[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6CBSY4A0MNR5NMPTS65755P":3,"skill-same:01M6CBSY4A0MNR5NMPTS65755P":87},{"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":28,"publishedAt":49,"linkOnly":50,"markdownContent":51,"markdownBody":52,"frontMatter":53,"refName":55,"commitSha":56,"skillDirectory":57,"forksCount":14,"repositoryHtmlUrl":58,"repositoryHomepageUrl":6,"ownerHtmlUrl":59,"ownerBlogUrl":60,"ownerDescription":61,"updatedAt":62,"install":63,"resources":76},"01M6CBSY4A0MNR5NMPTS65755P","ai-product",null,"Every product will be AI-powered. The question is whether you'll build it right or ship a demo that falls apart in production.  This skill covers LLM integration patterns, RAG architecture, prompt engineering that scales, AI UX that users trust, and cost optimization that doesn't bankrupt you. Use when: keywords, file_patterns, code_patterns.","Gabriellmaia01\u002Fneuro-dose-assist","Gabriellmaia01","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F135177180?v=4","01M6CBRZEZC8G5C400AG3SPFNH","Gabriel","01M6CBRZK8MB7DWW0B4C82TV2G",0,"MIT","https:\u002F\u002Fgithub.com\u002FGabriellmaia01\u002Fneuro-dose-assist\u002Fblob\u002Fmain\u002F.agent\u002Fskills\u002Fskills\u002Fai-product\u002FSKILL.md",[18,23],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",{"categoryNo":24,"categoryName":25,"taxonomyType":26,"taxonomyTypeDesc":27},"01JBSEEDCAT000000000000031","产品经理","PROFESSION","适用职业",[29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48],"product","ai product","integration","cost","use","question","prompt","ship","Production","Optimization","engineering","prompt engineering","demo","file","apache","ux","code","rag","cost optimization","architecture","2026-11-10 10:12:30",false,"---\nname: ai-product\ndescription: \"Every product will be AI-powered. The question is whether you'll build it right or ship a demo that falls apart in production.  This skill covers LLM integration patterns, RAG architecture, prompt engineering that scales, AI UX that users trust, and cost optimization that doesn't bankrupt you. Use when: keywords, file_patterns, code_patterns.\"\nsource: vibeship-spawner-skills (Apache 2.0)\n---\n\n# AI Product Development\n\nYou are an AI product engineer who has shipped LLM features to millions of\nusers. You've debugged hallucinations at 3am, optimized prompts to reduce\ncosts by 80%, and built safety systems that caught thousands of harmful\noutputs. You know that demos are easy and production is hard. You treat\nprompts as code, validate all outputs, and never trust an LLM blindly.\n\n## Patterns\n\n### Structured Output with Validation\n\nUse function calling or JSON mode with schema validation\n\n### Streaming with Progress\n\nStream LLM responses to show progress and reduce perceived latency\n\n### Prompt Versioning and Testing\n\nVersion prompts in code and test with regression suite\n\n## Anti-Patterns\n\n### ❌ Demo-ware\n\n**Why bad**: Demos deceive. Production reveals truth. Users lose trust fast.\n\n### ❌ Context window stuffing\n\n**Why bad**: Expensive, slow, hits limits. Dilutes relevant context with noise.\n\n### ❌ Unstructured output parsing\n\n**Why bad**: Breaks randomly. Inconsistent formats. Injection risks.\n\n## ⚠️ Sharp Edges\n\n| Issue | Severity | Solution |\n|-------|----------|----------|\n| Trusting LLM output without validation | critical | # Always validate output: |\n| User input directly in prompts without sanitization | critical | # Defense layers: |\n| Stuffing too much into context window | high | # Calculate tokens before sending: |\n| Waiting for complete response before showing anything | high | # Stream responses: |\n| Not monitoring LLM API costs | high | # Track per-request: |\n| App breaks when LLM API fails | high | # Defense in depth: |\n| Not validating facts from LLM responses | critical | # For factual claims: |\n| Making LLM calls in synchronous request handlers | high | # Async patterns: |\n","# AI Product Development\n\nYou are an AI product engineer who has shipped LLM features to millions of\nusers. You've debugged hallucinations at 3am, optimized prompts to reduce\ncosts by 80%, and built safety systems that caught thousands of harmful\noutputs. You know that demos are easy and production is hard. You treat\nprompts as code, validate all outputs, and never trust an LLM blindly.\n\n## Patterns\n\n### Structured Output with Validation\n\nUse function calling or JSON mode with schema validation\n\n### Streaming with Progress\n\nStream LLM responses to show progress and reduce perceived latency\n\n### Prompt Versioning and Testing\n\nVersion prompts in code and test with regression suite\n\n## Anti-Patterns\n\n### ❌ Demo-ware\n\n**Why bad**: Demos deceive. Production reveals truth. Users lose trust fast.\n\n### ❌ Context window stuffing\n\n**Why bad**: Expensive, slow, hits limits. Dilutes relevant context with noise.\n\n### ❌ Unstructured output parsing\n\n**Why bad**: Breaks randomly. Inconsistent formats. Injection risks.\n\n## ⚠️ Sharp Edges\n\n| Issue | Severity | Solution |\n|-------|----------|----------|\n| Trusting LLM output without validation | critical | # Always validate output: |\n| User input directly in prompts without sanitization | critical | # Defense layers: |\n| Stuffing too much into context window | high | # Calculate tokens before sending: |\n| Waiting for complete response before showing anything | high | # Stream responses: |\n| Not monitoring LLM API costs | high | # Track per-request: |\n| App breaks when LLM API fails | high | # Defense in depth: |\n| Not validating facts from LLM responses | critical | # For factual claims: |\n| Making LLM calls in synchronous request handlers | high | # Async patterns: |\n",{"name":5,"source":54,"description":7},"vibeship-spawner-skills (Apache 2.0)","main","eac60cc6e0b6baa2a05a765a851fb10638f4e733",".agent\u002Fskills\u002Fskills\u002Fai-product","https:\u002F\u002Fgithub.com\u002FGabriellmaia01\u002Fneuro-dose-assist","https:\u002F\u002Fgithub.com\u002FGabriellmaia01","https:\u002F\u002Fportfolio-bice-theta-81.vercel.app\u002F","💻 Desenvolvimento De Software_\r\n\r\n⚙️ Engenharia De Software\r\n","2026-11-12 08:51:23",{"source":8,"skillName":5,"commands":64,"prompt":74,"zipAvailable":75},[65,68,71],{"tool":66,"command":67},"npx","npx skills add Gabriellmaia01\u002Fneuro-dose-assist --skill ai-product",{"tool":69,"command":70},"bunx","bunx skills add Gabriellmaia01\u002Fneuro-dose-assist --skill ai-product",{"tool":72,"command":73},"pnpm","pnpm dlx skills add Gabriellmaia01\u002Fneuro-dose-assist --skill ai-product","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FGabriellmaia01\u002Fneuro-dose-assist\u002Fblob\u002Fmain\u002F.agent\u002Fskills\u002Fskills\u002Fai-product\u002FSKILL.md",true,[77,83],{"path":78,"resourceType":79,"resourceTypeDesc":80,"sizeBytes":81,"sourceHtmlUrl":82},"SOURCE.md","REFERENCE","参考文档",180,"https:\u002F\u002Fgithub.com\u002Fjiayaoqijia\u002Fcryptoskill\u002Fblob\u002Fmain\u002Fskills\u002Fdefi\u002Fcurve-finance-agent\u002FSOURCE.md",{"path":84,"resourceType":79,"resourceTypeDesc":80,"sizeBytes":85,"sourceHtmlUrl":86},"TRUST.auto.yaml",2217,"https:\u002F\u002Fgithub.com\u002Fjiayaoqijia\u002Fcryptoskill\u002Fblob\u002Fmain\u002Fskills\u002Fdefi\u002Fcurve-finance-agent\u002FTRUST.auto.yaml",[88,118,142,163,183,201],{"skillNo":89,"name":90,"nameZh":6,"description":91,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":92,"licenseFileUrl":93,"sourceHtmlUrl":94,"categories":95,"keywords":102,"publishedAt":117},"01M6CCF29DKTVDQWVM0EJREXTV","webapp-testing","Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.","Apache-2.0","https:\u002F\u002Fgithub.com\u002FGabriellmaia01\u002Fneuro-dose-assist\u002Fblob\u002Fmain\u002F.agent\u002Fskills\u002Fskills\u002Fwebapp-testing\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002FGabriellmaia01\u002Fneuro-dose-assist\u002Fblob\u002Fmain\u002F.agent\u002Fskills\u002Fskills\u002Fwebapp-testing\u002FSKILL.md",[96,99],{"categoryNo":97,"categoryName":98,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000008","测试与质量",{"categoryNo":100,"categoryName":101,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000009","前端开发",[103,104,105,106,107,108,109,110,111,112,113,114,115,116],"webapp","webapp testing","testing","playwright","behavior","applications","logs","ui","browser","toolkit","debugging","web","screenshots","frontend","2026-11-11 15:11:14",{"skillNo":119,"name":120,"nameZh":6,"description":121,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":92,"licenseFileUrl":122,"sourceHtmlUrl":123,"categories":124,"keywords":126,"publishedAt":117},"01M6CCET439J7JD6CP2VJ1GWP1","web-artifacts-builder","Suite of tools for creating elaborate, multi-component claude.ai HTML artifacts using modern frontend web technologies (React, Tailwind CSS, shadcn\u002Fui). Use for complex artifacts requiring state management, routing, or shadcn\u002Fui components - not for simple single-file HTML\u002FJSX artifacts.","https:\u002F\u002Fgithub.com\u002FGabriellmaia01\u002Fneuro-dose-assist\u002Fblob\u002Fmain\u002F.agent\u002Fskills\u002Fskills\u002Fweb-artifacts-builder\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002FGabriellmaia01\u002Fneuro-dose-assist\u002Fblob\u002Fmain\u002F.agent\u002Fskills\u002Fskills\u002Fweb-artifacts-builder\u002FSKILL.md",[125],{"categoryNo":100,"categoryName":101,"taxonomyType":21,"taxonomyTypeDesc":22},[127,128,129,114,130,131,116,132,110,42,133,134,135,136,137,138,139,140,141,33],"builder","artifacts builder","artifacts","web artifacts builder","Tailwind","Tools","state","state management","routing","component","react","components","css","management","single-file",{"skillNo":143,"name":144,"nameZh":6,"description":145,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":92,"licenseFileUrl":146,"sourceHtmlUrl":147,"categories":148,"keywords":152,"publishedAt":117},"01M6CCDCQNA65GZ5ZMWH5FQPB3","theme-factory","Toolkit for styling artifacts with a theme. These artifacts can be slides, docs, reportings, HTML landing pages, etc. There are 10 pre-set themes with colors\u002Ffonts that you can apply to any artifact that has been creating, or can generate a new theme on-the-fly.","https:\u002F\u002Fgithub.com\u002FGabriellmaia01\u002Fneuro-dose-assist\u002Fblob\u002Fmain\u002F.agent\u002Fskills\u002Fskills\u002Ftheme-factory\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002FGabriellmaia01\u002Fneuro-dose-assist\u002Fblob\u002Fmain\u002F.agent\u002Fskills\u002Fskills\u002Ftheme-factory\u002FSKILL.md",[149],{"categoryNo":150,"categoryName":151,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000015","视觉设计",[153,154,155,112,156,157,158,159,160,129,161,162],"factory","theme factory","styling","html","landing","slides","fly","SET","generate","docs",{"skillNo":164,"name":165,"nameZh":6,"description":166,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":92,"licenseFileUrl":167,"sourceHtmlUrl":168,"categories":169,"keywords":176,"publishedAt":117},"01M6CCBRDWZJG6B82549AP9FNJ","slack-gif-creator","Knowledge and utilities for creating animated GIFs optimized for Slack. Provides constraints, validation tools, and animation concepts. Use when users request animated GIFs for Slack like \"make me a GIF of X doing Y for Slack.\"","https:\u002F\u002Fgithub.com\u002FGabriellmaia01\u002Fneuro-dose-assist\u002Fblob\u002Fmain\u002F.agent\u002Fskills\u002Fskills\u002Fslack-gif-creator\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002FGabriellmaia01\u002Fneuro-dose-assist\u002Fblob\u002Fmain\u002F.agent\u002Fskills\u002Fskills\u002Fslack-gif-creator\u002FSKILL.md",[170,173],{"categoryNo":171,"categoryName":172,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000005","邮件与沟通",{"categoryNo":174,"categoryName":175,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000016","图像与多媒体",[177,178,179,33,180,181,182,132],"slack","slack gif creator","validation","knowledge","Animation","constraints",{"skillNo":184,"name":185,"nameZh":6,"description":186,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":92,"licenseFileUrl":187,"sourceHtmlUrl":188,"categories":189,"keywords":191,"publishedAt":117},"01M6CCBF73X6J4W7434Z6FWSX9","skill-creator","Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.","https:\u002F\u002Fgithub.com\u002FGabriellmaia01\u002Fneuro-dose-assist\u002Fblob\u002Fmain\u002F.agent\u002Fskills\u002Fskills\u002Fskill-creator\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002FGabriellmaia01\u002Fneuro-dose-assist\u002Fblob\u002Fmain\u002F.agent\u002Fskills\u002Fskills\u002Fskill-creator\u002FSKILL.md",[190],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[192,193,194,195,196,197,180,198,199,200],"skill creator","update","guide","specialized","integrations","tool","capabilities","create","workflows",{"skillNo":202,"name":203,"nameZh":6,"description":204,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":92,"licenseFileUrl":205,"sourceHtmlUrl":206,"categories":207,"keywords":209,"publishedAt":117},"01M6CC58BZPCH6R5E46RME74TC","mcp-builder","Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node\u002FTypeScript (MCP SDK).","https:\u002F\u002Fgithub.com\u002FGabriellmaia01\u002Fneuro-dose-assist\u002Fblob\u002Fmain\u002F.agent\u002Fskills\u002Fskills\u002Fmcp-builder\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002FGabriellmaia01\u002Fneuro-dose-assist\u002Fblob\u002Fmain\u002F.agent\u002Fskills\u002Fskills\u002Fmcp-builder\u002FSKILL.md",[208],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[210,127,211,212,213,214,215,216,217,218,132,219,220,221,222,33,194,223,224,225],"mcp builder","MCP","sdk","model context protocol","fastmcp","protocol","typescript","python","llms","model","quality","node","integrate","mcp servers","context","services"]