[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M73EP1N47QXSTQZDF4YKHFBV":3,"skill-same:01M73EP1N47QXSTQZDF4YKHFBV":56},{"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},"01M73EP1N47QXSTQZDF4YKHFBV","azure-ai-contentsafety-java",null,"Build content moderation applications with Azure AI Content Safety SDK for Java. Use when implementing text\u002Fimage analysis, blocklist management, or harm detection for hate, violence, sexual content, and self-harm.","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-java__skills__azure-ai-contentsafety-java\u002FSKILL.md",[],[],"2026-11-11 15:11:14",false,"---\nname: azure-ai-contentsafety-java\ndescription: Build content moderation applications with Azure AI Content Safety SDK for Java. Use when implementing text\u002Fimage analysis, blocklist management, or harm detection for hate, violence, sexual content, and self-harm.\nlicense: MIT\nmetadata:\n  author: Microsoft\n  version: \"1.0.0\"\n  package: com.azure:azure-ai-contentsafety\n---\n\n# Azure AI Content Safety SDK for Java\n\nBuild content moderation applications using the Azure AI Content Safety SDK for Java.\n\n## Installation\n\n```xml\n\u003Cdependency>\n    \u003CgroupId>com.azure\u003C\u002FgroupId>\n    \u003CartifactId>azure-ai-contentsafety\u003C\u002FartifactId>\n    \u003Cversion>1.1.0-beta.1\u003C\u002Fversion>\n\u003C\u002Fdependency>\n```\n\n## Client Creation\n\n### With API Key\n\n```java\nimport com.azure.ai.contentsafety.ContentSafetyClient;\nimport com.azure.ai.contentsafety.ContentSafetyClientBuilder;\nimport com.azure.ai.contentsafety.BlocklistClient;\nimport com.azure.ai.contentsafety.BlocklistClientBuilder;\nimport com.azure.core.credential.KeyCredential;\n\nString endpoint = System.getenv(\"CONTENT_SAFETY_ENDPOINT\");\nString key = System.getenv(\"CONTENT_SAFETY_KEY\");\n\nContentSafetyClient contentSafetyClient = new ContentSafetyClientBuilder()\n    .credential(new KeyCredential(key))\n    .endpoint(endpoint)\n    .buildClient();\n\nBlocklistClient blocklistClient = new BlocklistClientBuilder()\n    .credential(new KeyCredential(key))\n    .endpoint(endpoint)\n    .buildClient();\n```\n\n### With DefaultAzureCredential\n\n```java\nimport com.azure.core.credential.TokenCredential;\nimport com.azure.identity.AzureIdentityEnvVars;\nimport com.azure.identity.DefaultAzureCredentialBuilder;\nimport com.azure.identity.ManagedIdentityCredentialBuilder;\n\nTokenCredential credential = new DefaultAzureCredentialBuilder()\n    .requireEnvVars(AzureIdentityEnvVars.AZURE_TOKEN_CREDENTIALS)\n    .build();\n\u002F\u002F Or use a specific credential directly in production:\n\u002F\u002F See https:\u002F\u002Flearn.microsoft.com\u002Fjava\u002Fapi\u002Foverview\u002Fazure\u002Fidentity-readme?view=azure-java-stable#credential-classes\n\u002F\u002F TokenCredential credential = new ManagedIdentityCredentialBuilder().build();\n\nContentSafetyClient client = new ContentSafetyClientBuilder()\n    .credential(credential)\n    .endpoint(endpoint)\n    .buildClient();\n```\n\n## Key Concepts\n\n### Harm Categories\n| Category | Description |\n|----------|-------------|\n| Hate | Discriminatory language based on identity groups |\n| Sexual | Sexual content, relationships, acts |\n| Violence | Physical harm, weapons, injury |\n| Self-harm | Self-injury, suicide-related content |\n\n### Severity Levels\n- Text: 0-7 scale (default outputs 0, 2, 4, 6)\n- Image: 0, 2, 4, 6 (trimmed scale)\n\n## Core Patterns\n\n### Analyze Text\n\n```java\nimport com.azure.ai.contentsafety.models.*;\n\nAnalyzeTextResult result = contentSafetyClient.analyzeText(\n    new AnalyzeTextOptions(\"This is text to analyze\"));\n\nfor (TextCategoriesAnalysis category : result.getCategoriesAnalysis()) {\n    System.out.printf(\"Category: %s, Severity: %d%n\",\n        category.getCategory(),\n        category.getSeverity());\n}\n```\n\n### Analyze Text with Options\n\n```java\nAnalyzeTextOptions options = new AnalyzeTextOptions(\"Text to analyze\")\n    .setCategories(Arrays.asList(\n        TextCategory.HATE,\n        TextCategory.VIOLENCE))\n    .setOutputType(AnalyzeTextOutputType.EIGHT_SEVERITY_LEVELS);\n\nAnalyzeTextResult result = contentSafetyClient.analyzeText(options);\n```\n\n### Analyze Text with Blocklist\n\n```java\nAnalyzeTextOptions options = new AnalyzeTextOptions(\"I h*te you and want to k*ll you\")\n    .setBlocklistNames(Arrays.asList(\"my-blocklist\"))\n    .setHaltOnBlocklistHit(true);\n\nAnalyzeTextResult result = contentSafetyClient.analyzeText(options);\n\nif (result.getBlocklistsMatch() != null) {\n    for (TextBlocklistMatch match : result.getBlocklistsMatch()) {\n        System.out.printf(\"Blocklist: %s, Item: %s, Text: %s%n\",\n            match.getBlocklistName(),\n            match.getBlocklistItemId(),\n            match.getBlocklistItemText());\n    }\n}\n```\n\n### Analyze Image\n\n```java\nimport com.azure.ai.contentsafety.models.*;\nimport com.azure.core.util.BinaryData;\nimport java.nio.file.Files;\nimport java.nio.file.Paths;\n\n\u002F\u002F From file\nbyte[] imageBytes = Files.readAllBytes(Paths.get(\"image.png\"));\nContentSafetyImageData imageData = new ContentSafetyImageData()\n    .setContent(BinaryData.fromBytes(imageBytes));\n\nAnalyzeImageResult result = contentSafetyClient.analyzeImage(\n    new AnalyzeImageOptions(imageData));\n\nfor (ImageCategoriesAnalysis category : result.getCategoriesAnalysis()) {\n    System.out.printf(\"Category: %s, Severity: %d%n\",\n        category.getCategory(),\n        category.getSeverity());\n}\n```\n\n### Analyze Image from URL\n\n```java\nContentSafetyImageData imageData = new ContentSafetyImageData()\n    .setBlobUrl(\"https:\u002F\u002Fexample.com\u002Fimage.jpg\");\n\nAnalyzeImageResult result = contentSafetyClient.analyzeImage(\n    new AnalyzeImageOptions(imageData));\n```\n\n## Blocklist Management\n\n### Create or Update Blocklist\n\n```java\nimport com.azure.core.http.rest.RequestOptions;\nimport com.azure.core.http.rest.Response;\nimport com.azure.core.util.BinaryData;\nimport java.util.Map;\n\nMap\u003CString, String> description = Map.of(\"description\", \"Custom blocklist\");\nBinaryData resource = BinaryData.fromObject(description);\n\nResponse\u003CBinaryData> response = blocklistClient.createOrUpdateTextBlocklistWithResponse(\n    \"my-blocklist\", resource, new RequestOptions());\n\nif (response.getStatusCode() == 201) {\n    System.out.println(\"Blocklist created\");\n} else if (response.getStatusCode() == 200) {\n    System.out.println(\"Blocklist updated\");\n}\n```\n\n### Add Block Items\n\n```java\nimport com.azure.ai.contentsafety.models.*;\nimport java.util.Arrays;\n\nList\u003CTextBlocklistItem> items = Arrays.asList(\n    new TextBlocklistItem(\"badword1\").setDescription(\"Offensive term\"),\n    new TextBlocklistItem(\"badword2\").setDescription(\"Another term\")\n);\n\nAddOrUpdateTextBlocklistItemsResult result = blocklistClient.addOrUpdateBlocklistItems(\n    \"my-blocklist\",\n    new AddOrUpdateTextBlocklistItemsOptions(items));\n\nfor (TextBlocklistItem item : result.getBlocklistItems()) {\n    System.out.printf(\"Added: %s (ID: %s)%n\",\n        item.getText(),\n        item.getBlocklistItemId());\n}\n```\n\n### List Blocklists\n\n```java\nPagedIterable\u003CTextBlocklist> blocklists = blocklistClient.listTextBlocklists();\n\nfor (TextBlocklist blocklist : blocklists) {\n    System.out.printf(\"Blocklist: %s, Description: %s%n\",\n        blocklist.getName(),\n        blocklist.getDescription());\n}\n```\n\n### Get Blocklist\n\n```java\nTextBlocklist blocklist = blocklistClient.getTextBlocklist(\"my-blocklist\");\nSystem.out.println(\"Name: \" + blocklist.getName());\n```\n\n### List Block Items\n\n```java\nPagedIterable\u003CTextBlocklistItem> items = \n    blocklistClient.listTextBlocklistItems(\"my-blocklist\");\n\nfor (TextBlocklistItem item : items) {\n    System.out.printf(\"ID: %s, Text: %s%n\",\n        item.getBlocklistItemId(),\n        item.getText());\n}\n```\n\n### Remove Block Items\n\n```java\nList\u003CString> itemIds = Arrays.asList(\"item-id-1\", \"item-id-2\");\n\nblocklistClient.removeBlocklistItems(\n    \"my-blocklist\",\n    new RemoveTextBlocklistItemsOptions(itemIds));\n```\n\n### Delete Blocklist\n\n```java\nblocklistClient.deleteTextBlocklist(\"my-blocklist\");\n```\n\n## Error Handling\n\n```java\nimport com.azure.core.exception.HttpResponseException;\n\ntry {\n    contentSafetyClient.analyzeText(new AnalyzeTextOptions(\"test\"));\n} catch (HttpResponseException e) {\n    System.out.println(\"Status: \" + e.getResponse().getStatusCode());\n    System.out.println(\"Error: \" + e.getMessage());\n    \u002F\u002F Common codes: InvalidRequestBody, ResourceNotFound, TooManyRequests\n}\n```\n\n## Environment Variables\n\n```bash\nCONTENT_SAFETY_ENDPOINT=https:\u002F\u002F\u003Cresource>.cognitiveservices.azure.com\u002F # Required for all auth methods\nCONTENT_SAFETY_KEY=\u003Cyour-api-key> # Only required for AzureKeyCredential auth\nAZURE_TOKEN_CREDENTIALS=prod  # Required only if DefaultAzureCredential is used in production\n```\n\n## Best Practices\n\n1. **Blocklist Delay**: Changes take ~5 minutes to take effect\n2. **Category Selection**: Only request needed categories to reduce latency\n3. **Severity Thresholds**: Typically block severity >= 4 for strict moderation\n4. **Batch Processing**: Process multiple items in parallel for throughput\n5. **Caching**: Cache blocklist results where appropriate\n\n## Trigger Phrases\n\n- \"content safety Java\"\n- \"content moderation Azure\"\n- \"analyze text safety\"\n- \"image moderation Java\"\n- \"blocklist management\"\n- \"hate speech detection\"\n- \"harmful content filter\"\n","# Azure AI Content Safety SDK for Java\n\nBuild content moderation applications using the Azure AI Content Safety SDK for Java.\n\n## Installation\n\n```xml\n\u003Cdependency>\n    \u003CgroupId>com.azure\u003C\u002FgroupId>\n    \u003CartifactId>azure-ai-contentsafety\u003C\u002FartifactId>\n    \u003Cversion>1.1.0-beta.1\u003C\u002Fversion>\n\u003C\u002Fdependency>\n```\n\n## Client Creation\n\n### With API Key\n\n```java\nimport com.azure.ai.contentsafety.ContentSafetyClient;\nimport com.azure.ai.contentsafety.ContentSafetyClientBuilder;\nimport com.azure.ai.contentsafety.BlocklistClient;\nimport com.azure.ai.contentsafety.BlocklistClientBuilder;\nimport com.azure.core.credential.KeyCredential;\n\nString endpoint = System.getenv(\"CONTENT_SAFETY_ENDPOINT\");\nString key = System.getenv(\"CONTENT_SAFETY_KEY\");\n\nContentSafetyClient contentSafetyClient = new ContentSafetyClientBuilder()\n    .credential(new KeyCredential(key))\n    .endpoint(endpoint)\n    .buildClient();\n\nBlocklistClient blocklistClient = new BlocklistClientBuilder()\n    .credential(new KeyCredential(key))\n    .endpoint(endpoint)\n    .buildClient();\n```\n\n### With DefaultAzureCredential\n\n```java\nimport com.azure.core.credential.TokenCredential;\nimport com.azure.identity.AzureIdentityEnvVars;\nimport com.azure.identity.DefaultAzureCredentialBuilder;\nimport com.azure.identity.ManagedIdentityCredentialBuilder;\n\nTokenCredential credential = new DefaultAzureCredentialBuilder()\n    .requireEnvVars(AzureIdentityEnvVars.AZURE_TOKEN_CREDENTIALS)\n    .build();\n\u002F\u002F Or use a specific credential directly in production:\n\u002F\u002F See https:\u002F\u002Flearn.microsoft.com\u002Fjava\u002Fapi\u002Foverview\u002Fazure\u002Fidentity-readme?view=azure-java-stable#credential-classes\n\u002F\u002F TokenCredential credential = new ManagedIdentityCredentialBuilder().build();\n\nContentSafetyClient client = new ContentSafetyClientBuilder()\n    .credential(credential)\n    .endpoint(endpoint)\n    .buildClient();\n```\n\n## Key Concepts\n\n### Harm Categories\n| Category | Description |\n|----------|-------------|\n| Hate | Discriminatory language based on identity groups |\n| Sexual | Sexual content, relationships, acts |\n| Violence | Physical harm, weapons, injury |\n| Self-harm | Self-injury, suicide-related content |\n\n### Severity Levels\n- Text: 0-7 scale (default outputs 0, 2, 4, 6)\n- Image: 0, 2, 4, 6 (trimmed scale)\n\n## Core Patterns\n\n### Analyze Text\n\n```java\nimport com.azure.ai.contentsafety.models.*;\n\nAnalyzeTextResult result = contentSafetyClient.analyzeText(\n    new AnalyzeTextOptions(\"This is text to analyze\"));\n\nfor (TextCategoriesAnalysis category : result.getCategoriesAnalysis()) {\n    System.out.printf(\"Category: %s, Severity: %d%n\",\n        category.getCategory(),\n        category.getSeverity());\n}\n```\n\n### Analyze Text with Options\n\n```java\nAnalyzeTextOptions options = new AnalyzeTextOptions(\"Text to analyze\")\n    .setCategories(Arrays.asList(\n        TextCategory.HATE,\n        TextCategory.VIOLENCE))\n    .setOutputType(AnalyzeTextOutputType.EIGHT_SEVERITY_LEVELS);\n\nAnalyzeTextResult result = contentSafetyClient.analyzeText(options);\n```\n\n### Analyze Text with Blocklist\n\n```java\nAnalyzeTextOptions options = new AnalyzeTextOptions(\"I h*te you and want to k*ll you\")\n    .setBlocklistNames(Arrays.asList(\"my-blocklist\"))\n    .setHaltOnBlocklistHit(true);\n\nAnalyzeTextResult result = contentSafetyClient.analyzeText(options);\n\nif (result.getBlocklistsMatch() != null) {\n    for (TextBlocklistMatch match : result.getBlocklistsMatch()) {\n        System.out.printf(\"Blocklist: %s, Item: %s, Text: %s%n\",\n            match.getBlocklistName(),\n            match.getBlocklistItemId(),\n            match.getBlocklistItemText());\n    }\n}\n```\n\n### Analyze Image\n\n```java\nimport com.azure.ai.contentsafety.models.*;\nimport com.azure.core.util.BinaryData;\nimport java.nio.file.Files;\nimport java.nio.file.Paths;\n\n\u002F\u002F From file\nbyte[] imageBytes = Files.readAllBytes(Paths.get(\"image.png\"));\nContentSafetyImageData imageData = new ContentSafetyImageData()\n    .setContent(BinaryData.fromBytes(imageBytes));\n\nAnalyzeImageResult result = contentSafetyClient.analyzeImage(\n    new AnalyzeImageOptions(imageData));\n\nfor (ImageCategoriesAnalysis category : result.getCategoriesAnalysis()) {\n    System.out.printf(\"Category: %s, Severity: %d%n\",\n        category.getCategory(),\n        category.getSeverity());\n}\n```\n\n### Analyze Image from URL\n\n```java\nContentSafetyImageData imageData = new ContentSafetyImageData()\n    .setBlobUrl(\"https:\u002F\u002Fexample.com\u002Fimage.jpg\");\n\nAnalyzeImageResult result = contentSafetyClient.analyzeImage(\n    new AnalyzeImageOptions(imageData));\n```\n\n## Blocklist Management\n\n### Create or Update Blocklist\n\n```java\nimport com.azure.core.http.rest.RequestOptions;\nimport com.azure.core.http.rest.Response;\nimport com.azure.core.util.BinaryData;\nimport java.util.Map;\n\nMap\u003CString, String> description = Map.of(\"description\", \"Custom blocklist\");\nBinaryData resource = BinaryData.fromObject(description);\n\nResponse\u003CBinaryData> response = blocklistClient.createOrUpdateTextBlocklistWithResponse(\n    \"my-blocklist\", resource, new RequestOptions());\n\nif (response.getStatusCode() == 201) {\n    System.out.println(\"Blocklist created\");\n} else if (response.getStatusCode() == 200) {\n    System.out.println(\"Blocklist updated\");\n}\n```\n\n### Add Block Items\n\n```java\nimport com.azure.ai.contentsafety.models.*;\nimport java.util.Arrays;\n\nList\u003CTextBlocklistItem> items = Arrays.asList(\n    new TextBlocklistItem(\"badword1\").setDescription(\"Offensive term\"),\n    new TextBlocklistItem(\"badword2\").setDescription(\"Another term\")\n);\n\nAddOrUpdateTextBlocklistItemsResult result = blocklistClient.addOrUpdateBlocklistItems(\n    \"my-blocklist\",\n    new AddOrUpdateTextBlocklistItemsOptions(items));\n\nfor (TextBlocklistItem item : result.getBlocklistItems()) {\n    System.out.printf(\"Added: %s (ID: %s)%n\",\n        item.getText(),\n        item.getBlocklistItemId());\n}\n```\n\n### List Blocklists\n\n```java\nPagedIterable\u003CTextBlocklist> blocklists = blocklistClient.listTextBlocklists();\n\nfor (TextBlocklist blocklist : blocklists) {\n    System.out.printf(\"Blocklist: %s, Description: %s%n\",\n        blocklist.getName(),\n        blocklist.getDescription());\n}\n```\n\n### Get Blocklist\n\n```java\nTextBlocklist blocklist = blocklistClient.getTextBlocklist(\"my-blocklist\");\nSystem.out.println(\"Name: \" + blocklist.getName());\n```\n\n### List Block Items\n\n```java\nPagedIterable\u003CTextBlocklistItem> items = \n    blocklistClient.listTextBlocklistItems(\"my-blocklist\");\n\nfor (TextBlocklistItem item : items) {\n    System.out.printf(\"ID: %s, Text: %s%n\",\n        item.getBlocklistItemId(),\n        item.getText());\n}\n```\n\n### Remove Block Items\n\n```java\nList\u003CString> itemIds = Arrays.asList(\"item-id-1\", \"item-id-2\");\n\nblocklistClient.removeBlocklistItems(\n    \"my-blocklist\",\n    new RemoveTextBlocklistItemsOptions(itemIds));\n```\n\n### Delete Blocklist\n\n```java\nblocklistClient.deleteTextBlocklist(\"my-blocklist\");\n```\n\n## Error Handling\n\n```java\nimport com.azure.core.exception.HttpResponseException;\n\ntry {\n    contentSafetyClient.analyzeText(new AnalyzeTextOptions(\"test\"));\n} catch (HttpResponseException e) {\n    System.out.println(\"Status: \" + e.getResponse().getStatusCode());\n    System.out.println(\"Error: \" + e.getMessage());\n    \u002F\u002F Common codes: InvalidRequestBody, ResourceNotFound, TooManyRequests\n}\n```\n\n## Environment Variables\n\n```bash\nCONTENT_SAFETY_ENDPOINT=https:\u002F\u002F\u003Cresource>.cognitiveservices.azure.com\u002F # Required for all auth methods\nCONTENT_SAFETY_KEY=\u003Cyour-api-key> # Only required for AzureKeyCredential auth\nAZURE_TOKEN_CREDENTIALS=prod  # Required only if DefaultAzureCredential is used in production\n```\n\n## Best Practices\n\n1. **Blocklist Delay**: Changes take ~5 minutes to take effect\n2. **Category Selection**: Only request needed categories to reduce latency\n3. **Severity Thresholds**: Typically block severity >= 4 for strict moderation\n4. **Batch Processing**: Process multiple items in parallel for throughput\n5. **Caching**: Cache blocklist results where appropriate\n\n## Trigger Phrases\n\n- \"content safety Java\"\n- \"content moderation Azure\"\n- \"analyze text safety\"\n- \"image moderation Java\"\n- \"blocklist management\"\n- \"hate speech detection\"\n- \"harmful content filter\"\n",{"name":5,"license":15,"metadata":24,"description":7},{"author":25,"package":26,"version":27},"Microsoft","com.azure:azure-ai-contentsafety","1.0.0","master","c247302c836de6438d746b45670990eb71691166","skills_collected\u002Fmicrosoft--skills--.github__plugins__azure-sdk-java__skills__azure-ai-contentsafety-java",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-contentsafety-java",{"tool":42,"command":43},"bunx","bunx skills add qhjqhj00\u002Fresearch-skills-pool --skill azure-ai-contentsafety-java",{"tool":45,"command":46},"pnpm","pnpm dlx skills add qhjqhj00\u002Fresearch-skills-pool --skill azure-ai-contentsafety-java","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-java__skills__azure-ai-contentsafety-java\u002FSKILL.md",true,[50],{"path":51,"resourceType":52,"resourceTypeDesc":53,"sizeBytes":54,"sourceHtmlUrl":55},"references\u002Fexamples.md","REFERENCE","参考文档",17451,"https:\u002F\u002Fgithub.com\u002Fqhjqhj00\u002Fresearch-skills-pool\u002Fblob\u002Fmaster\u002Fskills_collected\u002Fmicrosoft--skills--.github__plugins__azure-sdk-java__skills__azure-ai-contentsafety-java\u002Freferences\u002Fexamples.md",[57,64,71,78,85,92],{"skillNo":58,"name":59,"nameZh":6,"description":60,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":61,"categories":62,"keywords":63,"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":65,"name":66,"nameZh":6,"description":67,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":68,"categories":69,"keywords":70,"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":72,"name":73,"nameZh":6,"description":74,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":75,"categories":76,"keywords":77,"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":79,"name":80,"nameZh":6,"description":81,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":82,"categories":83,"keywords":84,"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":86,"name":87,"nameZh":6,"description":88,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":89,"categories":90,"keywords":91,"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":93,"name":94,"nameZh":6,"description":95,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":96,"licenseFileUrl":6,"sourceHtmlUrl":97,"categories":98,"keywords":99,"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",[],[]]