[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6CDKYYXDDMSX1DHSA0KZ31H":3,"skill-same:01M6CDKYYXDDMSX1DHSA0KZ31H":113},{"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":37,"linkOnly":38,"markdownContent":39,"markdownBody":40,"frontMatter":41,"refName":48,"commitSha":49,"skillDirectory":50,"forksCount":51,"repositoryHtmlUrl":52,"repositoryHomepageUrl":6,"ownerHtmlUrl":53,"ownerBlogUrl":54,"ownerDescription":55,"updatedAt":56,"install":57,"resources":70},"01M6CDKYYXDDMSX1DHSA0KZ31H","optimizing-prompts",null,"This skill optimizes prompts for large language models (llms) to reduce token usage, lower costs, and improve performance. it analyzes the prompt, identifies areas for simplification and redundancy removal, and rewrites the prompt to be more conci...","BbgnsurfTech\u002Fclaude-skills-collection","BbgnsurfTech","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F59598605?v=4","01M6C5ZT4G3G4QPQB64QDVW438","Bbgnsurf Technologies","01M6C5ZT8JN4VWSZZH3DD8J4EG",29,"MIT","https:\u002F\u002Fgithub.com\u002FBbgnsurfTech\u002Fclaude-skills-collection\u002Fblob\u002Fmain\u002Fplugins\u002Fclaude-code-plugins-plus\u002Fplugins\u002Fpackages\u002Fai-ml-engineering-pack\u002Fskills\u002Fai-ml-engineering-pack\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],"prompts","Optimizing Prompts","large language models","llms","performance","Bash","improve","grep","prompt","read","write","edit","models","2026-11-10 10:12:30",false,"---\ndescription: This skill optimizes prompts for large language models (llms) to reduce\n  token usage, lower costs, and improve performance. it analyzes the prompt, identifies\n  areas for simplification and redundancy removal, and rewrites the prompt to be more\n  conci...\nallowed-tools:\n- Read\n- Write\n- Edit\n- Grep\n- Glob\n- Bash\nname: optimizing-prompts\nlicense: MIT\n---\n## Overview\n\nThis skill empowers Claude to refine prompts for optimal LLM performance. It streamlines prompts to minimize token count, thereby reducing costs and enhancing response speed, all while maintaining or improving output quality.\n\n## How It Works\n\n1. **Analyzing Prompt**: The skill analyzes the input prompt to identify areas of redundancy, verbosity, and potential for simplification.\n2. **Rewriting Prompt**: It rewrites the prompt using techniques like concise language, targeted instructions, and efficient phrasing.\n3. **Suggesting Alternatives**: The skill provides the optimized prompt along with an explanation of the changes made and their expected impact.\n\n## When to Use This Skill\n\nThis skill activates when you need to:\n- Reduce the cost of using an LLM.\n- Improve the speed of LLM responses.\n- Enhance the quality or clarity of LLM outputs by refining the prompt.\n\n## Examples\n\n### Example 1: Reducing LLM Costs\n\nUser request: \"Optimize this prompt for cost and quality: 'I would like you to create a detailed product description for a new ergonomic office chair, highlighting its features, benefits, and target audience, and also include information about its warranty and return policy.'\"\n\nThe skill will:\n1. Analyze the prompt for redundancies and areas for simplification.\n2. Rewrite the prompt to be more concise: \"Create a product description for an ergonomic office chair. Include features, benefits, target audience, warranty, and return policy.\"\n3. Provide the optimized prompt and explain the token reduction achieved.\n\n### Example 2: Improving Prompt Performance\n\nUser request: \"Optimize this prompt for better summarization: 'Please read the following document and provide a comprehensive summary of all the key points, main arguments, supporting evidence, and overall conclusion, ensuring that the summary is accurate, concise, and easy to understand.'\"\n\nThe skill will:\n1. Identify areas for improvement in the prompt's clarity and focus.\n2. Rewrite the prompt to be more direct: \"Summarize this document, including key points, arguments, evidence, and the conclusion.\"\n3. Present the optimized prompt and explain how it enhances summarization performance.\n\n## Best Practices\n\n- **Clarity**: Ensure the original prompt is clear and well-defined before optimization.\n- **Context**: Provide sufficient context to the skill so it can understand the prompt's purpose.\n- **Iteration**: Iterate on the optimized prompt based on the LLM's output to fine-tune performance.\n\n## Integration\n\nThis skill integrates with the `prompt-architect` agent to leverage advanced prompt engineering techniques. It can also be used in conjunction with the `llm-integration-expert` to optimize prompts for specific LLM APIs.","## Overview\n\nThis skill empowers Claude to refine prompts for optimal LLM performance. It streamlines prompts to minimize token count, thereby reducing costs and enhancing response speed, all while maintaining or improving output quality.\n\n## How It Works\n\n1. **Analyzing Prompt**: The skill analyzes the input prompt to identify areas of redundancy, verbosity, and potential for simplification.\n2. **Rewriting Prompt**: It rewrites the prompt using techniques like concise language, targeted instructions, and efficient phrasing.\n3. **Suggesting Alternatives**: The skill provides the optimized prompt along with an explanation of the changes made and their expected impact.\n\n## When to Use This Skill\n\nThis skill activates when you need to:\n- Reduce the cost of using an LLM.\n- Improve the speed of LLM responses.\n- Enhance the quality or clarity of LLM outputs by refining the prompt.\n\n## Examples\n\n### Example 1: Reducing LLM Costs\n\nUser request: \"Optimize this prompt for cost and quality: 'I would like you to create a detailed product description for a new ergonomic office chair, highlighting its features, benefits, and target audience, and also include information about its warranty and return policy.'\"\n\nThe skill will:\n1. Analyze the prompt for redundancies and areas for simplification.\n2. Rewrite the prompt to be more concise: \"Create a product description for an ergonomic office chair. Include features, benefits, target audience, warranty, and return policy.\"\n3. Provide the optimized prompt and explain the token reduction achieved.\n\n### Example 2: Improving Prompt Performance\n\nUser request: \"Optimize this prompt for better summarization: 'Please read the following document and provide a comprehensive summary of all the key points, main arguments, supporting evidence, and overall conclusion, ensuring that the summary is accurate, concise, and easy to understand.'\"\n\nThe skill will:\n1. Identify areas for improvement in the prompt's clarity and focus.\n2. Rewrite the prompt to be more direct: \"Summarize this document, including key points, arguments, evidence, and the conclusion.\"\n3. Present the optimized prompt and explain how it enhances summarization performance.\n\n## Best Practices\n\n- **Clarity**: Ensure the original prompt is clear and well-defined before optimization.\n- **Context**: Provide sufficient context to the skill so it can understand the prompt's purpose.\n- **Iteration**: Iterate on the optimized prompt based on the LLM's output to fine-tune performance.\n\n## Integration\n\nThis skill integrates with the `prompt-architect` agent to leverage advanced prompt engineering techniques. It can also be used in conjunction with the `llm-integration-expert` to optimize prompts for specific LLM APIs.",{"name":5,"license":15,"description":7,"allowed-tools":42},[43,44,45,46,47,29],"Read","Write","Edit","Grep","Glob","main","01d3fafeca1133f841956b8b90b939fee92d71e7","plugins\u002Fclaude-code-plugins-plus\u002Fplugins\u002Fpackages\u002Fai-ml-engineering-pack\u002Fskills\u002Fai-ml-engineering-pack",9,"https:\u002F\u002Fgithub.com\u002FBbgnsurfTech\u002Fclaude-skills-collection","https:\u002F\u002Fgithub.com\u002FBbgnsurfTech","www.bbgnsurf.com","An ICT solutions provider and software development company","2025-12-18 20:19:58",{"source":8,"skillName":5,"commands":58,"prompt":68,"zipAvailable":69},[59,62,65],{"tool":60,"command":61},"npx","npx skills add BbgnsurfTech\u002Fclaude-skills-collection --skill optimizing-prompts",{"tool":63,"command":64},"bunx","bunx skills add BbgnsurfTech\u002Fclaude-skills-collection --skill optimizing-prompts",{"tool":66,"command":67},"pnpm","pnpm dlx skills add BbgnsurfTech\u002Fclaude-skills-collection --skill optimizing-prompts","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FBbgnsurfTech\u002Fclaude-skills-collection\u002Fblob\u002Fmain\u002Fplugins\u002Fclaude-code-plugins-plus\u002Fplugins\u002Fpackages\u002Fai-ml-engineering-pack\u002Fskills\u002Fai-ml-engineering-pack\u002FSKILL.md",true,[71,77,81,85,89,95,101,105,109],{"path":72,"resourceType":73,"resourceTypeDesc":74,"sizeBytes":75,"sourceHtmlUrl":76},"assets\u002Fexample_prompts.md","ASSET","资产文件",8562,"https:\u002F\u002Fgithub.com\u002FBbgnsurfTech\u002Fclaude-skills-collection\u002Fblob\u002Fmain\u002Fplugins\u002Fclaude-code-plugins-plus\u002Fplugins\u002Fpackages\u002Fai-ml-engineering-pack\u002Fskills\u002Fai-ml-engineering-pack\u002Fassets\u002Fexample_prompts.md",{"path":78,"resourceType":73,"resourceTypeDesc":74,"sizeBytes":79,"sourceHtmlUrl":80},"assets\u002Foptimization_report_template.md",5626,"https:\u002F\u002Fgithub.com\u002FBbgnsurfTech\u002Fclaude-skills-collection\u002Fblob\u002Fmain\u002Fplugins\u002Fclaude-code-plugins-plus\u002Fplugins\u002Fpackages\u002Fai-ml-engineering-pack\u002Fskills\u002Fai-ml-engineering-pack\u002Fassets\u002Foptimization_report_template.md",{"path":82,"resourceType":73,"resourceTypeDesc":74,"sizeBytes":83,"sourceHtmlUrl":84},"assets\u002Fprompt_template.json",2863,"https:\u002F\u002Fgithub.com\u002FBbgnsurfTech\u002Fclaude-skills-collection\u002Fblob\u002Fmain\u002Fplugins\u002Fclaude-code-plugins-plus\u002Fplugins\u002Fpackages\u002Fai-ml-engineering-pack\u002Fskills\u002Fai-ml-engineering-pack\u002Fassets\u002Fprompt_template.json",{"path":86,"resourceType":73,"resourceTypeDesc":74,"sizeBytes":87,"sourceHtmlUrl":88},"assets\u002FREADME.md",299,"https:\u002F\u002Fgithub.com\u002FBbgnsurfTech\u002Fclaude-skills-collection\u002Fblob\u002Fmain\u002Fplugins\u002Fclaude-code-plugins-plus\u002Fplugins\u002Fpackages\u002Fai-ml-engineering-pack\u002Fskills\u002Fai-ml-engineering-pack\u002Fassets\u002FREADME.md",{"path":90,"resourceType":91,"resourceTypeDesc":92,"sizeBytes":93,"sourceHtmlUrl":94},"references\u002FREADME.md","REFERENCE","参考文档",392,"https:\u002F\u002Fgithub.com\u002FBbgnsurfTech\u002Fclaude-skills-collection\u002Fblob\u002Fmain\u002Fplugins\u002Fclaude-code-plugins-plus\u002Fplugins\u002Fpackages\u002Fai-ml-engineering-pack\u002Fskills\u002Fai-ml-engineering-pack\u002Freferences\u002FREADME.md",{"path":96,"resourceType":97,"resourceTypeDesc":98,"sizeBytes":99,"sourceHtmlUrl":100},"scripts\u002Fcost_estimator.py","SCRIPT","脚本",2879,"https:\u002F\u002Fgithub.com\u002FBbgnsurfTech\u002Fclaude-skills-collection\u002Fblob\u002Fmain\u002Fplugins\u002Fclaude-code-plugins-plus\u002Fplugins\u002Fpackages\u002Fai-ml-engineering-pack\u002Fskills\u002Fai-ml-engineering-pack\u002Fscripts\u002Fcost_estimator.py",{"path":102,"resourceType":97,"resourceTypeDesc":98,"sizeBytes":103,"sourceHtmlUrl":104},"scripts\u002Fprompt_optimizer.py",2931,"https:\u002F\u002Fgithub.com\u002FBbgnsurfTech\u002Fclaude-skills-collection\u002Fblob\u002Fmain\u002Fplugins\u002Fclaude-code-plugins-plus\u002Fplugins\u002Fpackages\u002Fai-ml-engineering-pack\u002Fskills\u002Fai-ml-engineering-pack\u002Fscripts\u002Fprompt_optimizer.py",{"path":106,"resourceType":97,"resourceTypeDesc":98,"sizeBytes":107,"sourceHtmlUrl":108},"scripts\u002Fprompt_validator.py",2845,"https:\u002F\u002Fgithub.com\u002FBbgnsurfTech\u002Fclaude-skills-collection\u002Fblob\u002Fmain\u002Fplugins\u002Fclaude-code-plugins-plus\u002Fplugins\u002Fpackages\u002Fai-ml-engineering-pack\u002Fskills\u002Fai-ml-engineering-pack\u002Fscripts\u002Fprompt_validator.py",{"path":110,"resourceType":97,"resourceTypeDesc":98,"sizeBytes":111,"sourceHtmlUrl":112},"scripts\u002FREADME.md",409,"https:\u002F\u002Fgithub.com\u002FBbgnsurfTech\u002Fclaude-skills-collection\u002Fblob\u002Fmain\u002Fplugins\u002Fclaude-code-plugins-plus\u002Fplugins\u002Fpackages\u002Fai-ml-engineering-pack\u002Fskills\u002Fai-ml-engineering-pack\u002Fscripts\u002FREADME.md",[114,133,152,173,186,200],{"skillNo":115,"name":116,"nameZh":6,"description":117,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":118,"categories":119,"keywords":123,"publishedAt":37},"01M6CDVX5RHG36WP2Z7X8WAYYA","testing-visual-regression","Detect visual changes in UI components using screenshot comparison.\nUse when detecting unintended UI changes or pixel differences.\nTrigger with phrases like \"test visual changes\", \"compare screenshots\", or \"detect UI regressions\".","https:\u002F\u002Fgithub.com\u002FBbgnsurfTech\u002Fclaude-skills-collection\u002Fblob\u002Fmain\u002Fplugins\u002Fclaude-code-plugins-plus\u002Fplugins\u002Ftesting\u002Fvisual-regression-tester\u002Fskills\u002Fvisual-regression-tester\u002FSKILL.md",[120],{"categoryNo":121,"categoryName":122,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000008","测试与质量",[124,125,126,35,31,33,34,127,128,129,130,131,132,29],"testing visual regression","testing","regression","use","components","test","screenshots","screenshot","ui",{"skillNo":134,"name":135,"nameZh":6,"description":136,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":137,"categories":138,"keywords":140,"publishedAt":37},"01M6CDVT4S54EMAPZ231KSP2XQ","generating-unit-tests","Automatically generate comprehensive unit tests from source code covering happy paths, edge cases, and error conditions.\nUse when creating test coverage for functions, classes, or modules.\nTrigger with phrases like \"generate unit tests\", \"create tests for\", or \"add test coverage\".","https:\u002F\u002Fgithub.com\u002FBbgnsurfTech\u002Fclaude-skills-collection\u002Fblob\u002Fmain\u002Fplugins\u002Fclaude-code-plugins-plus\u002Fplugins\u002Ftesting\u002Funit-test-generator\u002Fskills\u002Funit-test-generator\u002FSKILL.md",[139],{"categoryNo":121,"categoryName":122,"taxonomyType":21,"taxonomyTypeDesc":22},[141,142,143,144,145,129,35,146,147,148,127,149,150,34,33,31,29,151],"unit tests","Generating Unit Tests","generate","create","add test","functions","modules","test coverage","coverage","code","edge",{"skillNo":153,"name":154,"nameZh":6,"description":155,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":156,"categories":157,"keywords":164,"publishedAt":37},"01M6CDVPQKGQ450Q50ZC84FPMR","generating-test-reports","Generate comprehensive test reports with metrics, coverage, and visualizations.\nUse when performing specialized testing.\nTrigger with phrases like \"generate test report\", \"create test documentation\", or \"show test metrics\".","https:\u002F\u002Fgithub.com\u002FBbgnsurfTech\u002Fclaude-skills-collection\u002Fblob\u002Fmain\u002Fplugins\u002Fclaude-code-plugins-plus\u002Fplugins\u002Ftesting\u002Ftest-report-generator\u002Fskills\u002Ftest-report-generator\u002FSKILL.md",[158,159],{"categoryNo":121,"categoryName":122,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":160,"categoryName":161,"taxonomyType":162,"taxonomyTypeDesc":163},"01JBSEEDCAT000000000000034","行政与办公人员","PROFESSION","适用职业",[129,165,166,167,168,127,149,35,169,34,33,170,29,171,143,144,172,125,31],"reports","Generating Test Reports","test report","specialized","report","visualizations","metrics","documentation",{"skillNo":174,"name":175,"nameZh":6,"description":176,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":177,"categories":178,"keywords":180,"publishedAt":37},"01M6CDVK97VFZ53CEYEGQ4QFZ6","orchestrating-test-execution","Coordinate parallel test execution across multiple environments and frameworks.\nUse when performing specialized testing.\nTrigger with phrases like \"orchestrate tests\", \"run parallel tests\", or \"coordinate test execution\".","https:\u002F\u002Fgithub.com\u002FBbgnsurfTech\u002Fclaude-skills-collection\u002Fblob\u002Fmain\u002Fplugins\u002Fclaude-code-plugins-plus\u002Fplugins\u002Ftesting\u002Ftest-orchestrator\u002Fskills\u002Ftest-orchestrator\u002FSKILL.md",[179],{"categoryNo":121,"categoryName":122,"taxonomyType":21,"taxonomyTypeDesc":22},[181,182,129,33,127,35,34,168,31,183,29,184,185,125],"orchestrating test execution","execution","parallel","orchestrate","run",{"skillNo":187,"name":188,"nameZh":6,"description":189,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":190,"categories":191,"keywords":193,"publishedAt":37},"01M6CDVFTCBQ65TGB1YJCZB90G","managing-test-environments","Provision and manage isolated test environments with configuration and data.\nUse when performing specialized testing.\nTrigger with phrases like \"manage test environment\", \"provision test env\", or \"setup test infrastructure\".","https:\u002F\u002Fgithub.com\u002FBbgnsurfTech\u002Fclaude-skills-collection\u002Fblob\u002Fmain\u002Fplugins\u002Fclaude-code-plugins-plus\u002Fplugins\u002Ftesting\u002Ftest-environment-manager\u002Fskills\u002Ftest-environment-manager\u002FSKILL.md",[192],{"categoryNo":121,"categoryName":122,"taxonomyType":21,"taxonomyTypeDesc":22},[194,129,35,34,33,168,31,29,195,196,197,125,198,199,127],"Managing Test Environments","data","infrastructure","setup","environment","manage",{"skillNo":201,"name":202,"nameZh":6,"description":203,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":204,"categories":205,"keywords":207,"publishedAt":37},"01M6CDVD0NPFXVEQGT9CMF02H0","generating-test-doubles","Generate mocks, stubs, spies, and fakes for dependency isolation.\nUse when creating mocks, stubs, or test isolation fixtures.\nTrigger with phrases like \"generate mocks\", \"create test doubles\", or \"setup stubs\".","https:\u002F\u002Fgithub.com\u002FBbgnsurfTech\u002Fclaude-skills-collection\u002Fblob\u002Fmain\u002Fplugins\u002Fclaude-code-plugins-plus\u002Fplugins\u002Ftesting\u002Ftest-doubles-generator\u002Fskills\u002Ftest-doubles-generator\u002FSKILL.md",[206],{"categoryNo":121,"categoryName":122,"taxonomyType":21,"taxonomyTypeDesc":22},[129,208,209,127,35,34,33,31,29,143,144,197],"Generating Test Doubles","dependency"]