[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M73EWCDJVDW6XBKYV4N1NN0Z":3,"skill-same:01M73EWCDJVDW6XBKYV4N1NN0Z":50},{"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":18,"publishedAt":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":28,"commitSha":29,"skillDirectory":30,"forksCount":31,"repositoryHtmlUrl":32,"repositoryHomepageUrl":6,"ownerHtmlUrl":33,"ownerBlogUrl":34,"ownerDescription":6,"updatedAt":35,"install":36,"resources":49},"01M73EWCDJVDW6XBKYV4N1NN0Z","azure-ai-translation-ts",null,"Build translation applications using Azure Translation SDKs for JavaScript (@azure-rest\u002Fai-translation-text, @azure-rest\u002Fai-translation-document). Use when implementing text translation, transliteration, language detection, or batch document translation.","qhjqhj00\u002Fresearch-skills-pool","qhjqhj00","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F29684092?v=4","01M72AE0ZGXVM5C57N512DGQG8","Tommy Chien","01M72AE107ESJMHT7QC5SXX144",3,"MIT","https:\u002F\u002Fgithub.com\u002Fqhjqhj00\u002Fresearch-skills-pool\u002Fblob\u002Fmaster\u002Fskills_collected\u002Fmicrosoft--skills--.github__plugins__azure-sdk-typescript__skills__azure-ai-translation-ts\u002FSKILL.md",[],[],"2026-11-11 15:11:14",false,"---\nname: azure-ai-translation-ts\ndescription: Build translation applications using Azure Translation SDKs for JavaScript (@azure-rest\u002Fai-translation-text, @azure-rest\u002Fai-translation-document). Use when implementing text translation, transliteration, language detection, or batch document translation.\nlicense: MIT\nmetadata:\n  author: Microsoft\n  version: \"1.0.0\"\n  package: '@azure-rest\u002Fai-translation-text, @azure-rest\u002Fai-translation-document'\n---\n\n# Azure Translation SDKs for TypeScript\n\nText and document translation with REST-style clients.\n\n## Installation\n\n```bash\n# Text translation\nnpm install @azure-rest\u002Fai-translation-text @azure\u002Fidentity\n\n# Document translation\nnpm install @azure-rest\u002Fai-translation-document @azure\u002Fidentity\n```\n\n## Environment Variables\n\n```bash\nTRANSLATOR_ENDPOINT=https:\u002F\u002Fapi.cognitive.microsofttranslator.com\nTRANSLATOR_SUBSCRIPTION_KEY=\u003Cyour-api-key>\nTRANSLATOR_REGION=\u003Cyour-region>  # e.g., westus, eastus\nAZURE_TOKEN_CREDENTIALS=prod # Required only if DefaultAzureCredential is used in production\n```\n\n## Text Translation Client\n\n### Authentication\n\n```typescript\nimport TextTranslationClient, { TranslatorCredential } from \"@azure-rest\u002Fai-translation-text\";\n\n\u002F\u002F API Key + Region\nconst credential: TranslatorCredential = {\n  key: process.env.TRANSLATOR_SUBSCRIPTION_KEY!,\n  region: process.env.TRANSLATOR_REGION!,\n};\nconst client = TextTranslationClient(process.env.TRANSLATOR_ENDPOINT!, credential);\n\n\u002F\u002F Or just credential (uses global endpoint)\nconst client2 = TextTranslationClient(credential);\n```\n\n### Translate Text\n\n```typescript\nimport TextTranslationClient, { isUnexpected } from \"@azure-rest\u002Fai-translation-text\";\n\nconst response = await client.path(\"\u002Ftranslate\").post({\n  body: {\n    inputs: [\n      {\n        text: \"Hello, how are you?\",\n        language: \"en\",  \u002F\u002F source (optional, auto-detect)\n        targets: [\n          { language: \"es\" },\n          { language: \"fr\" },\n        ],\n      },\n    ],\n  },\n});\n\nif (isUnexpected(response)) {\n  throw response.body.error;\n}\n\nfor (const result of response.body.value) {\n  for (const translation of result.translations) {\n    console.log(`${translation.language}: ${translation.text}`);\n  }\n}\n```\n\n### Translate with Options\n\n```typescript\nconst response = await client.path(\"\u002Ftranslate\").post({\n  body: {\n    inputs: [\n      {\n        text: \"Hello world\",\n        language: \"en\",\n        textType: \"Plain\",  \u002F\u002F or \"Html\"\n        targets: [\n          {\n            language: \"de\",\n            profanityAction: \"NoAction\",  \u002F\u002F \"Marked\" | \"Deleted\"\n            tone: \"formal\",  \u002F\u002F LLM-specific\n          },\n        ],\n      },\n    ],\n  },\n});\n```\n\n### Get Supported Languages\n\n```typescript\nconst response = await client.path(\"\u002Flanguages\").get();\n\nif (isUnexpected(response)) {\n  throw response.body.error;\n}\n\n\u002F\u002F Translation languages\nfor (const [code, lang] of Object.entries(response.body.translation || {})) {\n  console.log(`${code}: ${lang.name} (${lang.nativeName})`);\n}\n```\n\n### Transliterate\n\n```typescript\nconst response = await client.path(\"\u002Ftransliterate\").post({\n  body: { inputs: [{ text: \"这是个测试\" }] },\n  queryParameters: {\n    language: \"zh-Hans\",\n    fromScript: \"Hans\",\n    toScript: \"Latn\",\n  },\n});\n\nif (!isUnexpected(response)) {\n  for (const t of response.body.value) {\n    console.log(`${t.script}: ${t.text}`);  \u002F\u002F Latn: zhè shì gè cè shì\n  }\n}\n```\n\n### Detect Language\n\n```typescript\nconst response = await client.path(\"\u002Fdetect\").post({\n  body: { inputs: [{ text: \"Bonjour le monde\" }] },\n});\n\nif (!isUnexpected(response)) {\n  for (const result of response.body.value) {\n    console.log(`Language: ${result.language}, Score: ${result.score}`);\n  }\n}\n```\n\n## Document Translation Client\n\n### Authentication\n\n```typescript\nimport DocumentTranslationClient from \"@azure-rest\u002Fai-translation-document\";\nimport { DefaultAzureCredential, ManagedIdentityCredential } from \"@azure\u002Fidentity\";\n\nconst endpoint = \"https:\u002F\u002F\u003Ctranslator>.cognitiveservices.azure.com\";\n\n\u002F\u002F Local dev: DefaultAzureCredential. Production: set AZURE_TOKEN_CREDENTIALS=prod or AZURE_TOKEN_CREDENTIALS=\u003Cspecific_credential>\nconst credential = new DefaultAzureCredential({requiredEnvVars: [\"AZURE_TOKEN_CREDENTIALS\"]});\n\u002F\u002F Or use a specific credential directly in production:\n\u002F\u002F See https:\u002F\u002Flearn.microsoft.com\u002Fjavascript\u002Fapi\u002Foverview\u002Fazure\u002Fidentity-readme?view=azure-node-latest#credential-classes\n\u002F\u002F const credential = new ManagedIdentityCredential();\n\n\u002F\u002F TokenCredential\nconst client = DocumentTranslationClient(endpoint, credential);\n\n\u002F\u002F API Key\nconst client2 = DocumentTranslationClient(endpoint, { key: \"\u003Capi-key>\" });\n```\n\n### Single Document Translation\n\n```typescript\nimport DocumentTranslationClient from \"@azure-rest\u002Fai-translation-document\";\nimport { writeFile } from \"node:fs\u002Fpromises\";\n\nconst response = await client.path(\"\u002Fdocument:translate\").post({\n  queryParameters: {\n    targetLanguage: \"es\",\n    sourceLanguage: \"en\",  \u002F\u002F optional\n  },\n  contentType: \"multipart\u002Fform-data\",\n  body: [\n    {\n      name: \"document\",\n      body: \"Hello, this is a test document.\",\n      filename: \"test.txt\",\n      contentType: \"text\u002Fplain\",\n    },\n  ],\n}).asNodeStream();\n\nif (response.status === \"200\") {\n  await writeFile(\"translated.txt\", response.body);\n}\n```\n\n### Batch Document Translation\n\n```typescript\nimport { ContainerSASPermissions, BlobServiceClient } from \"@azure\u002Fstorage-blob\";\n\n\u002F\u002F Generate SAS URLs for source and target containers\nconst sourceSas = await sourceContainer.generateSasUrl({\n  permissions: ContainerSASPermissions.parse(\"rl\"),\n  expiresOn: new Date(Date.now() + 24 * 60 * 60 * 1000),\n});\n\nconst targetSas = await targetContainer.generateSasUrl({\n  permissions: ContainerSASPermissions.parse(\"rwl\"),\n  expiresOn: new Date(Date.now() + 24 * 60 * 60 * 1000),\n});\n\n\u002F\u002F Start batch translation\nconst response = await client.path(\"\u002Fdocument\u002Fbatches\").post({\n  body: {\n    inputs: [\n      {\n        source: { sourceUrl: sourceSas },\n        targets: [\n          { targetUrl: targetSas, language: \"fr\" },\n        ],\n      },\n    ],\n  },\n});\n\n\u002F\u002F Get operation ID from header\nconst operationId = new URL(response.headers[\"operation-location\"])\n  .pathname.split(\"\u002F\").pop();\n```\n\n### Get Translation Status\n\n```typescript\nimport { isUnexpected, paginate } from \"@azure-rest\u002Fai-translation-document\";\n\nconst statusResponse = await client.path(\"\u002Fdocument\u002Fbatches\u002F{id}\", operationId).get();\n\nif (!isUnexpected(statusResponse)) {\n  const status = statusResponse.body;\n  console.log(`Status: ${status.status}`);\n  console.log(`Total: ${status.summary.total}`);\n  console.log(`Success: ${status.summary.success}`);\n}\n\n\u002F\u002F List documents with pagination\nconst docsResponse = await client.path(\"\u002Fdocument\u002Fbatches\u002F{id}\u002Fdocuments\", operationId).get();\nconst documents = paginate(client, docsResponse);\n\nfor await (const doc of documents) {\n  console.log(`${doc.id}: ${doc.status}`);\n}\n```\n\n### Get Supported Formats\n\n```typescript\nconst response = await client.path(\"\u002Fdocument\u002Fformats\").get();\n\nif (!isUnexpected(response)) {\n  for (const format of response.body.value) {\n    console.log(`${format.format}: ${format.fileExtensions.join(\", \")}`);\n  }\n}\n```\n\n## Key Types\n\n```typescript\n\u002F\u002F Text Translation\nimport type {\n  TranslatorCredential,\n  TranslatorTokenCredential,\n} from \"@azure-rest\u002Fai-translation-text\";\n\n\u002F\u002F Document Translation\nimport type {\n  DocumentTranslateParameters,\n  StartTranslationDetails,\n  TranslationStatus,\n} from \"@azure-rest\u002Fai-translation-document\";\n```\n\n## Best Practices\n\n1. **Auto-detect source** - Omit `language` parameter to auto-detect\n2. **Batch requests** - Translate multiple texts in one call for efficiency\n3. **Use SAS tokens** - For document translation, use time-limited SAS URLs\n4. **Handle errors** - Always check `isUnexpected(response)` before accessing body\n5. **Regional endpoints** - Use regional endpoints for lower latency\n","# Azure Translation SDKs for TypeScript\n\nText and document translation with REST-style clients.\n\n## Installation\n\n```bash\n# Text translation\nnpm install @azure-rest\u002Fai-translation-text @azure\u002Fidentity\n\n# Document translation\nnpm install @azure-rest\u002Fai-translation-document @azure\u002Fidentity\n```\n\n## Environment Variables\n\n```bash\nTRANSLATOR_ENDPOINT=https:\u002F\u002Fapi.cognitive.microsofttranslator.com\nTRANSLATOR_SUBSCRIPTION_KEY=\u003Cyour-api-key>\nTRANSLATOR_REGION=\u003Cyour-region>  # e.g., westus, eastus\nAZURE_TOKEN_CREDENTIALS=prod # Required only if DefaultAzureCredential is used in production\n```\n\n## Text Translation Client\n\n### Authentication\n\n```typescript\nimport TextTranslationClient, { TranslatorCredential } from \"@azure-rest\u002Fai-translation-text\";\n\n\u002F\u002F API Key + Region\nconst credential: TranslatorCredential = {\n  key: process.env.TRANSLATOR_SUBSCRIPTION_KEY!,\n  region: process.env.TRANSLATOR_REGION!,\n};\nconst client = TextTranslationClient(process.env.TRANSLATOR_ENDPOINT!, credential);\n\n\u002F\u002F Or just credential (uses global endpoint)\nconst client2 = TextTranslationClient(credential);\n```\n\n### Translate Text\n\n```typescript\nimport TextTranslationClient, { isUnexpected } from \"@azure-rest\u002Fai-translation-text\";\n\nconst response = await client.path(\"\u002Ftranslate\").post({\n  body: {\n    inputs: [\n      {\n        text: \"Hello, how are you?\",\n        language: \"en\",  \u002F\u002F source (optional, auto-detect)\n        targets: [\n          { language: \"es\" },\n          { language: \"fr\" },\n        ],\n      },\n    ],\n  },\n});\n\nif (isUnexpected(response)) {\n  throw response.body.error;\n}\n\nfor (const result of response.body.value) {\n  for (const translation of result.translations) {\n    console.log(`${translation.language}: ${translation.text}`);\n  }\n}\n```\n\n### Translate with Options\n\n```typescript\nconst response = await client.path(\"\u002Ftranslate\").post({\n  body: {\n    inputs: [\n      {\n        text: \"Hello world\",\n        language: \"en\",\n        textType: \"Plain\",  \u002F\u002F or \"Html\"\n        targets: [\n          {\n            language: \"de\",\n            profanityAction: \"NoAction\",  \u002F\u002F \"Marked\" | \"Deleted\"\n            tone: \"formal\",  \u002F\u002F LLM-specific\n          },\n        ],\n      },\n    ],\n  },\n});\n```\n\n### Get Supported Languages\n\n```typescript\nconst response = await client.path(\"\u002Flanguages\").get();\n\nif (isUnexpected(response)) {\n  throw response.body.error;\n}\n\n\u002F\u002F Translation languages\nfor (const [code, lang] of Object.entries(response.body.translation || {})) {\n  console.log(`${code}: ${lang.name} (${lang.nativeName})`);\n}\n```\n\n### Transliterate\n\n```typescript\nconst response = await client.path(\"\u002Ftransliterate\").post({\n  body: { inputs: [{ text: \"这是个测试\" }] },\n  queryParameters: {\n    language: \"zh-Hans\",\n    fromScript: \"Hans\",\n    toScript: \"Latn\",\n  },\n});\n\nif (!isUnexpected(response)) {\n  for (const t of response.body.value) {\n    console.log(`${t.script}: ${t.text}`);  \u002F\u002F Latn: zhè shì gè cè shì\n  }\n}\n```\n\n### Detect Language\n\n```typescript\nconst response = await client.path(\"\u002Fdetect\").post({\n  body: { inputs: [{ text: \"Bonjour le monde\" }] },\n});\n\nif (!isUnexpected(response)) {\n  for (const result of response.body.value) {\n    console.log(`Language: ${result.language}, Score: ${result.score}`);\n  }\n}\n```\n\n## Document Translation Client\n\n### Authentication\n\n```typescript\nimport DocumentTranslationClient from \"@azure-rest\u002Fai-translation-document\";\nimport { DefaultAzureCredential, ManagedIdentityCredential } from \"@azure\u002Fidentity\";\n\nconst endpoint = \"https:\u002F\u002F\u003Ctranslator>.cognitiveservices.azure.com\";\n\n\u002F\u002F Local dev: DefaultAzureCredential. Production: set AZURE_TOKEN_CREDENTIALS=prod or AZURE_TOKEN_CREDENTIALS=\u003Cspecific_credential>\nconst credential = new DefaultAzureCredential({requiredEnvVars: [\"AZURE_TOKEN_CREDENTIALS\"]});\n\u002F\u002F Or use a specific credential directly in production:\n\u002F\u002F See https:\u002F\u002Flearn.microsoft.com\u002Fjavascript\u002Fapi\u002Foverview\u002Fazure\u002Fidentity-readme?view=azure-node-latest#credential-classes\n\u002F\u002F const credential = new ManagedIdentityCredential();\n\n\u002F\u002F TokenCredential\nconst client = DocumentTranslationClient(endpoint, credential);\n\n\u002F\u002F API Key\nconst client2 = DocumentTranslationClient(endpoint, { key: \"\u003Capi-key>\" });\n```\n\n### Single Document Translation\n\n```typescript\nimport DocumentTranslationClient from \"@azure-rest\u002Fai-translation-document\";\nimport { writeFile } from \"node:fs\u002Fpromises\";\n\nconst response = await client.path(\"\u002Fdocument:translate\").post({\n  queryParameters: {\n    targetLanguage: \"es\",\n    sourceLanguage: \"en\",  \u002F\u002F optional\n  },\n  contentType: \"multipart\u002Fform-data\",\n  body: [\n    {\n      name: \"document\",\n      body: \"Hello, this is a test document.\",\n      filename: \"test.txt\",\n      contentType: \"text\u002Fplain\",\n    },\n  ],\n}).asNodeStream();\n\nif (response.status === \"200\") {\n  await writeFile(\"translated.txt\", response.body);\n}\n```\n\n### Batch Document Translation\n\n```typescript\nimport { ContainerSASPermissions, BlobServiceClient } from \"@azure\u002Fstorage-blob\";\n\n\u002F\u002F Generate SAS URLs for source and target containers\nconst sourceSas = await sourceContainer.generateSasUrl({\n  permissions: ContainerSASPermissions.parse(\"rl\"),\n  expiresOn: new Date(Date.now() + 24 * 60 * 60 * 1000),\n});\n\nconst targetSas = await targetContainer.generateSasUrl({\n  permissions: ContainerSASPermissions.parse(\"rwl\"),\n  expiresOn: new Date(Date.now() + 24 * 60 * 60 * 1000),\n});\n\n\u002F\u002F Start batch translation\nconst response = await client.path(\"\u002Fdocument\u002Fbatches\").post({\n  body: {\n    inputs: [\n      {\n        source: { sourceUrl: sourceSas },\n        targets: [\n          { targetUrl: targetSas, language: \"fr\" },\n        ],\n      },\n    ],\n  },\n});\n\n\u002F\u002F Get operation ID from header\nconst operationId = new URL(response.headers[\"operation-location\"])\n  .pathname.split(\"\u002F\").pop();\n```\n\n### Get Translation Status\n\n```typescript\nimport { isUnexpected, paginate } from \"@azure-rest\u002Fai-translation-document\";\n\nconst statusResponse = await client.path(\"\u002Fdocument\u002Fbatches\u002F{id}\", operationId).get();\n\nif (!isUnexpected(statusResponse)) {\n  const status = statusResponse.body;\n  console.log(`Status: ${status.status}`);\n  console.log(`Total: ${status.summary.total}`);\n  console.log(`Success: ${status.summary.success}`);\n}\n\n\u002F\u002F List documents with pagination\nconst docsResponse = await client.path(\"\u002Fdocument\u002Fbatches\u002F{id}\u002Fdocuments\", operationId).get();\nconst documents = paginate(client, docsResponse);\n\nfor await (const doc of documents) {\n  console.log(`${doc.id}: ${doc.status}`);\n}\n```\n\n### Get Supported Formats\n\n```typescript\nconst response = await client.path(\"\u002Fdocument\u002Fformats\").get();\n\nif (!isUnexpected(response)) {\n  for (const format of response.body.value) {\n    console.log(`${format.format}: ${format.fileExtensions.join(\", \")}`);\n  }\n}\n```\n\n## Key Types\n\n```typescript\n\u002F\u002F Text Translation\nimport type {\n  TranslatorCredential,\n  TranslatorTokenCredential,\n} from \"@azure-rest\u002Fai-translation-text\";\n\n\u002F\u002F Document Translation\nimport type {\n  DocumentTranslateParameters,\n  StartTranslationDetails,\n  TranslationStatus,\n} from \"@azure-rest\u002Fai-translation-document\";\n```\n\n## Best Practices\n\n1. **Auto-detect source** - Omit `language` parameter to auto-detect\n2. **Batch requests** - Translate multiple texts in one call for efficiency\n3. **Use SAS tokens** - For document translation, use time-limited SAS URLs\n4. **Handle errors** - Always check `isUnexpected(response)` before accessing body\n5. **Regional endpoints** - Use regional endpoints for lower latency\n",{"name":5,"license":15,"metadata":24,"description":7},{"author":25,"package":26,"version":27},"Microsoft","@azure-rest\u002Fai-translation-text, @azure-rest\u002Fai-translation-document","1.0.0","master","c247302c836de6438d746b45670990eb71691166","skills_collected\u002Fmicrosoft--skills--.github__plugins__azure-sdk-typescript__skills__azure-ai-translation-ts",1,"https:\u002F\u002Fgithub.com\u002Fqhjqhj00\u002Fresearch-skills-pool","https:\u002F\u002Fgithub.com\u002Fqhjqhj00","chien.io","2026-05-11 15:07:59",{"source":8,"skillName":5,"commands":37,"prompt":47,"zipAvailable":48},[38,41,44],{"tool":39,"command":40},"npx","npx skills add qhjqhj00\u002Fresearch-skills-pool --skill azure-ai-translation-ts",{"tool":42,"command":43},"bunx","bunx skills add qhjqhj00\u002Fresearch-skills-pool --skill azure-ai-translation-ts",{"tool":45,"command":46},"pnpm","pnpm dlx skills add qhjqhj00\u002Fresearch-skills-pool --skill azure-ai-translation-ts","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fqhjqhj00\u002Fresearch-skills-pool\u002Fblob\u002Fmaster\u002Fskills_collected\u002Fmicrosoft--skills--.github__plugins__azure-sdk-typescript__skills__azure-ai-translation-ts\u002FSKILL.md",true,[],[51,58,65,72,79,86],{"skillNo":52,"name":53,"nameZh":6,"description":54,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":55,"categories":56,"keywords":57,"publishedAt":19},"01M73JJB6EQPFPPVQK2Y9N67Q0","transformer-lens-interpretability","Provides guidance for mechanistic interpretability research using TransformerLens to inspect and manipulate transformer internals via HookPoints and activation caching. Use when reverse-engineering model algorithms, studying attention patterns, or performing activation patching experiments.","https:\u002F\u002Fgithub.com\u002Fqhjqhj00\u002Fresearch-skills-pool\u002Fblob\u002Fmaster\u002Ftop100-runs\u002F130-transformer-lens\u002FSKILL.md",[],[],{"skillNo":59,"name":60,"nameZh":6,"description":61,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":62,"categories":63,"keywords":64,"publishedAt":19},"01M73JHTANRRWEE9HP98TPEHAY","wiki-vitepress","Packages generated wiki Markdown into a VitePress static site with dark theme, dark-mode Mermaid diagrams with click-to-zoom, and production build output. Use when the user wants to create a browsable website from generated wiki pages.","https:\u002F\u002Fgithub.com\u002Fqhjqhj00\u002Fresearch-skills-pool\u002Fblob\u002Fmaster\u002Ftop100-runs\u002F126-wiki-vitepress\u002FSKILL.md",[],[],{"skillNo":66,"name":67,"nameZh":6,"description":68,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":69,"categories":70,"keywords":71,"publishedAt":19},"01M73JHJBMVFW46F1Y8K3SBF43","phoenix-observability","Open-source AI observability platform for LLM tracing, evaluation, and monitoring. Use when debugging LLM applications with detailed traces, running evaluations on datasets, or monitoring production AI systems with real-time insights.","https:\u002F\u002Fgithub.com\u002Fqhjqhj00\u002Fresearch-skills-pool\u002Fblob\u002Fmaster\u002Ftop100-runs\u002F124-phoenix\u002FSKILL.md",[],[],{"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":78,"publishedAt":19},"01M73JHFPA3A2806PMP42ZN86Q","frontend-ui-dark-ts","Build dark-themed React applications using Tailwind CSS with custom theming, glassmorphism effects, and Framer Motion animations. Use when creating dashboards, admin panels, or data-rich interfaces with a refined dark aesthetic.","https:\u002F\u002Fgithub.com\u002Fqhjqhj00\u002Fresearch-skills-pool\u002Fblob\u002Fmaster\u002Ftop100-runs\u002F123-frontend-ui-dark-ts\u002FSKILL.md",[],[],{"skillNo":80,"name":81,"nameZh":6,"description":82,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":83,"categories":84,"keywords":85,"publishedAt":19},"01M73JFVBVK57NRJS49TT2VDCT","tensorboard","Visualize training metrics, debug models with histograms, compare experiments, visualize model graphs, and profile performance with TensorBoard - Google's ML visualization toolkit","https:\u002F\u002Fgithub.com\u002Fqhjqhj00\u002Fresearch-skills-pool\u002Fblob\u002Fmaster\u002Ftop100-runs\u002F113-tensorboard\u002FSKILL.md",[],[],{"skillNo":87,"name":88,"nameZh":6,"description":89,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":90,"licenseFileUrl":6,"sourceHtmlUrl":91,"categories":92,"keywords":93,"publishedAt":19},"01M73JFF6PK6ZCN41C89J7HS2B","markdown-mermaid-writing","Comprehensive markdown and Mermaid diagram writing skill. Use when creating any scientific document, report, analysis, or visualization. Establishes text-based diagrams as the default documentation standard with full style guides (markdown + mermaid), 24 diagram type references, and 9 document templates.","Apache-2.0","https:\u002F\u002Fgithub.com\u002Fqhjqhj00\u002Fresearch-skills-pool\u002Fblob\u002Fmaster\u002Ftop100-runs\u002F110-markdown-mermaid-writing\u002FSKILL.md",[],[]]