[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M718YDWPJTF957BBGSNKKNSR":3,"skill-same:01M718YDWPJTF957BBGSNKKNSR":86},{"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":60,"commitSha":61,"skillDirectory":62,"forksCount":14,"repositoryHtmlUrl":63,"repositoryHomepageUrl":6,"ownerHtmlUrl":64,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":65,"install":66,"resources":79},"01M718YDWPJTF957BBGSNKKNSR","aircraft-design-rag",null,"Retrieve and answer from the local RAG-data Markdown corpus for aircraft, missile, rocket, propulsion, engine, and aerospace design questions. Use when the user asks domain questions that should be grounded in local project knowledge instead of model memory.","C-zj02\u002FCFD-claw","C-zj02","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F249250493?v=4","01M718Y5H70TSFYFCPCY92GQEE","陈泽坚","01M718Y5HWP7WAP30A4YPQ9KFM",2,"MIT","https:\u002F\u002Fgithub.com\u002FC-zj02\u002FCFD-claw\u002Fblob\u002Fmain\u002F.clawd\u002Fskills\u002Faircraft-design-rag\u002FSKILL.md",[18,23],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000015","视觉设计","SCENARIO","使用场景",{"categoryNo":24,"categoryName":25,"taxonomyType":26,"taxonomyTypeDesc":27},"01JBSEEDCAT000000000000032","设计师","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],"aircraft design rag","rag","design","domain","when","for","answer","rocket","propulsion","project","local","project knowledge","query","use","model","knowledge","Bash","search","memory","python","2026-11-10 10:12:30",false,"---\nname: aircraft-design-rag\ndescription: Retrieve and answer from the local RAG-data Markdown corpus for aircraft, missile, rocket, propulsion, engine, and aerospace design questions. Use when the user asks domain questions that should be grounded in local project knowledge instead of model memory.\nallowed-tools:\n  - Bash\n  - Read\n  - Glob\narguments: [query]\nmax-turns: 100\nrun-command: python ${CLAUDE_SKILL_DIR}\u002Fscripts\u002Fsearch_rag.py --data-dir ${CLAUDE_PROJECT_DIR}\u002FRAG-data --query $ARGUMENTS --format json --use-cache --top-k 8 --max-snippet-chars 700\n---\n\nUse the local Markdown corpus under the project `RAG-data` directory as the primary knowledge base.\n\nWorkflow:\n\n1. Clawd runs the retriever automatically before the model answers. Use the returned command output as the evidence:\n   `python \"${CLAUDE_SKILL_DIR}\u002Fscripts\u002Fsearch_rag.py\" --data-dir \"${CLAUDE_PROJECT_DIR}\u002FRAG-data\" --query \"$ARGUMENTS\" --format json --use-cache --top-k 8 --max-snippet-chars 700`\n2. If the query contains an exact model or engine designation such as `YF-21`, `RD-170`, or `Orion 50`, search with that exact designation first.\n3. If the first retrieval is weak, try one or two shorter alternate queries built from the user's core technical terms.\n4. Use the JSON `hits` array as structured evidence. Each hit includes `file`, `start_line`, `end_line`, `heading`, `score`, and `snippet`.\n5. Answer only from retrieved evidence. Do not fill gaps with unsupported background knowledge.\n6. If the corpus still does not contain the answer, say clearly that the answer was not found in `RAG-data`.\n\nAnswer requirements:\n\n- Answer in Chinese by default.\n- Do not merely summarize that \"many aspects should be considered\". Give a direct, useful engineering answer.\n- For broad design questions such as \"如何设计一个好的发动机\", organize the answer as:\n  1. `先定义任务和指标`: state the mission\u002Fapplication, thrust or shaft power, fuel consumption, envelope, life, reliability, maintainability, cost, and integration constraints.\n  2. `总体方案权衡`: explain the cycle\u002Farchitecture choice and the trade-offs among performance, weight, temperature, pressure ratio, cooling, complexity, reliability, and maintainability.\n  3. `核心子系统设计`: cover inlet\u002Ffan\u002Fcompressor, combustor, turbine, nozzle, control\u002Ffuel, cooling\u002Fair system, lubrication\u002Faccessories, structure\u002Frotor dynamics, materials, and sensors\u002Fhealth monitoring when evidence supports them.\n  4. `限制与验证`: include operating limits, stability margin, strength\u002Fthermal\u002Fvibration margins, reliability and maintainability targets, rig tests, ground tests, and iterative verification.\n  5. `可执行检查清单`: end the main answer with concrete checklist items or next design steps.\n- If the retrieved evidence is sparse, still synthesize a structured answer from the retrieved evidence, and explicitly mark unsupported gaps as `资料未覆盖`.\n- End with an `依据` section that lists the file paths and line ranges you used.\n","Use the local Markdown corpus under the project `RAG-data` directory as the primary knowledge base.\n\nWorkflow:\n\n1. Clawd runs the retriever automatically before the model answers. Use the returned command output as the evidence:\n   `python \"${CLAUDE_SKILL_DIR}\u002Fscripts\u002Fsearch_rag.py\" --data-dir \"${CLAUDE_PROJECT_DIR}\u002FRAG-data\" --query \"$ARGUMENTS\" --format json --use-cache --top-k 8 --max-snippet-chars 700`\n2. If the query contains an exact model or engine designation such as `YF-21`, `RD-170`, or `Orion 50`, search with that exact designation first.\n3. If the first retrieval is weak, try one or two shorter alternate queries built from the user's core technical terms.\n4. Use the JSON `hits` array as structured evidence. Each hit includes `file`, `start_line`, `end_line`, `heading`, `score`, and `snippet`.\n5. Answer only from retrieved evidence. Do not fill gaps with unsupported background knowledge.\n6. If the corpus still does not contain the answer, say clearly that the answer was not found in `RAG-data`.\n\nAnswer requirements:\n\n- Answer in Chinese by default.\n- Do not merely summarize that \"many aspects should be considered\". Give a direct, useful engineering answer.\n- For broad design questions such as \"如何设计一个好的发动机\", organize the answer as:\n  1. `先定义任务和指标`: state the mission\u002Fapplication, thrust or shaft power, fuel consumption, envelope, life, reliability, maintainability, cost, and integration constraints.\n  2. `总体方案权衡`: explain the cycle\u002Farchitecture choice and the trade-offs among performance, weight, temperature, pressure ratio, cooling, complexity, reliability, and maintainability.\n  3. `核心子系统设计`: cover inlet\u002Ffan\u002Fcompressor, combustor, turbine, nozzle, control\u002Ffuel, cooling\u002Fair system, lubrication\u002Faccessories, structure\u002Frotor dynamics, materials, and sensors\u002Fhealth monitoring when evidence supports them.\n  4. `限制与验证`: include operating limits, stability margin, strength\u002Fthermal\u002Fvibration margins, reliability and maintainability targets, rig tests, ground tests, and iterative verification.\n  5. `可执行检查清单`: end the main answer with concrete checklist items or next design steps.\n- If the retrieved evidence is sparse, still synthesize a structured answer from the retrieved evidence, and explicitly mark unsupported gaps as `资料未覆盖`.\n- End with an `依据` section that lists the file paths and line ranges you used.\n",{"name":5,"arguments":54,"max-turns":55,"description":7,"run-command":56,"allowed-tools":57},[41],100,"python ${CLAUDE_SKILL_DIR}\u002Fscripts\u002Fsearch_rag.py --data-dir ${CLAUDE_PROJECT_DIR}\u002FRAG-data --query $ARGUMENTS --format json --use-cache --top-k 8 --max-snippet-chars 700",[45,58,59],"Read","Glob","main","70729a9e5e9c05a7facf6ce04080a9d013d1f96f",".clawd\u002Fskills\u002Faircraft-design-rag","https:\u002F\u002Fgithub.com\u002FC-zj02\u002FCFD-claw","https:\u002F\u002Fgithub.com\u002FC-zj02","2026-07-15 00:23:01",{"source":8,"skillName":5,"commands":67,"prompt":77,"zipAvailable":78},[68,71,74],{"tool":69,"command":70},"npx","npx skills add C-zj02\u002FCFD-claw --skill aircraft-design-rag",{"tool":72,"command":73},"bunx","bunx skills add C-zj02\u002FCFD-claw --skill aircraft-design-rag",{"tool":75,"command":76},"pnpm","pnpm dlx skills add C-zj02\u002FCFD-claw --skill aircraft-design-rag","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FC-zj02\u002FCFD-claw\u002Fblob\u002Fmain\u002F.clawd\u002Fskills\u002Faircraft-design-rag\u002FSKILL.md",true,[80],{"path":81,"resourceType":82,"resourceTypeDesc":83,"sizeBytes":84,"sourceHtmlUrl":85},"scripts\u002Fsearch_rag.py","SCRIPT","脚本",34595,"https:\u002F\u002Fgithub.com\u002FC-zj02\u002FCFD-claw\u002Fblob\u002Fmain\u002F.clawd\u002Fskills\u002Faircraft-design-rag\u002Fscripts\u002Fsearch_rag.py",[87,108,130,140,157,168],{"skillNo":88,"name":89,"nameZh":6,"description":90,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":91,"categories":92,"keywords":96,"publishedAt":49},"01M718YMY2C22JE2YCHG6GXDYE","flight-performance-analysis","面向飞行性能分析智能体的中文技能。用于用户提出飞行性能分析、气动\u002F动力特性数据管理、任务或飞行剖面选取与调整、重量状态管理、起飞着陆\u002F爬升\u002F巡航\u002F航程\u002F航时\u002F升限\u002F盘旋\u002F加速等性能计算、飞行剖面优化、飞行包线绘制、性能结果保存和图表可视化等任务时，指导智能体识别意图、编排流程、进行关键人机确认并格式化输出结果。","https:\u002F\u002Fgithub.com\u002FC-zj02\u002FCFD-claw\u002Fblob\u002Fmain\u002F.clawd\u002Fskills\u002Fflight-performance-analysis\u002FSKILL.md",[93],{"categoryNo":94,"categoryName":95,"taxonomyType":26,"taxonomyTypeDesc":27},"01JBSEEDCAT000000000000033","数据分析师",[97,98,99,100,101,102,103,104,105,106,107],"flight performance analysis","performance analysis","analysis","performance","图表","计算","中文","格式化","request","可视化","数据",{"skillNo":109,"name":110,"nameZh":6,"description":111,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":112,"categories":113,"keywords":117,"publishedAt":49},"01M718YKQSQWX0HGW98EBF4M6P","explain-code","Explains code with visual diagrams and analogies. Use when explaining how code works, teaching about a codebase, or when the user asks \"how does this work?\"","https:\u002F\u002Fgithub.com\u002FC-zj02\u002FCFD-claw\u002Fblob\u002Fmain\u002F.clawd\u002Fskills\u002Fexplain-code\u002FSKILL.md",[114],{"categoryNo":115,"categoryName":116,"taxonomyType":26,"taxonomyTypeDesc":27},"01JBSEEDCAT000000000000030","开发工程师",[118,119,120,121,122,123,124,42,33,125,126,127,128,129],"explain code","code","explain","about","how","work","codebase","teaching","visual","user","diagrams","with",{"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":136,"publishedAt":49},"01M718YJHG6953NCJZGVCFPYV0","echo-arg","Echo the passed arg for testing","https:\u002F\u002Fgithub.com\u002FC-zj02\u002FCFD-claw\u002Fblob\u002Fmain\u002F.clawd\u002Fskills\u002Fecho-arg\u002FSKILL.md",[],[137,138,34,139],"echo arg","Echo","testing",{"skillNo":141,"name":142,"nameZh":6,"description":143,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":144,"categories":145,"keywords":151,"publishedAt":49},"01M718YGPKBD515JSN6VYK6DN2","aircraft-design-skill","接入 BaiSongt\u002Faircraft-design-skill 的可交付固定翼总体设计工具包。用于 Class I\u002FII 重量、分段任务燃油、结构与几何闭合，有界自动修正与完整复验、阻断约束验收、气动\u002F推进\u002F操稳分析、外形参数化和设计报告生成。","https:\u002F\u002Fgithub.com\u002FC-zj02\u002FCFD-claw\u002Fblob\u002Fmain\u002F.clawd\u002Fskills\u002Faircraft-design-skill\u002FSKILL.md",[146,147,150],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":148,"categoryName":149,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发",{"categoryNo":24,"categoryName":25,"taxonomyType":26,"taxonomyTypeDesc":27},[152,31,153,154,155,45,156],"aircraft design skill","报告","生成","工具","read",{"skillNo":158,"name":159,"nameZh":6,"description":160,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":161,"categories":162,"keywords":165,"publishedAt":49},"01M718YBMDA527MJ4PM1NQ3VKZ","aircraft-conceptual-design","面向飞行器总体设计与概念方案设计的本地知识库增强技能。用于飞行器总体设计；飞机总体设计；任务剖面处理；翼载荷与推重比约束分析；方案界限线图绘制；起飞重量估算；燃油或能量估算；布局参数校核；历史型号检索；三视图参数输出；总体设计报告生成；以及显式工程推理记录。","https:\u002F\u002Fgithub.com\u002FC-zj02\u002FCFD-claw\u002Fblob\u002Fmain\u002F.clawd\u002Fskills\u002Faircraft-conceptual-design\u002FSKILL.md",[163,164],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":24,"categoryName":25,"taxonomyType":26,"taxonomyTypeDesc":27},[166,31,45,153,167,154,156],"aircraft conceptual design","brief",{"skillNo":169,"name":170,"nameZh":6,"description":171,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":172,"categories":173,"keywords":175,"publishedAt":49},"01M718YA8W77R4220S3A4GAQMP","aero-propulsion-analysis","用于气动\u002F推进特性分析智能体。处理气动力数据查询，升力线斜率，推阻特性，纵向安定性，横航向安定性，配平能力，进气道总压恢复系数，发动机推力与耗油率，喷管推力系数，安装推力运算，上传数据文件处理，气动\u002F推进方案设计参数推荐，人机确认和规范化数据输出。","https:\u002F\u002Fgithub.com\u002FC-zj02\u002FCFD-claw\u002Fblob\u002Fmain\u002F.clawd\u002Fskills\u002Faero-propulsion-analysis\u002FSKILL.md",[174],{"categoryNo":148,"categoryName":149,"taxonomyType":21,"taxonomyTypeDesc":22},[176,37,99,177,31,178,45,156,107,179],"aero propulsion analysis","grep","文件","write"]