| `optimization.md` | Testing patterns, MIPROv2 optimization, observability, monitoring |\n| `quickstart.md` | Step-by-step new project setup, Rails integration |\n| `patterns.md` | Multi-step pipelines, agents with tools, conditional routing, retry\u002Ffallback, vision, observability |\n\n### Assets (templates for quick starts)\n\n- `assets\u002Fsignature-template.rb` -- Examples of signatures including basic, vision, sentiment, code gen\n- `assets\u002Fmodule-template.rb` -- Module patterns including pipelines, agents, error handling, caching\n- `assets\u002Fconfig-template.rb` -- Configuration for all providers, environments, observability, production\n\n## When to Use This Skill\n\n- Implementing LLM-powered features in Ruby applications\n- Creating type-safe interfaces for AI operations\n- Building agent systems with tool usage\n- Setting up or troubleshooting LLM providers\n- Optimizing prompts and improving accuracy\n- Testing LLM functionality\n- Adding observability to AI applications\n- Converting from manual prompt engineering to programmatic approach\n- Debugging DSPy.rb code or configuration issues\n",{"name":5,"model":24,"description":7,"allowed-tools":25,"user-invocable":32},"inherit",[26,27,28,29,30,31],"Bash","Read","Write","Edit","Grep","Glob",true,"main","e7b39d448c7d905feed2b044d3ccdf60822596ab","skills\u002Fdspy-ruby",0,"https:\u002F\u002Fgithub.com\u002Fbarkleesanders\u002Fclaude-code-starter","https:\u002F\u002Fgithub.com\u002Fbarkleesanders","barkleesanders.com","Stay Hungry, Stay Foolish","2026-11-06 08:47:06",{"source":8,"skillName":5,"commands":43,"prompt":53,"zipAvailable":32},[44,47,50],{"tool":45,"command":46},"npx","npx skills add barkleesanders\u002Fclaude-code-starter --skill dspy-ruby",{"tool":48,"command":49},"bunx","bunx skills add barkleesanders\u002Fclaude-code-starter --skill dspy-ruby",{"tool":51,"command":52},"pnpm","pnpm dlx skills add barkleesanders\u002Fclaude-code-starter --skill dspy-ruby","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fbarkleesanders\u002Fclaude-code-starter\u002Fblob\u002Fmain\u002Fskills\u002Fdspy-ruby\u002FSKILL.md",[55,61,65,69,75,79,83,87],{"path":56,"resourceType":57,"resourceTypeDesc":58,"sizeBytes":59,"sourceHtmlUrl":60},"assets\u002Fconfig-template.rb","SCRIPT","脚本",10321,"https:\u002F\u002Fgithub.com\u002Fbarkleesanders\u002Fclaude-code-starter\u002Fblob\u002Fmain\u002Fskills\u002Fdspy-ruby\u002Fassets\u002Fconfig-template.rb",{"path":62,"resourceType":57,"resourceTypeDesc":58,"sizeBytes":63,"sourceHtmlUrl":64},"assets\u002Fmodule-template.rb",7664,"https:\u002F\u002Fgithub.com\u002Fbarkleesanders\u002Fclaude-code-starter\u002Fblob\u002Fmain\u002Fskills\u002Fdspy-ruby\u002Fassets\u002Fmodule-template.rb",{"path":66,"resourceType":57,"resourceTypeDesc":58,"sizeBytes":67,"sourceHtmlUrl":68},"assets\u002Fsignature-template.rb",4838,"https:\u002F\u002Fgithub.com\u002Fbarkleesanders\u002Fclaude-code-starter\u002Fblob\u002Fmain\u002Fskills\u002Fdspy-ruby\u002Fassets\u002Fsignature-template.rb",{"path":70,"resourceType":71,"resourceTypeDesc":72,"sizeBytes":73,"sourceHtmlUrl":74},"references\u002Fcore-concepts.md","REFERENCE","参考文档",6301,"https:\u002F\u002Fgithub.com\u002Fbarkleesanders\u002Fclaude-code-starter\u002Fblob\u002Fmain\u002Fskills\u002Fdspy-ruby\u002Freferences\u002Fcore-concepts.md",{"path":76,"resourceType":71,"resourceTypeDesc":72,"sizeBytes":77,"sourceHtmlUrl":78},"references\u002Foptimization.md",14272,"https:\u002F\u002Fgithub.com\u002Fbarkleesanders\u002Fclaude-code-starter\u002Fblob\u002Fmain\u002Fskills\u002Fdspy-ruby\u002Freferences\u002Foptimization.md",{"path":80,"resourceType":71,"resourceTypeDesc":72,"sizeBytes":81,"sourceHtmlUrl":82},"references\u002Fpatterns.md",3316,"https:\u002F\u002Fgithub.com\u002Fbarkleesanders\u002Fclaude-code-starter\u002Fblob\u002Fmain\u002Fskills\u002Fdspy-ruby\u002Freferences\u002Fpatterns.md",{"path":84,"resourceType":71,"resourceTypeDesc":72,"sizeBytes":85,"sourceHtmlUrl":86},"references\u002Fproviders.md",8229,"https:\u002F\u002Fgithub.com\u002Fbarkleesanders\u002Fclaude-code-starter\u002Fblob\u002Fmain\u002Fskills\u002Fdspy-ruby\u002Freferences\u002Fproviders.md",{"path":88,"resourceType":71,"resourceTypeDesc":72,"sizeBytes":89,"sourceHtmlUrl":90},"references\u002Fquickstart.md",2130,"https:\u002F\u002Fgithub.com\u002Fbarkleesanders\u002Fclaude-code-starter\u002Fblob\u002Fmain\u002Fskills\u002Fdspy-ruby\u002Freferences\u002Fquickstart.md",[92,98,105,112,119,126],{"skillNo":93,"name":94,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":95,"categories":96,"keywords":97,"publishedAt":19},"01M7AWV75B37B6YKG7ZKGZ783F","zi-search","https:\u002F\u002Fgithub.com\u002Fbarkleesanders\u002Fclaude-code-starter\u002Fblob\u002Fmain\u002Fskills\u002Fzi-search\u002FSKILL.md",[],[],{"skillNo":99,"name":100,"nameZh":6,"description":101,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":102,"categories":103,"keywords":104,"publishedAt":19},"01M7AWTZA3JGK1T7V1HS543FG7","visualise","Render inline interactive visuals — SVG diagrams, HTML widgets, charts, and explainers — directly in the conversation. Use this skill whenever the user asks to visualize, diagram, chart, illustrate, or explain something visually, or when an explanation would genuinely benefit from a spatial\u002Finteractive diagram rather than text. Also triggers for: flowcharts, architecture diagrams, data visualizations, interactive explainers, comparison layouts, UI mockups, and any request containing 'show me', 'draw', 'map out', 'visualize', or 'diagram'. Even when the user doesn't explicitly ask for a visual, use this skill proactively when the topic has spatial, sequential, or systemic relationships that a diagram would clarify better than prose.","https:\u002F\u002Fgithub.com\u002Fbarkleesanders\u002Fclaude-code-starter\u002Fblob\u002Fmain\u002Fskills\u002Fvisualise\u002FSKILL.md",[],[],{"skillNo":106,"name":107,"nameZh":6,"description":108,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":109,"categories":110,"keywords":111,"publishedAt":19},"01M7AWTR056C3P9R3VS8YVM2WX","video","When the user wants to create, generate, or produce video content using AI tools or programmatic frameworks. Also use when the user mentions 'video production,' 'AI video,' 'Remotion,' 'Hyperframes,' 'HeyGen,' 'Synthesia,' 'Veo,' 'Runway,' 'Kling,' 'Pika,' 'video generation,' 'AI avatar,' 'talking head video,' 'programmatic video,' 'video template,' 'explainer video,' 'product demo video,' 'video pipeline,' or 'make me a video.' Use this for video creation, generation, and production workflows. For video content strategy and what to post, see social-content. For paid video ad creative, see ad-creative.","https:\u002F\u002Fgithub.com\u002Fbarkleesanders\u002Fclaude-code-starter\u002Fblob\u002Fmain\u002Fskills\u002Fvideo\u002FSKILL.md",[],[],{"skillNo":113,"name":114,"nameZh":6,"description":115,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":116,"categories":117,"keywords":118,"publishedAt":19},"01M7AWTHTWBMTYZPMHHEYX3TTG","manim-video","Production pipeline for mathematical and technical animations using Manim Community Edition. Creates 3Blue1Brown-style explainer videos, algorithm visualizations, equation derivations, architecture diagrams, and data stories. Use when users request: animated explanations, math animations, concept visualizations, algorithm walkthroughs, technical explainers, 3Blue1Brown style videos, or any programmatic animation with geometric\u002Fmathematical content.","https:\u002F\u002Fgithub.com\u002Fbarkleesanders\u002Fclaude-code-starter\u002Fblob\u002Fmain\u002Fskills\u002Fvideo-use\u002Fskills\u002Fmanim-video\u002FSKILL.md",[],[],{"skillNo":120,"name":121,"nameZh":6,"description":122,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":123,"categories":124,"keywords":125,"publishedAt":19},"01M7AWTCXDJ9NWFQW51ENM8A2Z","video-use","Edit any video by conversation. Transcribe, cut, color grade, generate overlay animations, burn subtitles — for talking heads, montages, tutorials, travel, interviews. No presets, no menus. Ask questions, confirm the plan, execute, iterate, persist. Production-correctness rules are hard; everything else is artistic freedom.","https:\u002F\u002Fgithub.com\u002Fbarkleesanders\u002Fclaude-code-starter\u002Fblob\u002Fmain\u002Fskills\u002Fvideo-use\u002FSKILL.md",[],[],{"skillNo":127,"name":128,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":129,"categories":130,"keywords":131,"publishedAt":19},"01M7AWTA1D5FP895S33GHSA2G5","ui-improver","https:\u002F\u002Fgithub.com\u002Fbarkleesanders\u002Fclaude-code-starter\u002Fblob\u002Fmain\u002Fskills\u002Fui-improver\u002FSKILL.md",[],[]]