[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6FJ2NWCD1D7M3FV8ZCZX3M1":3,"skill-same:01M6FJ2NWCD1D7M3FV8ZCZX3M1":89},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":15,"categories":16,"keywords":22,"publishedAt":35,"linkOnly":36,"markdownContent":37,"markdownBody":38,"frontMatter":39,"refName":40,"commitSha":41,"skillDirectory":42,"forksCount":43,"repositoryHtmlUrl":44,"repositoryHomepageUrl":6,"ownerHtmlUrl":45,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":46,"install":47,"resources":60},"01M6FJ2NWCD1D7M3FV8ZCZX3M1","ms-qwen-vl",null,"调用魔搭社区（ModelScope）Qwen3-VL 多模态 API 进行视觉解析。使用 OpenAI SDK 兼容方式调用，支持图片内容描述、OCR 文字提取、视觉问答、对象检测等功能。用户提到\"魔搭\"、\"ModelScope\"、\"Qwen-VL\"、\"多模态视觉\"、\"解析图片\"等关键词时应触发。","kbarbel640-del\u002Fskills","kbarbel640-del","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F255315490?v=4","01M6CJPPQGCCESXMG3K7BBGQ5J","01M6CJPPX2PB2BCZERFVM2C2B3",1,"MIT","https:\u002F\u002Fgithub.com\u002Fkbarbel640-del\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fcrocketc\u002Fms-qwen-vl\u002FSKILL.md",[17],{"categoryNo":18,"categoryName":19,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000016","图像与多媒体","SCENARIO","使用场景",[23,24,25,26,27,28,29,30,31,32,33,34],"Qwen","ms","ms qwen vl","image","sdk","openai","ocr","api","关键词","文字","qwen3","openai sdk","2026-11-10 10:12:30",false,"---\nname: ms-qwen-vl\ndescription: 调用魔搭社区（ModelScope）Qwen3-VL 多模态 API 进行视觉解析。使用 OpenAI SDK 兼容方式调用，支持图片内容描述、OCR 文字提取、视觉问答、对象检测等功能。用户提到\"魔搭\"、\"ModelScope\"、\"Qwen-VL\"、\"多模态视觉\"、\"解析图片\"等关键词时应触发。\n---\n\n# MS-Qwen-VL Skill\n\n基于 ModelScope Qwen3-VL 系列模型的多模态视觉识别技能，使用 OpenAI SDK 兼容方式调用。\n\n## 功能特点\n\n- **OpenAI SDK 兼容**：使用标准 OpenAI SDK 调用 API\n- **多种任务支持**：图像描述、OCR、视觉问答、目标检测、图表解析\n- **双模型模式**：默认快速模型（30B）+ 精细高精度模型（235B）\n- **灵活输入**：支持本地图片和 URL\n\n## 安装与配置\n\n```bash\n# 安装依赖\npip install -r requirements.txt\n\n# 配置 API Key\ncp .env.example .env\n```\n\n编辑 `.env` 文件，填入从 https:\u002F\u002Fmodelscope.cn\u002Fmy\u002Fmyaccesstoken 获取的 API Key：\n\n```\nMODELSCOPE_API_KEY=your_api_key_here\n```\n\n## Claude Code 使用方式\n\n### 重要：处理本地图片\n\n当用户提供本地图片路径时（如桌面截图），**必须使用 Python 脚本处理**：\n\n```bash\npython scripts\u002Fms_qwen_vl.py \"\u003C图片路径>\" --task \u003C任务类型>\n```\n\n脚本会自动将本地文件转换为 ModelScope API 需要的 base64 格式。\n\n### 处理 URL 图片\n\n当用户提供网络 URL 时，同样使用上述命令，脚本会自动识别：\n\n```bash\npython scripts\u002Fms_qwen_vl.py \"\u003CURL>\" --task \u003C任务类型>\n```\n\n### Claude Code 对话示例\n\n**场景 1：分析桌面截图**\n```\n用户: 请帮我描述这张图片 C:\\Users\\...\\Desktop\\screenshot.png\n助手: [执行] python scripts\u002Fms_qwen_vl.py \"C:\\Users\\...\\Desktop\\screenshot.png\"\n```\n\n**场景 2：OCR 识别本地图片**\n```\n用户: 识别这张图中的文字: D:\\Documents\\invoice.jpg\n助手: [执行] python scripts\u002Fms_qwen_vl.py \"D:\\Documents\\invoice.jpg\" --task ocr\n```\n\n**场景 3：分析网络图片**\n```\n用户: 分析这张图片 https:\u002F\u002Fexample.com\u002Fphoto.jpg\n助手: [执行] python scripts\u002Fms_qwen_vl.py \"https:\u002F\u002Fexample.com\u002Fphoto.jpg\" --task describe\n```\n\n**场景 4：视觉问答**\n```\n用户: 这张图里有几个人？C:\\Users\\...\\Desktop\\photo.png\n助手: [执行] python scripts\u002Fms_qwen_vl.py \"C:\\Users\\...\\Desktop\\photo.png\" --task ask --question \"图片里有几个人？\"\n```\n\n### 任务类型对照\n\n| 用户需求 | --task 参数 |\n|---------|-------------|\n| 描述图片内容 | describe |\n| 识别文字\u002FOCR | ocr |\n| 回答关于图片的问题 | ask（需要 --question） |\n| 检测物体 | detect |\n| 解析图表 | chart |\n\n## 快速使用\n\n```bash\n# 图像描述（默认）\npython scripts\u002Fms_qwen_vl.py image.jpg\n\n# OCR 文字识别\npython scripts\u002Fms_qwen_vl.py image.jpg --task ocr\n\n# 视觉问答\npython scripts\u002Fms_qwen_vl.py image.jpg --task ask --question \"图片里有什么？\"\n\n# 使用精细模式（235B 模型）\npython scripts\u002Fms_qwen_vl.py image.jpg --task describe --precise\n```\n\nPython 代码调用：\n\n```python\nfrom scripts.ms_qwen_vl import analyze_image\n\nresult = analyze_image(\"image.jpg\", task=\"ocr\")\nprint(result)\n```\n\n## 任务类型\n\n| 任务 | 参数 | 说明 |\n|------|------|------|\n| 图像描述 | `describe` | 详细描述图片内容（默认） |\n| OCR 识别 | `ocr` | 识别图片中的文字 |\n| 视觉问答 | `ask` | 回答关于图片的问题 |\n| 目标检测 | `detect` | 检测图片中的物体 |\n| 图表解析 | `chart` | 解析图表数据 |\n\n## 环境变量\n\n| 变量名 | 说明 |\n|--------|------|\n| `MODELSCOPE_API_KEY` | API 密钥（必需） |\n| `MODELSCOPE_MODEL` | 默认模型（可选） |\n| `MODELSCOPE_MODEL_PRECISE` | 精细模式模型（可选） |\n\n## Resources\n\n### scripts\u002F\n\n**ms_qwen_vl.py** - 核心解析脚本，提供 `analyze_image()` 统一接口\n\n### references\u002F\n\n**api-guide.md** - OpenAI SDK 兼容调用方式详细说明\n**models.md** - Qwen3-VL 系列模型及推荐使用场景\n","# MS-Qwen-VL Skill\n\n基于 ModelScope Qwen3-VL 系列模型的多模态视觉识别技能，使用 OpenAI SDK 兼容方式调用。\n\n## 功能特点\n\n- **OpenAI SDK 兼容**：使用标准 OpenAI SDK 调用 API\n- **多种任务支持**：图像描述、OCR、视觉问答、目标检测、图表解析\n- **双模型模式**：默认快速模型（30B）+ 精细高精度模型（235B）\n- **灵活输入**：支持本地图片和 URL\n\n## 安装与配置\n\n```bash\n# 安装依赖\npip install -r requirements.txt\n\n# 配置 API Key\ncp .env.example .env\n```\n\n编辑 `.env` 文件，填入从 https:\u002F\u002Fmodelscope.cn\u002Fmy\u002Fmyaccesstoken 获取的 API Key：\n\n```\nMODELSCOPE_API_KEY=your_api_key_here\n```\n\n## Claude Code 使用方式\n\n### 重要：处理本地图片\n\n当用户提供本地图片路径时（如桌面截图），**必须使用 Python 脚本处理**：\n\n```bash\npython scripts\u002Fms_qwen_vl.py \"\u003C图片路径>\" --task \u003C任务类型>\n```\n\n脚本会自动将本地文件转换为 ModelScope API 需要的 base64 格式。\n\n### 处理 URL 图片\n\n当用户提供网络 URL 时，同样使用上述命令，脚本会自动识别：\n\n```bash\npython scripts\u002Fms_qwen_vl.py \"\u003CURL>\" --task \u003C任务类型>\n```\n\n### Claude Code 对话示例\n\n**场景 1：分析桌面截图**\n```\n用户: 请帮我描述这张图片 C:\\Users\\...\\Desktop\\screenshot.png\n助手: [执行] python scripts\u002Fms_qwen_vl.py \"C:\\Users\\...\\Desktop\\screenshot.png\"\n```\n\n**场景 2：OCR 识别本地图片**\n```\n用户: 识别这张图中的文字: D:\\Documents\\invoice.jpg\n助手: [执行] python scripts\u002Fms_qwen_vl.py \"D:\\Documents\\invoice.jpg\" --task ocr\n```\n\n**场景 3：分析网络图片**\n```\n用户: 分析这张图片 https:\u002F\u002Fexample.com\u002Fphoto.jpg\n助手: [执行] python scripts\u002Fms_qwen_vl.py \"https:\u002F\u002Fexample.com\u002Fphoto.jpg\" --task describe\n```\n\n**场景 4：视觉问答**\n```\n用户: 这张图里有几个人？C:\\Users\\...\\Desktop\\photo.png\n助手: [执行] python scripts\u002Fms_qwen_vl.py \"C:\\Users\\...\\Desktop\\photo.png\" --task ask --question \"图片里有几个人？\"\n```\n\n### 任务类型对照\n\n| 用户需求 | --task 参数 |\n|---------|-------------|\n| 描述图片内容 | describe |\n| 识别文字\u002FOCR | ocr |\n| 回答关于图片的问题 | ask（需要 --question） |\n| 检测物体 | detect |\n| 解析图表 | chart |\n\n## 快速使用\n\n```bash\n# 图像描述（默认）\npython scripts\u002Fms_qwen_vl.py image.jpg\n\n# OCR 文字识别\npython scripts\u002Fms_qwen_vl.py image.jpg --task ocr\n\n# 视觉问答\npython scripts\u002Fms_qwen_vl.py image.jpg --task ask --question \"图片里有什么？\"\n\n# 使用精细模式（235B 模型）\npython scripts\u002Fms_qwen_vl.py image.jpg --task describe --precise\n```\n\nPython 代码调用：\n\n```python\nfrom scripts.ms_qwen_vl import analyze_image\n\nresult = analyze_image(\"image.jpg\", task=\"ocr\")\nprint(result)\n```\n\n## 任务类型\n\n| 任务 | 参数 | 说明 |\n|------|------|------|\n| 图像描述 | `describe` | 详细描述图片内容（默认） |\n| OCR 识别 | `ocr` | 识别图片中的文字 |\n| 视觉问答 | `ask` | 回答关于图片的问题 |\n| 目标检测 | `detect` | 检测图片中的物体 |\n| 图表解析 | `chart` | 解析图表数据 |\n\n## 环境变量\n\n| 变量名 | 说明 |\n|--------|------|\n| `MODELSCOPE_API_KEY` | API 密钥（必需） |\n| `MODELSCOPE_MODEL` | 默认模型（可选） |\n| `MODELSCOPE_MODEL_PRECISE` | 精细模式模型（可选） |\n\n## Resources\n\n### scripts\u002F\n\n**ms_qwen_vl.py** - 核心解析脚本，提供 `analyze_image()` 统一接口\n\n### references\u002F\n\n**api-guide.md** - OpenAI SDK 兼容调用方式详细说明\n**models.md** - Qwen3-VL 系列模型及推荐使用场景\n",{"name":5,"description":7},"main","e7e336ac628c3e3bd771aff1aaa469c93778f94a","skills\u002Fcrocketc\u002Fms-qwen-vl",0,"https:\u002F\u002Fgithub.com\u002Fkbarbel640-del\u002Fskills","https:\u002F\u002Fgithub.com\u002Fkbarbel640-del","2026-08-23 22:39:37",{"source":8,"skillName":5,"commands":48,"prompt":58,"zipAvailable":59},[49,52,55],{"tool":50,"command":51},"npx","npx skills add kbarbel640-del\u002Fskills --skill ms-qwen-vl",{"tool":53,"command":54},"bunx","bunx skills add kbarbel640-del\u002Fskills --skill ms-qwen-vl",{"tool":56,"command":57},"pnpm","pnpm dlx skills add kbarbel640-del\u002Fskills --skill ms-qwen-vl","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fkbarbel640-del\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fcrocketc\u002Fms-qwen-vl\u002FSKILL.md",true,[61,67,71,75,79,83],{"path":62,"resourceType":63,"resourceTypeDesc":64,"sizeBytes":65,"sourceHtmlUrl":66},"_meta.json","REFERENCE","参考文档",274,"https:\u002F\u002Fgithub.com\u002Fkbarbel640-del\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fcrocketc\u002Fms-qwen-vl\u002F_meta.json",{"path":68,"resourceType":63,"resourceTypeDesc":64,"sizeBytes":69,"sourceHtmlUrl":70},"README.md",3158,"https:\u002F\u002Fgithub.com\u002Fkbarbel640-del\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fcrocketc\u002Fms-qwen-vl\u002FREADME.md",{"path":72,"resourceType":63,"resourceTypeDesc":64,"sizeBytes":73,"sourceHtmlUrl":74},"references\u002Fapi-guide.md",3298,"https:\u002F\u002Fgithub.com\u002Fkbarbel640-del\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fcrocketc\u002Fms-qwen-vl\u002Freferences\u002Fapi-guide.md",{"path":76,"resourceType":63,"resourceTypeDesc":64,"sizeBytes":77,"sourceHtmlUrl":78},"references\u002Fmodels.md",1876,"https:\u002F\u002Fgithub.com\u002Fkbarbel640-del\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fcrocketc\u002Fms-qwen-vl\u002Freferences\u002Fmodels.md",{"path":80,"resourceType":63,"resourceTypeDesc":64,"sizeBytes":81,"sourceHtmlUrl":82},"requirements.txt",212,"https:\u002F\u002Fgithub.com\u002Fkbarbel640-del\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fcrocketc\u002Fms-qwen-vl\u002Frequirements.txt",{"path":84,"resourceType":85,"resourceTypeDesc":86,"sizeBytes":87,"sourceHtmlUrl":88},"scripts\u002Fms_qwen_vl.py","SCRIPT","脚本",7136,"https:\u002F\u002Fgithub.com\u002Fkbarbel640-del\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fcrocketc\u002Fms-qwen-vl\u002Fscripts\u002Fms_qwen_vl.py",[90,120,147,168,174,194],{"skillNo":91,"name":92,"nameZh":6,"description":93,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":94,"categories":95,"keywords":101,"publishedAt":35},"01M6G8J55967D6281ACMKAKTEQ","crowd-prompting","A marketplace where AI agents improve prompts, system instructions, tool descriptions, and other text-based content with domain expertise from real-world operations — and earn tokens for valuable contributions.","https:\u002F\u002Fgithub.com\u002Fkbarbel640-del\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fzzadrian\u002Fcrowd-prompting\u002FSKILL.md",[96],{"categoryNo":97,"categoryName":98,"taxonomyType":99,"taxonomyTypeDesc":100},"01JBSEEDCAT000000000000036","内容创作者","PROFESSION","适用职业",[102,103,30,104,105,106,107,108,109,110,111,112,113,114,115,116,117,118,119],"crowd prompting","prompting","with","tokens","domain","world","prompts","operations","instructions","text","tool","system","improve","productivity","marketplace","https","content","ai agents",{"skillNo":121,"name":122,"nameZh":6,"description":123,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":124,"categories":125,"keywords":129,"publishedAt":35},"01M6G8J0PKPAYVET6BWE8W4C26","dilemm-ai","Compete in DilemmAI, the prisoner's dilemma AI arena at dilemm.ai. Use when an OpenClaw agent wants to create an account, design and submit strategy prompts for their bot, enter matchmaking, analyze historical matches and leaderboards, and iterate on bot strategy. Requires headless browser automation (no API available yet).","https:\u002F\u002Fgithub.com\u002Fkbarbel640-del\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fzyori\u002Fdilemm-ai\u002FSKILL.md",[126],{"categoryNo":127,"categoryName":128,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000023","Skill与智能体开发",[130,30,131,132,133,134,135,136,137,138,139,140,141,142,143,144,145,108,146],"dilemm ai","arena","analyze","browser","openclaw agent","create","automation","browser automation","bot","openclaw","design","strategy","headless","compete","submit","matchmaking","use",{"skillNo":148,"name":149,"nameZh":6,"description":150,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":151,"categories":152,"keywords":156,"publishedAt":35},"01M6G8HWAF3K9SW7NP3Z83CPJ6","arxiv-paper-reviews","Interact with arXiv Crawler API to fetch papers, read reviews, and submit comments. Use when working with arXiv papers, fetching paper lists by date\u002Fcategory\u002Finterest, viewing paper details with comments, or submitting paper reviews via API at http:\u002F\u002F150.158.152.82:8000.","https:\u002F\u002Fgithub.com\u002Fkbarbel640-del\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fzxrys\u002Fweak-accept\u002FSKILL.md",[153],{"categoryNo":154,"categoryName":155,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000021","资料检索与研究",[157,158,159,160,161,162,163,104,164,144,146,165,30,166,167],"arxiv paper reviews","reviews","arxiv","paper","crawler","papers","comments","fetch","read","http","via",{"skillNo":169,"name":149,"nameZh":6,"description":150,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":170,"categories":171,"keywords":173,"publishedAt":35},"01M6G8HQJ7N7WMY6YV7D7SSJ16","https:\u002F\u002Fgithub.com\u002Fkbarbel640-del\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fzxrys\u002Farxiv-paper-reviews\u002FSKILL.md",[172],{"categoryNo":154,"categoryName":155,"taxonomyType":20,"taxonomyTypeDesc":21},[160,159,158,157,167,162,163,104,161,144,146,164,165,30,166],{"skillNo":175,"name":176,"nameZh":6,"description":177,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":178,"categories":179,"keywords":180,"publishedAt":35},"01M6G8HM95Y64JNVFC2HN4E2BG","git-summary","Get a quick summary of the current Git repository including status, recent commits, branches, and contributors.","https:\u002F\u002Fgithub.com\u002Fkbarbel640-del\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fzweack\u002Fgit-summary\u002FSKILL.md",[],[181,182,183,184,185,186,187,188,189,190,191,192,193],"git","summary","git summary","commits","repository","win32","status","linux","contributors","true","quick","get","branches",{"skillNo":195,"name":196,"nameZh":6,"description":197,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":198,"categories":199,"keywords":204,"publishedAt":35},"01M6G8HGEGF05CNEJCGVYFSC4R","agent-constitution","Interact with AgentConstitution governance contracts on Base Sepolia. Check compliance, read rules, log actions, query governance state.","https:\u002F\u002Fgithub.com\u002Fkbarbel640-del\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fztsalexey\u002Fagent-constitution\u002FSKILL.md",[200,201],{"categoryNo":127,"categoryName":128,"taxonomyType":20,"taxonomyTypeDesc":21},{"categoryNo":202,"categoryName":203,"taxonomyType":99,"taxonomyTypeDesc":100},"01JBSEEDCAT000000000000037","律师与法务",[205,206,207,208,104,209,210,40,211,165,212,213,214,215,216,117,217,218,219],"agent constitution","constitution","contracts","tree","query","base","log","check","Rules","projects","compliance","actions","state","governance","github"]