[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6K4QGF5AD5QDZ9RXGQFQF8G":3,"skill-same:01M6K4QGF5AD5QDZ9RXGQFQF8G":76},{"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":26,"publishedAt":47,"linkOnly":48,"markdownContent":49,"markdownBody":50,"frontMatter":51,"refName":53,"commitSha":54,"skillDirectory":55,"forksCount":56,"repositoryHtmlUrl":57,"repositoryHomepageUrl":6,"ownerHtmlUrl":58,"ownerBlogUrl":59,"ownerDescription":60,"updatedAt":61,"install":62,"resources":75},"01M6K4QGF5AD5QDZ9RXGQFQF8G","transloadit-media-processing",null,"Process media files (video, audio, images, documents) using Transloadit. Use when asked to encode video to HLS\u002FMP4, generate thumbnails, resize or watermark images, extract audio, concatenate clips, add subtitles, OCR documents, or run any media processing pipeline. Covers 86+ processing robots for file transformation at scale.","anjijava16\u002FAgent_Skills","anjijava16","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F5849522?v=4","01M6JZVCV62H56AYM59D11EGAW","Anjaiah Methuku","01M6JZVD04H0QP910VNCZMJFAG",0,"MIT","https:\u002F\u002Fgithub.com\u002Fanjijava16\u002FAgent_Skills\u002Fblob\u002Fdevelop\u002F.github\u002Fskills\u002Ftransloadit-media-processing\u002FSKILL.md",[18,23],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000016","图像与多媒体","SCENARIO","使用场景",{"categoryNo":24,"categoryName":25,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发",[27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46],"processing","transloadit media processing","Media","media processing","mp4","hls","for","free","transformation","files","images","use","MCP","Audio","Video","ocr","pipeline","subtitles","documents","mcp server","2026-11-10 10:12:30",false,"---\nname: transloadit-media-processing\ndescription: 'Process media files (video, audio, images, documents) using Transloadit. Use when asked to encode video to HLS\u002FMP4, generate thumbnails, resize or watermark images, extract audio, concatenate clips, add subtitles, OCR documents, or run any media processing pipeline. Covers 86+ processing robots for file transformation at scale.'\nlicense: MIT\ncompatibility: Requires a free Transloadit account (https:\u002F\u002Ftransloadit.com\u002Fsignup). Uses the @transloadit\u002Fmcp-server MCP server or the @transloadit\u002Fnode CLI.\n---\n\n# Transloadit Media Processing\n\nProcess, transform, and encode media files using Transloadit's cloud infrastructure.\nSupports video, audio, images, and documents with 86+ specialized processing robots.\n\n## When to Use This Skill\n\nUse this skill when you need to:\n\n- Encode video to HLS, MP4, WebM, or other formats\n- Generate thumbnails or animated GIFs from video\n- Resize, crop, watermark, or optimize images\n- Convert between image formats (JPEG, PNG, WebP, AVIF, HEIF)\n- Extract or transcode audio (MP3, AAC, FLAC, WAV)\n- Concatenate video or audio clips\n- Add subtitles or overlay text on video\n- OCR documents (PDF, scanned images)\n- Run speech-to-text or text-to-speech\n- Apply AI-based content moderation or object detection\n- Build multi-step media pipelines that chain operations together\n\n## Setup\n\n### Option A: MCP Server (recommended for Copilot)\n\nAdd the Transloadit MCP server to your IDE config. This gives the agent direct access\nto Transloadit tools (`create_template`, `create_assembly`, `list_assembly_notifications`, etc.).\n\n**VS Code \u002F GitHub Copilot** (`.vscode\u002Fmcp.json` or user settings):\n\n```json\n{\n  \"servers\": {\n    \"transloadit\": {\n      \"command\": \"npx\",\n      \"args\": [\"-y\", \"@transloadit\u002Fmcp-server\", \"stdio\"],\n      \"env\": {\n        \"TRANSLOADIT_KEY\": \"YOUR_AUTH_KEY\",\n        \"TRANSLOADIT_SECRET\": \"YOUR_AUTH_SECRET\"\n      }\n    }\n  }\n}\n```\n\nGet your API credentials at https:\u002F\u002Ftransloadit.com\u002Fc\u002F-\u002Fapi-credentials\n\n### Option B: CLI\n\nIf you prefer running commands directly:\n\n```bash\nnpx -y @transloadit\u002Fnode assemblies create \\\n  --steps '{\"encoded\": {\"robot\": \"\u002Fvideo\u002Fencode\", \"use\": \":original\", \"preset\": \"hls-1080p\"}}' \\\n  --wait \\\n  --input .\u002Fmy-video.mp4\n```\n\n## Core Workflows\n\n### Encode Video to HLS (Adaptive Streaming)\n\n```json\n{\n  \"steps\": {\n    \"encoded\": {\n      \"robot\": \"\u002Fvideo\u002Fencode\",\n      \"use\": \":original\",\n      \"preset\": \"hls-1080p\"\n    }\n  }\n}\n```\n\n### Generate Thumbnails from Video\n\n```json\n{\n  \"steps\": {\n    \"thumbnails\": {\n      \"robot\": \"\u002Fvideo\u002Fthumbs\",\n      \"use\": \":original\",\n      \"count\": 8,\n      \"width\": 320,\n      \"height\": 240\n    }\n  }\n}\n```\n\n### Resize and Watermark Images\n\n```json\n{\n  \"steps\": {\n    \"resized\": {\n      \"robot\": \"\u002Fimage\u002Fresize\",\n      \"use\": \":original\",\n      \"width\": 1200,\n      \"height\": 800,\n      \"resize_strategy\": \"fit\"\n    },\n    \"watermarked\": {\n      \"robot\": \"\u002Fimage\u002Fresize\",\n      \"use\": \"resized\",\n      \"watermark_url\": \"https:\u002F\u002Fexample.com\u002Flogo.png\",\n      \"watermark_position\": \"bottom-right\",\n      \"watermark_size\": \"15%\"\n    }\n  }\n}\n```\n\n### OCR a Document\n\n```json\n{\n  \"steps\": {\n    \"recognized\": {\n      \"robot\": \"\u002Fdocument\u002Focr\",\n      \"use\": \":original\",\n      \"provider\": \"aws\",\n      \"format\": \"text\"\n    }\n  }\n}\n```\n\n### Concatenate Audio Clips\n\n```json\n{\n  \"steps\": {\n    \"imported\": {\n      \"robot\": \"\u002Fhttp\u002Fimport\",\n      \"url\": [\"https:\u002F\u002Fexample.com\u002Fclip1.mp3\", \"https:\u002F\u002Fexample.com\u002Fclip2.mp3\"]\n    },\n    \"concatenated\": {\n      \"robot\": \"\u002Faudio\u002Fconcat\",\n      \"use\": \"imported\",\n      \"preset\": \"mp3\"\n    }\n  }\n}\n```\n\n## Multi-Step Pipelines\n\nSteps can be chained using the `\"use\"` field. Each step references a previous step's output:\n\n```json\n{\n  \"steps\": {\n    \"resized\": {\n      \"robot\": \"\u002Fimage\u002Fresize\",\n      \"use\": \":original\",\n      \"width\": 1920\n    },\n    \"optimized\": {\n      \"robot\": \"\u002Fimage\u002Foptimize\",\n      \"use\": \"resized\"\n    },\n    \"exported\": {\n      \"robot\": \"\u002Fs3\u002Fstore\",\n      \"use\": \"optimized\",\n      \"bucket\": \"my-bucket\",\n      \"path\": \"processed\u002F${file.name}\"\n    }\n  }\n}\n```\n\n## Key Concepts\n\n- **Assembly**: A single processing job. Created via `create_assembly` (MCP) or `assemblies create` (CLI).\n- **Template**: A reusable set of steps stored on Transloadit. Created via `create_template` (MCP) or `templates create` (CLI).\n- **Robot**: A processing unit (e.g., `\u002Fvideo\u002Fencode`, `\u002Fimage\u002Fresize`). See full list at https:\u002F\u002Ftransloadit.com\u002Fdocs\u002Ftranscoding\u002F\n- **Steps**: JSON object defining the pipeline. Each key is a step name, each value configures a robot.\n- **`:original`**: Refers to the uploaded input file.\n\n## Tips\n\n- Use `--wait` with the CLI to block until processing completes.\n- Use `preset` values (e.g., `\"hls-1080p\"`, `\"mp3\"`, `\"webp\"`) for common format targets instead of specifying every parameter.\n- Chain `\"use\": \"step_name\"` to build multi-step pipelines without intermediate downloads.\n- For batch processing, use `\u002Fhttp\u002Fimport` to pull files from URLs, S3, GCS, Azure, FTP, or Dropbox.\n- Templates can include `${variables}` for dynamic values passed at assembly creation time.\n","# Transloadit Media Processing\n\nProcess, transform, and encode media files using Transloadit's cloud infrastructure.\nSupports video, audio, images, and documents with 86+ specialized processing robots.\n\n## When to Use This Skill\n\nUse this skill when you need to:\n\n- Encode video to HLS, MP4, WebM, or other formats\n- Generate thumbnails or animated GIFs from video\n- Resize, crop, watermark, or optimize images\n- Convert between image formats (JPEG, PNG, WebP, AVIF, HEIF)\n- Extract or transcode audio (MP3, AAC, FLAC, WAV)\n- Concatenate video or audio clips\n- Add subtitles or overlay text on video\n- OCR documents (PDF, scanned images)\n- Run speech-to-text or text-to-speech\n- Apply AI-based content moderation or object detection\n- Build multi-step media pipelines that chain operations together\n\n## Setup\n\n### Option A: MCP Server (recommended for Copilot)\n\nAdd the Transloadit MCP server to your IDE config. This gives the agent direct access\nto Transloadit tools (`create_template`, `create_assembly`, `list_assembly_notifications`, etc.).\n\n**VS Code \u002F GitHub Copilot** (`.vscode\u002Fmcp.json` or user settings):\n\n```json\n{\n  \"servers\": {\n    \"transloadit\": {\n      \"command\": \"npx\",\n      \"args\": [\"-y\", \"@transloadit\u002Fmcp-server\", \"stdio\"],\n      \"env\": {\n        \"TRANSLOADIT_KEY\": \"YOUR_AUTH_KEY\",\n        \"TRANSLOADIT_SECRET\": \"YOUR_AUTH_SECRET\"\n      }\n    }\n  }\n}\n```\n\nGet your API credentials at https:\u002F\u002Ftransloadit.com\u002Fc\u002F-\u002Fapi-credentials\n\n### Option B: CLI\n\nIf you prefer running commands directly:\n\n```bash\nnpx -y @transloadit\u002Fnode assemblies create \\\n  --steps '{\"encoded\": {\"robot\": \"\u002Fvideo\u002Fencode\", \"use\": \":original\", \"preset\": \"hls-1080p\"}}' \\\n  --wait \\\n  --input .\u002Fmy-video.mp4\n```\n\n## Core Workflows\n\n### Encode Video to HLS (Adaptive Streaming)\n\n```json\n{\n  \"steps\": {\n    \"encoded\": {\n      \"robot\": \"\u002Fvideo\u002Fencode\",\n      \"use\": \":original\",\n      \"preset\": \"hls-1080p\"\n    }\n  }\n}\n```\n\n### Generate Thumbnails from Video\n\n```json\n{\n  \"steps\": {\n    \"thumbnails\": {\n      \"robot\": \"\u002Fvideo\u002Fthumbs\",\n      \"use\": \":original\",\n      \"count\": 8,\n      \"width\": 320,\n      \"height\": 240\n    }\n  }\n}\n```\n\n### Resize and Watermark Images\n\n```json\n{\n  \"steps\": {\n    \"resized\": {\n      \"robot\": \"\u002Fimage\u002Fresize\",\n      \"use\": \":original\",\n      \"width\": 1200,\n      \"height\": 800,\n      \"resize_strategy\": \"fit\"\n    },\n    \"watermarked\": {\n      \"robot\": \"\u002Fimage\u002Fresize\",\n      \"use\": \"resized\",\n      \"watermark_url\": \"https:\u002F\u002Fexample.com\u002Flogo.png\",\n      \"watermark_position\": \"bottom-right\",\n      \"watermark_size\": \"15%\"\n    }\n  }\n}\n```\n\n### OCR a Document\n\n```json\n{\n  \"steps\": {\n    \"recognized\": {\n      \"robot\": \"\u002Fdocument\u002Focr\",\n      \"use\": \":original\",\n      \"provider\": \"aws\",\n      \"format\": \"text\"\n    }\n  }\n}\n```\n\n### Concatenate Audio Clips\n\n```json\n{\n  \"steps\": {\n    \"imported\": {\n      \"robot\": \"\u002Fhttp\u002Fimport\",\n      \"url\": [\"https:\u002F\u002Fexample.com\u002Fclip1.mp3\", \"https:\u002F\u002Fexample.com\u002Fclip2.mp3\"]\n    },\n    \"concatenated\": {\n      \"robot\": \"\u002Faudio\u002Fconcat\",\n      \"use\": \"imported\",\n      \"preset\": \"mp3\"\n    }\n  }\n}\n```\n\n## Multi-Step Pipelines\n\nSteps can be chained using the `\"use\"` field. Each step references a previous step's output:\n\n```json\n{\n  \"steps\": {\n    \"resized\": {\n      \"robot\": \"\u002Fimage\u002Fresize\",\n      \"use\": \":original\",\n      \"width\": 1920\n    },\n    \"optimized\": {\n      \"robot\": \"\u002Fimage\u002Foptimize\",\n      \"use\": \"resized\"\n    },\n    \"exported\": {\n      \"robot\": \"\u002Fs3\u002Fstore\",\n      \"use\": \"optimized\",\n      \"bucket\": \"my-bucket\",\n      \"path\": \"processed\u002F${file.name}\"\n    }\n  }\n}\n```\n\n## Key Concepts\n\n- **Assembly**: A single processing job. Created via `create_assembly` (MCP) or `assemblies create` (CLI).\n- **Template**: A reusable set of steps stored on Transloadit. Created via `create_template` (MCP) or `templates create` (CLI).\n- **Robot**: A processing unit (e.g., `\u002Fvideo\u002Fencode`, `\u002Fimage\u002Fresize`). See full list at https:\u002F\u002Ftransloadit.com\u002Fdocs\u002Ftranscoding\u002F\n- **Steps**: JSON object defining the pipeline. Each key is a step name, each value configures a robot.\n- **`:original`**: Refers to the uploaded input file.\n\n## Tips\n\n- Use `--wait` with the CLI to block until processing completes.\n- Use `preset` values (e.g., `\"hls-1080p\"`, `\"mp3\"`, `\"webp\"`) for common format targets instead of specifying every parameter.\n- Chain `\"use\": \"step_name\"` to build multi-step pipelines without intermediate downloads.\n- For batch processing, use `\u002Fhttp\u002Fimport` to pull files from URLs, S3, GCS, Azure, FTP, or Dropbox.\n- Templates can include `${variables}` for dynamic values passed at assembly creation time.\n",{"name":5,"license":15,"description":7,"compatibility":52},"Requires a free Transloadit account (https:\u002F\u002Ftransloadit.com\u002Fsignup). Uses the @transloadit\u002Fmcp-server MCP server or the @transloadit\u002Fnode CLI.","develop","d85a5e71a5e3e82038a005e5dfa50b6a78cafa7e",".github\u002Fskills\u002Ftransloadit-media-processing",1,"https:\u002F\u002Fgithub.com\u002Fanjijava16\u002FAgent_Skills","https:\u002F\u002Fgithub.com\u002Fanjijava16","https:\u002F\u002Fwww.linkedin.com\u002Fin\u002Fanjaiahmethuku\u002F","AI & Data Engineer ■ Real-time Streaming ■ BigData ■ Machine Learning ■ CLOUD ■ JAVA ■ PYTHON ■ Blog ■  Remain Curious And Keep Learning .....","2026-10-08 08:03:12",{"source":8,"skillName":5,"commands":63,"prompt":73,"zipAvailable":74},[64,67,70],{"tool":65,"command":66},"npx","npx skills add anjijava16\u002FAgent_Skills --skill transloadit-media-processing",{"tool":68,"command":69},"bunx","bunx skills add anjijava16\u002FAgent_Skills --skill transloadit-media-processing",{"tool":71,"command":72},"pnpm","pnpm dlx skills add anjijava16\u002FAgent_Skills --skill transloadit-media-processing","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fanjijava16\u002FAgent_Skills\u002Fblob\u002Fdevelop\u002F.github\u002Fskills\u002Ftransloadit-media-processing\u002FSKILL.md",true,[],[77,96,123,140,155,187],{"skillNo":78,"name":79,"nameZh":6,"description":80,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":81,"categories":82,"keywords":83,"publishedAt":47},"01M6K52P5M72CRGAHJTVAWSNRA","roll-dice","Roll dice using a random number generator. Use when asked to roll a die (d4, d6, d8, d10, d12, d20, d100), roll multiple dice, or generate random dice rolls for tabletop RPGs, board games, or decision making.","https:\u002F\u002Fgithub.com\u002Fanjijava16\u002FAgent_Skills\u002Fblob\u002Fdevelop\u002Froll-dice\u002FSKILL.md",[],[84,85,86,87,88,89,90,38,91,92,93,94,95,33],"roll dice","dice","welcome","generate","tabletop","decision","board","decision making","random","games","generator","number",{"skillNo":97,"name":98,"nameZh":6,"description":99,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":100,"categories":101,"keywords":105,"publishedAt":47},"01M6K52JJKRBM0A5EXT12G87RW","pdf-service","Extract text and tables from PDFs, fill PDF forms, merge and split PDF files, and convert PDFs to other formats. Use when the user mentions PDFs, document extraction, form filling, or needs to manipulate PDF files.","https:\u002F\u002Fgithub.com\u002Fanjijava16\u002FAgent_Skills\u002Fblob\u002Fdevelop\u002Fpdf-service\u002FSKILL.md",[102],{"categoryNo":103,"categoryName":104,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000002","文档处理",[106,107,108,109,110,86,111,112,113,114,115,38,36,116,117,118,119,120,121,122],"PDF","service","pdf service","python","merge","extraction","convert","text","user","extract","document","forms","form","formats","split","pip","fill",{"skillNo":124,"name":125,"nameZh":6,"description":126,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":127,"categories":128,"keywords":130,"publishedAt":47},"01M6K52EVG86E60AQFMJAZ1G09","pdf-processing","Extract text, tables, and metadata from PDF documents. Parse scanned PDFs with OCR, analyze PDF structure, and convert PDFs to other formats. Use when the user needs to read, parse, or extract content from PDF files, even if they just say \"get the text from this document.\"","https:\u002F\u002Fgithub.com\u002Fanjijava16\u002FAgent_Skills\u002Fblob\u002Fdevelop\u002Fpdf-processing\u002FSKILL.md",[129],{"categoryNo":103,"categoryName":104,"taxonomyType":21,"taxonomyTypeDesc":22},[106,131,27,109,45,42,112,132,113,133,134,38,135,36,116,136,137,138,139,121],"pdf processing","analyze","just","read","say","structure","get","tesseract","with",{"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":147,"publishedAt":47},"01M6K52A7EC35DTS48PP0VX5TB","my-skill","A template skill for [describe task]. Use when the user asks to [trigger phrases].","https:\u002F\u002Fgithub.com\u002Fanjijava16\u002FAgent_Skills\u002Fblob\u002Fdevelop\u002Fmy-skill\u002FSKILL.md",[146],{"categoryNo":24,"categoryName":25,"taxonomyType":21,"taxonomyTypeDesc":22},[148,149,150,151,114,38,152,153,154,33],"my skill","my","template skill","template","task","trigger","name",{"skillNo":156,"name":157,"nameZh":6,"description":158,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":159,"categories":160,"keywords":172,"publishedAt":47},"01M6K51Y5QVHMDX3F01JJRRV33","data-analysis","Analyze datasets — compute summary statistics, clean messy data, add derived columns, detect outliers, and generate charts. Use when the user has a CSV, TSV, Excel, or JSON data file and wants to explore, transform, visualize, or understand the data, even if they don't explicitly mention \"analysis.\"","https:\u002F\u002Fgithub.com\u002Fanjijava16\u002FAgent_Skills\u002Fblob\u002Fdevelop\u002Fdata-analysis\u002FSKILL.md",[161,164,167],{"categoryNo":162,"categoryName":163,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000004","电子表格",{"categoryNo":165,"categoryName":166,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000013","分析与可视化",{"categoryNo":168,"categoryName":169,"taxonomyType":170,"taxonomyTypeDesc":171},"01JBSEEDCAT000000000000033","数据分析师","PROFESSION","适用职业",[173,174,175,176,109,177,86,87,178,179,180,181,132,38,182,183,184,185,186,121],"data analysis","data","analysis","xlsx","visualize","file","csv","Charts","explore","clean","statistics","add","transform","columns",{"skillNo":188,"name":189,"nameZh":6,"description":190,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":191,"categories":192,"keywords":199,"publishedAt":47},"01M6K51P73MWRNWFM80SYVBST0","code-review","Review code for bugs, security vulnerabilities, performance issues, and style problems. Provide actionable feedback with severity levels and fix suggestions. Use when the user asks to review, audit, or check code quality, or wants a second pair of eyes on a pull request, diff, or code change.","https:\u002F\u002Fgithub.com\u002Fanjijava16\u002FAgent_Skills\u002Fblob\u002Fdevelop\u002Fcode-review\u002FSKILL.md",[193,196],{"categoryNo":194,"categoryName":195,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000007","代码审查",{"categoryNo":197,"categoryName":198,"taxonomyType":170,"taxonomyTypeDesc":171},"01JBSEEDCAT000000000000030","开发工程师",[200,201,202,203,204,205,206,207,208,209,210,211,212,38,213,214,215,139,33,216],"code review","review","code","performance","change","code quality","issues","pull","audit","severity","feedback","check","fix","diff","style","actionable","bugs"]