[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6DXVTZXEJK7RF4S9DEKJ3RG":3,"skill-same:01M6DXVTZXEJK7RF4S9DEKJ3RG":83},{"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":23,"publishedAt":43,"linkOnly":44,"markdownContent":45,"markdownBody":46,"frontMatter":47,"refName":49,"commitSha":50,"skillDirectory":51,"forksCount":14,"repositoryHtmlUrl":52,"repositoryHomepageUrl":6,"ownerHtmlUrl":53,"ownerBlogUrl":54,"ownerDescription":55,"updatedAt":56,"install":57,"resources":70},"01M6DXVTZXEJK7RF4S9DEKJ3RG","prompt-engineer",null,"Expert in designing effective prompts for LLM-powered applications. Masters prompt structure, context management, output formatting, and prompt evaluation. Use when: prompt engineering, system prompt, few-shot, chain of thought, prompt design.","EthanSheehan\u002FGrid-Sentinel","EthanSheehan","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F174215275?v=4","01M6DX9589ENESB2AYW9YK4Y50","Ethan Sheehan","01M6DX95P06JXASASFQZRFQ1NM",0,"MIT","https:\u002F\u002Fgithub.com\u002FEthanSheehan\u002FGrid-Sentinel\u002Fblob\u002Fmain\u002F.agent\u002Fskills\u002Fprompt-engineer\u002FSKILL.md",[18],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42],"prompt engineer","engineer","prompt","context","chain","context management","formatting","structure","expert","prompts","use","management","design","system","applications","Evaluation","engineering","apache","prompt engineering","2026-11-10 10:12:30",false,"---\nname: prompt-engineer\ndescription: \"Expert in designing effective prompts for LLM-powered applications. Masters prompt structure, context management, output formatting, and prompt evaluation. Use when: prompt engineering, system prompt, few-shot, chain of thought, prompt design.\"\nsource: vibeship-spawner-skills (Apache 2.0)\n---\n\n# Prompt Engineer\n\n**Role**: LLM Prompt Architect\n\nI translate intent into instructions that LLMs actually follow. I know\nthat prompts are programming - they need the same rigor as code. I iterate\nrelentlessly because small changes have big effects. I evaluate systematically\nbecause intuition about prompt quality is often wrong.\n\n## Capabilities\n\n- Prompt design and optimization\n- System prompt architecture\n- Context window management\n- Output format specification\n- Prompt testing and evaluation\n- Few-shot example design\n\n## Requirements\n\n- LLM fundamentals\n- Understanding of tokenization\n- Basic programming\n\n## Patterns\n\n### Structured System Prompt\n\nWell-organized system prompt with clear sections\n\n```javascript\n- Role: who the model is\n- Context: relevant background\n- Instructions: what to do\n- Constraints: what NOT to do\n- Output format: expected structure\n- Examples: demonstration of correct behavior\n```\n\n### Few-Shot Examples\n\nInclude examples of desired behavior\n\n```javascript\n- Show 2-5 diverse examples\n- Include edge cases in examples\n- Match example difficulty to expected inputs\n- Use consistent formatting across examples\n- Include negative examples when helpful\n```\n\n### Chain-of-Thought\n\nRequest step-by-step reasoning\n\n```javascript\n- Ask model to think step by step\n- Provide reasoning structure\n- Request explicit intermediate steps\n- Parse reasoning separately from answer\n- Use for debugging model failures\n```\n\n## Anti-Patterns\n\n### ❌ Vague Instructions\n\n### ❌ Kitchen Sink Prompt\n\n### ❌ No Negative Instructions\n\n## ⚠️ Sharp Edges\n\n| Issue | Severity | Solution |\n|-------|----------|----------|\n| Using imprecise language in prompts | high | Be explicit: |\n| Expecting specific format without specifying it | high | Specify format explicitly: |\n| Only saying what to do, not what to avoid | medium | Include explicit don'ts: |\n| Changing prompts without measuring impact | medium | Systematic evaluation: |\n| Including irrelevant context 'just in case' | medium | Curate context: |\n| Biased or unrepresentative examples | medium | Diverse examples: |\n| Using default temperature for all tasks | medium | Task-appropriate temperature: |\n| Not considering prompt injection in user input | high | Defend against injection: |\n\n## Related Skills\n\nWorks well with: `ai-agents-architect`, `rag-engineer`, `backend`, `product-manager`\n","# Prompt Engineer\n\n**Role**: LLM Prompt Architect\n\nI translate intent into instructions that LLMs actually follow. I know\nthat prompts are programming - they need the same rigor as code. I iterate\nrelentlessly because small changes have big effects. I evaluate systematically\nbecause intuition about prompt quality is often wrong.\n\n## Capabilities\n\n- Prompt design and optimization\n- System prompt architecture\n- Context window management\n- Output format specification\n- Prompt testing and evaluation\n- Few-shot example design\n\n## Requirements\n\n- LLM fundamentals\n- Understanding of tokenization\n- Basic programming\n\n## Patterns\n\n### Structured System Prompt\n\nWell-organized system prompt with clear sections\n\n```javascript\n- Role: who the model is\n- Context: relevant background\n- Instructions: what to do\n- Constraints: what NOT to do\n- Output format: expected structure\n- Examples: demonstration of correct behavior\n```\n\n### Few-Shot Examples\n\nInclude examples of desired behavior\n\n```javascript\n- Show 2-5 diverse examples\n- Include edge cases in examples\n- Match example difficulty to expected inputs\n- Use consistent formatting across examples\n- Include negative examples when helpful\n```\n\n### Chain-of-Thought\n\nRequest step-by-step reasoning\n\n```javascript\n- Ask model to think step by step\n- Provide reasoning structure\n- Request explicit intermediate steps\n- Parse reasoning separately from answer\n- Use for debugging model failures\n```\n\n## Anti-Patterns\n\n### ❌ Vague Instructions\n\n### ❌ Kitchen Sink Prompt\n\n### ❌ No Negative Instructions\n\n## ⚠️ Sharp Edges\n\n| Issue | Severity | Solution |\n|-------|----------|----------|\n| Using imprecise language in prompts | high | Be explicit: |\n| Expecting specific format without specifying it | high | Specify format explicitly: |\n| Only saying what to do, not what to avoid | medium | Include explicit don'ts: |\n| Changing prompts without measuring impact | medium | Systematic evaluation: |\n| Including irrelevant context 'just in case' | medium | Curate context: |\n| Biased or unrepresentative examples | medium | Diverse examples: |\n| Using default temperature for all tasks | medium | Task-appropriate temperature: |\n| Not considering prompt injection in user input | high | Defend against injection: |\n\n## Related Skills\n\nWorks well with: `ai-agents-architect`, `rag-engineer`, `backend`, `product-manager`\n",{"name":5,"source":48,"description":7},"vibeship-spawner-skills (Apache 2.0)","main","33d99efaac9ea5758fc27120b467eca96ad020d9",".agent\u002Fskills\u002Fprompt-engineer","https:\u002F\u002Fgithub.com\u002FEthanSheehan\u002FGrid-Sentinel","https:\u002F\u002Fgithub.com\u002FEthanSheehan","https:\u002F\u002Fwww.linkedin.com\u002Fin\u002Fethan-sheehan\u002F","Aerospace Engineering Student at the University of Bristol \u002F\u002F Propulsion Lead at HyPower Bristol","2026-05-22 21:19:23",{"source":8,"skillName":5,"commands":58,"prompt":68,"zipAvailable":69},[59,62,65],{"tool":60,"command":61},"npx","npx skills add EthanSheehan\u002FGrid-Sentinel --skill prompt-engineer",{"tool":63,"command":64},"bunx","bunx skills add EthanSheehan\u002FGrid-Sentinel --skill prompt-engineer",{"tool":66,"command":67},"pnpm","pnpm dlx skills add EthanSheehan\u002FGrid-Sentinel --skill prompt-engineer","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FEthanSheehan\u002FGrid-Sentinel\u002Fblob\u002Fmain\u002F.agent\u002Fskills\u002Fprompt-engineer\u002FSKILL.md",true,[71,77],{"path":72,"resourceType":73,"resourceTypeDesc":74,"sizeBytes":75,"sourceHtmlUrl":76},"references\u002FSLIDES_STYLE_GUIDE_short.md","REFERENCE","参考文档",13787,"https:\u002F\u002Fgithub.com\u002Ffranklee16\u002Facademic-research-skills\u002Fblob\u002Fmaster\u002Fpresentations\u002Fpaper-slides\u002Freferences\u002FSLIDES_STYLE_GUIDE_short.md",{"path":78,"resourceType":79,"resourceTypeDesc":80,"sizeBytes":81,"sourceHtmlUrl":82},"scripts\u002Fverify_slides.py","SCRIPT","脚本",4657,"https:\u002F\u002Fgithub.com\u002Ffranklee16\u002Facademic-research-skills\u002Fblob\u002Fmaster\u002Fpresentations\u002Fpaper-slides\u002Fscripts\u002Fverify_slides.py",[84,110,142,162,176,201],{"skillNo":85,"name":86,"nameZh":6,"description":87,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":88,"categories":89,"keywords":91,"publishedAt":43},"01M6DY3X97YDSKHCCZG9KMASHA","zapier-make-patterns","No-code automation democratizes workflow building. Zapier and Make (formerly Integromat) let non-developers automate business processes without writing code. But no-code doesn't mean no-complexity - these platforms have their own patterns, pitfalls, and breaking points.  This skill covers when to use which platform, how to build reliable automations, and when to graduate to code-based solutions. Key insight: Zapier optimizes for simplicity and integrations (7000+ apps), Make optimizes for power","https:\u002F\u002Fgithub.com\u002FEthanSheehan\u002FGrid-Sentinel\u002Fblob\u002Fmain\u002F.agent\u002Fskills\u002Fzapier-make-patterns\u002FSKILL.md",[90],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[92,93,94,95,96,97,98,99,100,101,102,103,34,104,105,106,41,107,108,109],"zapier make patterns","patterns","workflow","integrations","how to","apps","platform","but","build","complexity","power","simplicity","business","automate","how","code","automation","writing",{"skillNo":111,"name":112,"nameZh":6,"description":113,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":114,"categories":115,"keywords":122,"publishedAt":43},"01M6DY3SVP128ZZPF2478H9JYZ","Cross-Site Scripting and HTML Injection Testing","This skill should be used when the user asks to \"test for XSS vulnerabilities\", \"perform cross-site scripting attacks\", \"identify HTML injection flaws\", \"exploit client-side injection vulnerabilities\", \"steal cookies via XSS\", or \"bypass content security policies\". It provides comprehensive techniques for detecting, exploiting, and understanding XSS and HTML injection attack vectors in web applications.","https:\u002F\u002Fgithub.com\u002FEthanSheehan\u002FGrid-Sentinel\u002Fblob\u002Fmain\u002F.agent\u002Fskills\u002Fxss-html-injection\u002FSKILL.md",[116,119],{"categoryNo":117,"categoryName":118,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000008","测试与质量",{"categoryNo":120,"categoryName":121,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000009","前端开发",[123,124,125,126,127,128,129,130,131,38,132,133,134,135,136,137,138,139,140,141],"html injection testing","Cross Site Scripting and HTML Injection Testing","injection","scripting","site","html","testing","exploit","user","xss","cookies","content","web","test","vectors","via","steal","security","vulnerabilities",{"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":15,"licenseFileUrl":6,"sourceHtmlUrl":146,"categories":147,"keywords":157,"publishedAt":43},"01M6DY3D694G80Y5N79CD1J575","writing-skills","Use when creating new skills, editing existing skills, or verifying skills work before deployment","https:\u002F\u002Fgithub.com\u002FEthanSheehan\u002FGrid-Sentinel\u002Fblob\u002Fmain\u002F.agent\u002Fskills\u002Fwriting-skills\u002FSKILL.md",[148,149,152],{"categoryNo":117,"categoryName":118,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":150,"categoryName":151,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000018","写作与文案",{"categoryNo":153,"categoryName":154,"taxonomyType":155,"taxonomyTypeDesc":156},"01JBSEEDCAT000000000000036","内容创作者","PROFESSION","适用职业",[109,158,159,34,160,161],"writing skills","deployment","editing","work",{"skillNo":163,"name":164,"nameZh":6,"description":165,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":166,"categories":167,"keywords":170,"publishedAt":43},"01M6DY3A7BM31W5Q2QARW00JHS","writing-plans","Use when you have a spec or requirements for a multi-step task, before touching code","https:\u002F\u002Fgithub.com\u002FEthanSheehan\u002FGrid-Sentinel\u002Fblob\u002Fmain\u002F.agent\u002Fskills\u002Fwriting-plans\u002FSKILL.md",[168,169],{"categoryNo":150,"categoryName":151,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":153,"categoryName":154,"taxonomyType":155,"taxonomyTypeDesc":156},[171,109,172,173,174,34,107,175],"writing plans","plans","requirements","task","spec",{"skillNo":177,"name":178,"nameZh":6,"description":179,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":180,"categories":181,"keywords":183,"publishedAt":43},"01M6DY36NSATM95HR7HMVZJYB3","workflow-automation","Workflow automation is the infrastructure that makes AI agents reliable. Without durable execution, a network hiccup during a 10-step payment flow means lost money and angry customers. With it, workflows resume exactly where they left off.  This skill covers the platforms (n8n, Temporal, Inngest) and patterns (sequential, parallel, orchestrator-worker) that turn brittle scripts into production-grade automation.  Key insight: The platforms make different tradeoffs. n8n optimizes for accessibility","https:\u002F\u002Fgithub.com\u002FEthanSheehan\u002FGrid-Sentinel\u002Fblob\u002Fmain\u002F.agent\u002Fskills\u002Fworkflow-automation\u002FSKILL.md",[182],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[184,108,94,185,186,187,41,188,189,190,191,192,193,194,195,196,197,198,199,200],"Workflow Automation","Production","flow","network","workflows","accessibility","ai agents","execution","scripts","worker","payment","n8n","money","resume","orchestrator","parallel","inngest",{"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":15,"licenseFileUrl":6,"sourceHtmlUrl":205,"categories":206,"keywords":208,"publishedAt":43},"01M6DY32QTGD80MQHJ8TPDH53H","WordPress Penetration Testing","This skill should be used when the user asks to \"pentest WordPress sites\", \"scan WordPress for vulnerabilities\", \"enumerate WordPress users, themes, or plugins\", \"exploit WordPress vulnerabilities\", or \"use WPScan\". It provides comprehensive WordPress security assessment methodologies.","https:\u002F\u002Fgithub.com\u002FEthanSheehan\u002FGrid-Sentinel\u002Fblob\u002Fmain\u002F.agent\u002Fskills\u002Fwordpress-penetration-testing\u002FSKILL.md",[207],{"categoryNo":117,"categoryName":118,"taxonomyType":21,"taxonomyTypeDesc":22},[129,203,209,210,211,212,213,214,130,34,131,215,216,141,140],"penetration testing","wordpress","security assessment","sites","scan","pentest","plugins","assessment"]