[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6DXVXKB7CF8JQKAFBWDB207":3,"skill-same:01M6DXVXKB7CF8JQKAFBWDB207":71},{"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":44,"linkOnly":45,"markdownContent":46,"markdownBody":47,"frontMatter":48,"refName":49,"commitSha":50,"skillDirectory":51,"forksCount":14,"repositoryHtmlUrl":52,"repositoryHomepageUrl":6,"ownerHtmlUrl":53,"ownerBlogUrl":54,"ownerDescription":55,"updatedAt":56,"install":57,"resources":70},"01M6DXVXKB7CF8JQKAFBWDB207","prompt-engineering",null,"Expert guide on prompt engineering patterns, best practices, and optimization techniques. Use when user wants to improve prompts, learn prompting strategies, or debug agent behavior.","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-engineering\u002FSKILL.md",[18],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43],"prompt engineering","engineering","prompt","prompting","strategies","patterns","expert","prompts","use","guide","user","behavior","improve","prompt engineering patterns","Optimization","best practices","learn","engineering patterns","debug","debug agent","2026-11-10 10:12:30",false,"---\nname: prompt-engineering\ndescription: Expert guide on prompt engineering patterns, best practices, and optimization techniques. Use when user wants to improve prompts, learn prompting strategies, or debug agent behavior.\n---\n\n# Prompt Engineering Patterns\n\nAdvanced prompt engineering techniques to maximize LLM performance, reliability, and controllability.\n\n## Core Capabilities\n\n### 1. Few-Shot Learning\n\nTeach the model by showing examples instead of explaining rules. Include 2-5 input-output pairs that demonstrate the desired behavior. Use when you need consistent formatting, specific reasoning patterns, or handling of edge cases. More examples improve accuracy but consume tokens—balance based on task complexity.\n\n**Example:**\n\n```markdown\nExtract key information from support tickets:\n\nInput: \"My login doesn't work and I keep getting error 403\"\nOutput: {\"issue\": \"authentication\", \"error_code\": \"403\", \"priority\": \"high\"}\n\nInput: \"Feature request: add dark mode to settings\"\nOutput: {\"issue\": \"feature_request\", \"error_code\": null, \"priority\": \"low\"}\n\nNow process: \"Can't upload files larger than 10MB, getting timeout\"\n```\n\n### 2. Chain-of-Thought Prompting\n\nRequest step-by-step reasoning before the final answer. Add \"Let's think step by step\" (zero-shot) or include example reasoning traces (few-shot). Use for complex problems requiring multi-step logic, mathematical reasoning, or when you need to verify the model's thought process. Improves accuracy on analytical tasks by 30-50%.\n\n**Example:**\n\n```markdown\nAnalyze this bug report and determine root cause.\n\nThink step by step:\n\n1. What is the expected behavior?\n2. What is the actual behavior?\n3. What changed recently that could cause this?\n4. What components are involved?\n5. What is the most likely root cause?\n\nBug: \"Users can't save drafts after the cache update deployed yesterday\"\n```\n\n### 3. Prompt Optimization\n\nSystematically improve prompts through testing and refinement. Start simple, measure performance (accuracy, consistency, token usage), then iterate. Test on diverse inputs including edge cases. Use A\u002FB testing to compare variations. Critical for production prompts where consistency and cost matter.\n\n**Example:**\n\n```markdown\nVersion 1 (Simple): \"Summarize this article\"\n→ Result: Inconsistent length, misses key points\n\nVersion 2 (Add constraints): \"Summarize in 3 bullet points\"\n→ Result: Better structure, but still misses nuance\n\nVersion 3 (Add reasoning): \"Identify the 3 main findings, then summarize each\"\n→ Result: Consistent, accurate, captures key information\n```\n\n### 4. Template Systems\n\nBuild reusable prompt structures with variables, conditional sections, and modular components. Use for multi-turn conversations, role-based interactions, or when the same pattern applies to different inputs. Reduces duplication and ensures consistency across similar tasks.\n\n**Example:**\n\n```python\n# Reusable code review template\ntemplate = \"\"\"\nReview this {language} code for {focus_area}.\n\nCode:\n{code_block}\n\nProvide feedback on:\n{checklist}\n\"\"\"\n\n# Usage\nprompt = template.format(\n    language=\"Python\",\n    focus_area=\"security vulnerabilities\",\n    code_block=user_code,\n    checklist=\"1. SQL injection\\n2. XSS risks\\n3. Authentication\"\n)\n```\n\n### 5. System Prompt Design\n\nSet global behavior and constraints that persist across the conversation. Define the model's role, expertise level, output format, and safety guidelines. Use system prompts for stable instructions that shouldn't change turn-to-turn, freeing up user message tokens for variable content.\n\n**Example:**\n\n```markdown\nSystem: You are a senior backend engineer specializing in API design.\n\nRules:\n\n- Always consider scalability and performance\n- Suggest RESTful patterns by default\n- Flag security concerns immediately\n- Provide code examples in Python\n- Use early return pattern\n\nFormat responses as:\n\n1. Analysis\n2. Recommendation\n3. Code example\n4. Trade-offs\n```\n\n## Key Patterns\n\n### Progressive Disclosure\n\nStart with simple prompts, add complexity only when needed:\n\n1. **Level 1**: Direct instruction\n\n   - \"Summarize this article\"\n\n2. **Level 2**: Add constraints\n\n   - \"Summarize this article in 3 bullet points, focusing on key findings\"\n\n3. **Level 3**: Add reasoning\n\n   - \"Read this article, identify the main findings, then summarize in 3 bullet points\"\n\n4. **Level 4**: Add examples\n   - Include 2-3 example summaries with input-output pairs\n\n### Instruction Hierarchy\n\n```\n[System Context] → [Task Instruction] → [Examples] → [Input Data] → [Output Format]\n```\n\n### Error Recovery\n\nBuild prompts that gracefully handle failures:\n\n- Include fallback instructions\n- Request confidence scores\n- Ask for alternative interpretations when uncertain\n- Specify how to indicate missing information\n\n## Best Practices\n\n1. **Be Specific**: Vague prompts produce inconsistent results\n2. **Show, Don't Tell**: Examples are more effective than descriptions\n3. **Test Extensively**: Evaluate on diverse, representative inputs\n4. **Iterate Rapidly**: Small changes can have large impacts\n5. **Monitor Performance**: Track metrics in production\n6. **Version Control**: Treat prompts as code with proper versioning\n7. **Document Intent**: Explain why prompts are structured as they are\n\n## Common Pitfalls\n\n- **Over-engineering**: Starting with complex prompts before trying simple ones\n- **Example pollution**: Using examples that don't match the target task\n- **Context overflow**: Exceeding token limits with excessive examples\n- **Ambiguous instructions**: Leaving room for multiple interpretations\n- **Ignoring edge cases**: Not testing on unusual or boundary inputs\n","# Prompt Engineering Patterns\n\nAdvanced prompt engineering techniques to maximize LLM performance, reliability, and controllability.\n\n## Core Capabilities\n\n### 1. Few-Shot Learning\n\nTeach the model by showing examples instead of explaining rules. Include 2-5 input-output pairs that demonstrate the desired behavior. Use when you need consistent formatting, specific reasoning patterns, or handling of edge cases. More examples improve accuracy but consume tokens—balance based on task complexity.\n\n**Example:**\n\n```markdown\nExtract key information from support tickets:\n\nInput: \"My login doesn't work and I keep getting error 403\"\nOutput: {\"issue\": \"authentication\", \"error_code\": \"403\", \"priority\": \"high\"}\n\nInput: \"Feature request: add dark mode to settings\"\nOutput: {\"issue\": \"feature_request\", \"error_code\": null, \"priority\": \"low\"}\n\nNow process: \"Can't upload files larger than 10MB, getting timeout\"\n```\n\n### 2. Chain-of-Thought Prompting\n\nRequest step-by-step reasoning before the final answer. Add \"Let's think step by step\" (zero-shot) or include example reasoning traces (few-shot). Use for complex problems requiring multi-step logic, mathematical reasoning, or when you need to verify the model's thought process. Improves accuracy on analytical tasks by 30-50%.\n\n**Example:**\n\n```markdown\nAnalyze this bug report and determine root cause.\n\nThink step by step:\n\n1. What is the expected behavior?\n2. What is the actual behavior?\n3. What changed recently that could cause this?\n4. What components are involved?\n5. What is the most likely root cause?\n\nBug: \"Users can't save drafts after the cache update deployed yesterday\"\n```\n\n### 3. Prompt Optimization\n\nSystematically improve prompts through testing and refinement. Start simple, measure performance (accuracy, consistency, token usage), then iterate. Test on diverse inputs including edge cases. Use A\u002FB testing to compare variations. Critical for production prompts where consistency and cost matter.\n\n**Example:**\n\n```markdown\nVersion 1 (Simple): \"Summarize this article\"\n→ Result: Inconsistent length, misses key points\n\nVersion 2 (Add constraints): \"Summarize in 3 bullet points\"\n→ Result: Better structure, but still misses nuance\n\nVersion 3 (Add reasoning): \"Identify the 3 main findings, then summarize each\"\n→ Result: Consistent, accurate, captures key information\n```\n\n### 4. Template Systems\n\nBuild reusable prompt structures with variables, conditional sections, and modular components. Use for multi-turn conversations, role-based interactions, or when the same pattern applies to different inputs. Reduces duplication and ensures consistency across similar tasks.\n\n**Example:**\n\n```python\n# Reusable code review template\ntemplate = \"\"\"\nReview this {language} code for {focus_area}.\n\nCode:\n{code_block}\n\nProvide feedback on:\n{checklist}\n\"\"\"\n\n# Usage\nprompt = template.format(\n    language=\"Python\",\n    focus_area=\"security vulnerabilities\",\n    code_block=user_code,\n    checklist=\"1. SQL injection\\n2. XSS risks\\n3. Authentication\"\n)\n```\n\n### 5. System Prompt Design\n\nSet global behavior and constraints that persist across the conversation. Define the model's role, expertise level, output format, and safety guidelines. Use system prompts for stable instructions that shouldn't change turn-to-turn, freeing up user message tokens for variable content.\n\n**Example:**\n\n```markdown\nSystem: You are a senior backend engineer specializing in API design.\n\nRules:\n\n- Always consider scalability and performance\n- Suggest RESTful patterns by default\n- Flag security concerns immediately\n- Provide code examples in Python\n- Use early return pattern\n\nFormat responses as:\n\n1. Analysis\n2. Recommendation\n3. Code example\n4. Trade-offs\n```\n\n## Key Patterns\n\n### Progressive Disclosure\n\nStart with simple prompts, add complexity only when needed:\n\n1. **Level 1**: Direct instruction\n\n   - \"Summarize this article\"\n\n2. **Level 2**: Add constraints\n\n   - \"Summarize this article in 3 bullet points, focusing on key findings\"\n\n3. **Level 3**: Add reasoning\n\n   - \"Read this article, identify the main findings, then summarize in 3 bullet points\"\n\n4. **Level 4**: Add examples\n   - Include 2-3 example summaries with input-output pairs\n\n### Instruction Hierarchy\n\n```\n[System Context] → [Task Instruction] → [Examples] → [Input Data] → [Output Format]\n```\n\n### Error Recovery\n\nBuild prompts that gracefully handle failures:\n\n- Include fallback instructions\n- Request confidence scores\n- Ask for alternative interpretations when uncertain\n- Specify how to indicate missing information\n\n## Best Practices\n\n1. **Be Specific**: Vague prompts produce inconsistent results\n2. **Show, Don't Tell**: Examples are more effective than descriptions\n3. **Test Extensively**: Evaluate on diverse, representative inputs\n4. **Iterate Rapidly**: Small changes can have large impacts\n5. **Monitor Performance**: Track metrics in production\n6. **Version Control**: Treat prompts as code with proper versioning\n7. **Document Intent**: Explain why prompts are structured as they are\n\n## Common Pitfalls\n\n- **Over-engineering**: Starting with complex prompts before trying simple ones\n- **Example pollution**: Using examples that don't match the target task\n- **Context overflow**: Exceeding token limits with excessive examples\n- **Ambiguous instructions**: Leaving room for multiple interpretations\n- **Ignoring edge cases**: Not testing on unusual or boundary inputs\n",{"name":5,"description":7},"main","33d99efaac9ea5758fc27120b467eca96ad020d9",".agent\u002Fskills\u002Fprompt-engineering","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-engineering",{"tool":63,"command":64},"bunx","bunx skills add EthanSheehan\u002FGrid-Sentinel --skill prompt-engineering",{"tool":66,"command":67},"pnpm","pnpm dlx skills add EthanSheehan\u002FGrid-Sentinel --skill prompt-engineering","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FEthanSheehan\u002FGrid-Sentinel\u002Fblob\u002Fmain\u002F.agent\u002Fskills\u002Fprompt-engineering\u002FSKILL.md",true,[],[72,98,130,150,164,189],{"skillNo":73,"name":74,"nameZh":6,"description":75,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":76,"categories":77,"keywords":79,"publishedAt":44},"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",[78],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[80,29,81,82,83,84,85,86,87,88,89,90,32,91,92,93,94,95,96,97],"zapier make patterns","workflow","integrations","how to","apps","platform","but","build","complexity","power","simplicity","business","automate","how","apache","code","automation","writing",{"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":110,"publishedAt":44},"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",[104,107],{"categoryNo":105,"categoryName":106,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000008","测试与质量",{"categoryNo":108,"categoryName":109,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000009","前端开发",[111,112,113,114,115,116,117,118,34,119,120,121,122,123,124,125,126,127,128,129],"html injection testing","Cross Site Scripting and HTML Injection Testing","injection","scripting","site","html","testing","exploit","applications","xss","cookies","content","web","test","vectors","via","steal","security","vulnerabilities",{"skillNo":131,"name":132,"nameZh":6,"description":133,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":134,"categories":135,"keywords":145,"publishedAt":44},"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",[136,137,140],{"categoryNo":105,"categoryName":106,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":138,"categoryName":139,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000018","写作与文案",{"categoryNo":141,"categoryName":142,"taxonomyType":143,"taxonomyTypeDesc":144},"01JBSEEDCAT000000000000036","内容创作者","PROFESSION","适用职业",[97,146,147,32,148,149],"writing skills","deployment","editing","work",{"skillNo":151,"name":152,"nameZh":6,"description":153,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":154,"categories":155,"keywords":158,"publishedAt":44},"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",[156,157],{"categoryNo":138,"categoryName":139,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":141,"categoryName":142,"taxonomyType":143,"taxonomyTypeDesc":144},[159,97,160,161,162,32,95,163],"writing plans","plans","requirements","task","spec",{"skillNo":165,"name":166,"nameZh":6,"description":167,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":168,"categories":169,"keywords":171,"publishedAt":44},"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",[170],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[172,96,81,173,174,175,94,176,177,178,179,180,181,182,183,184,185,186,187,188],"Workflow Automation","Production","flow","network","workflows","accessibility","ai agents","execution","scripts","worker","payment","n8n","money","resume","orchestrator","parallel","inngest",{"skillNo":190,"name":191,"nameZh":6,"description":192,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":193,"categories":194,"keywords":196,"publishedAt":44},"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",[195],{"categoryNo":105,"categoryName":106,"taxonomyType":21,"taxonomyTypeDesc":22},[117,191,197,198,199,200,201,202,118,32,34,203,204,129,128],"penetration testing","wordpress","security assessment","sites","scan","pentest","plugins","assessment"]