[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M71G9HABAGCWN2PW058B5GCP":3,"skill-same:01M71G9HABAGCWN2PW058B5GCP":107},{"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":33,"publishedAt":53,"linkOnly":54,"markdownContent":55,"markdownBody":56,"frontMatter":57,"refName":58,"commitSha":59,"skillDirectory":60,"forksCount":61,"repositoryHtmlUrl":62,"repositoryHomepageUrl":6,"ownerHtmlUrl":63,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":64,"install":65,"resources":78},"01M71G9HABAGCWN2PW058B5GCP","markitdown",null,"Convert various file formats (PDF, Office documents, images, audio, web content, structured data) to Markdown optimized for LLM processing. Use when converting documents to markdown, extracting text from PDFs\u002FOffice files, transcribing audio, performing OCR on images, extracting YouTube transcripts, or processing batches of files. Supports 20+ formats including DOCX, XLSX, PPTX, PDF, HTML, EPUB, CSV, JSON, images with OCR, and audio with transcription.","JSGforever\u002Fskillguard","JSGforever","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F85541948?v=4","01M71FQD3E132VMR5F4TAYX3YS","01M71FQD4DYW0XJ4XQ4YQH75Y9",2,"GPL-3.0","https:\u002F\u002Fgithub.com\u002FJSGforever\u002Fskillguard\u002Fblob\u002Fmain\u002Fbenchmarks\u002Ffinal\u002Fskills\u002Fasset1__Microck--claude-scientific-skills\u002Fscientific-skills\u002Fmarkitdown\u002FSKILL.md",[17,22,25,28],{"categoryNo":18,"categoryName":19,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000002","文档处理","SCENARIO","使用场景",{"categoryNo":23,"categoryName":24,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000003","演示文稿",{"categoryNo":26,"categoryName":27,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000004","电子表格",{"categoryNo":29,"categoryName":30,"taxonomyType":31,"taxonomyTypeDesc":32},"01JBSEEDCAT000000000000034","行政与办公人员","PROFESSION","适用职业",[5,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48,49,50,51,52],"files","formats","data","youtube transcripts","markdown","youtube","text","web content","when","documents","xlsx","extracting","pptx","Audio","processing","PDF","docx","ocr","images","2026-11-10 10:12:30",false,"---\nname: markitdown\ndescription: Convert various file formats (PDF, Office documents, images, audio, web content, structured data) to Markdown optimized for LLM processing. Use when converting documents to markdown, extracting text from PDFs\u002FOffice files, transcribing audio, performing OCR on images, extracting YouTube transcripts, or processing batches of files. Supports 20+ formats including DOCX, XLSX, PPTX, PDF, HTML, EPUB, CSV, JSON, images with OCR, and audio with transcription.\n---\n\n# MarkItDown\n\n## Overview\n\nMarkItDown is a Python utility that converts various file formats into Markdown format, optimized for use with large language models and text analysis pipelines. It preserves document structure (headings, lists, tables, hyperlinks) while producing clean, token-efficient Markdown output.\n\n## When to Use This Skill\n\nUse this skill when users request:\n- Converting documents to Markdown format\n- Extracting text from PDF, Word, PowerPoint, or Excel files\n- Performing OCR on images to extract text\n- Transcribing audio files to text\n- Extracting YouTube video transcripts\n- Processing HTML, EPUB, or web content to Markdown\n- Converting structured data (CSV, JSON, XML) to readable Markdown\n- Batch converting multiple files or ZIP archives\n- Preparing documents for LLM analysis or RAG systems\n\n## Core Capabilities\n\n### 1. Document Conversion\n\nConvert Office documents and PDFs to Markdown while preserving structure.\n\n**Supported formats:**\n- PDF files (with optional Azure Document Intelligence integration)\n- Word documents (DOCX)\n- PowerPoint presentations (PPTX)\n- Excel spreadsheets (XLSX, XLS)\n\n**Basic usage:**\n```python\nfrom markitdown import MarkItDown\n\nmd = MarkItDown()\nresult = md.convert(\"document.pdf\")\nprint(result.text_content)\n```\n\n**Command-line:**\n```bash\nmarkitdown document.pdf -o output.md\n```\n\nSee `references\u002Fdocument_conversion.md` for detailed documentation on document-specific features.\n\n### 2. Media Processing\n\nExtract text from images using OCR and transcribe audio files to text.\n\n**Supported formats:**\n- Images (JPEG, PNG, GIF, etc.) with EXIF metadata extraction\n- Audio files with speech transcription (requires speech_recognition)\n\n**Image with OCR:**\n```python\nfrom markitdown import MarkItDown\n\nmd = MarkItDown()\nresult = md.convert(\"image.jpg\")\nprint(result.text_content)  # Includes EXIF metadata and OCR text\n```\n\n**Audio transcription:**\n```python\nresult = md.convert(\"audio.wav\")\nprint(result.text_content)  # Transcribed speech\n```\n\nSee `references\u002Fmedia_processing.md` for advanced media handling options.\n\n### 3. Web Content Extraction\n\nConvert web-based content and e-books to Markdown.\n\n**Supported formats:**\n- HTML files and web pages\n- YouTube video transcripts (via URL)\n- EPUB books\n- RSS feeds\n\n**YouTube transcript:**\n```python\nfrom markitdown import MarkItDown\n\nmd = MarkItDown()\nresult = md.convert(\"https:\u002F\u002Fyoutube.com\u002Fwatch?v=VIDEO_ID\")\nprint(result.text_content)\n```\n\nSee `references\u002Fweb_content.md` for web extraction details.\n\n### 4. Structured Data Handling\n\nConvert structured data formats to readable Markdown tables.\n\n**Supported formats:**\n- CSV files\n- JSON files\n- XML files\n\n**CSV to Markdown table:**\n```python\nfrom markitdown import MarkItDown\n\nmd = MarkItDown()\nresult = md.convert(\"data.csv\")\nprint(result.text_content)  # Formatted as Markdown table\n```\n\nSee `references\u002Fstructured_data.md` for format-specific options.\n\n### 5. Advanced Integrations\n\nEnhance conversion quality with AI-powered features.\n\n**Azure Document Intelligence:**\nFor enhanced PDF processing with better table extraction and layout analysis:\n```python\nfrom markitdown import MarkItDown\n\nmd = MarkItDown(docintel_endpoint=\"\u003Cendpoint>\", docintel_key=\"\u003Ckey>\")\nresult = md.convert(\"complex.pdf\")\n```\n\n**LLM-Powered Image Descriptions:**\nGenerate detailed image descriptions using GPT-4o:\n```python\nfrom markitdown import MarkItDown\nfrom openai import OpenAI\n\nclient = OpenAI()\nmd = MarkItDown(llm_client=client, llm_model=\"gpt-4o\")\nresult = md.convert(\"presentation.pptx\")  # Images described with LLM\n```\n\nSee `references\u002Fadvanced_integrations.md` for integration details.\n\n### 6. Batch Processing\n\nProcess multiple files or entire ZIP archives at once.\n\n**ZIP file processing:**\n```python\nfrom markitdown import MarkItDown\n\nmd = MarkItDown()\nresult = md.convert(\"archive.zip\")\nprint(result.text_content)  # All files converted and concatenated\n```\n\n**Batch script:**\nUse the provided batch processing script for directory conversion:\n```bash\npython scripts\u002Fbatch_convert.py \u002Fpath\u002Fto\u002Fdocuments \u002Fpath\u002Fto\u002Foutput\n```\n\nSee `scripts\u002Fbatch_convert.py` for implementation details.\n\n## Installation\n\n**Full installation (all features):**\n```bash\nuv pip install 'markitdown[all]'\n```\n\n**Modular installation (specific features):**\n```bash\nuv pip install 'markitdown[pdf]'           # PDF support\nuv pip install 'markitdown[docx]'          # Word support\nuv pip install 'markitdown[pptx]'          # PowerPoint support\nuv pip install 'markitdown[xlsx]'          # Excel support\nuv pip install 'markitdown[audio]'         # Audio transcription\nuv pip install 'markitdown[youtube]'       # YouTube transcripts\n```\n\n**Requirements:**\n- Python 3.10 or higher\n\n## Output Format\n\nMarkItDown produces clean, token-efficient Markdown optimized for LLM consumption:\n- Preserves headings, lists, and tables\n- Maintains hyperlinks and formatting\n- Includes metadata where relevant (EXIF, document properties)\n- No temporary files created (streaming approach)\n\n## Common Workflows\n\n**Preparing documents for RAG:**\n```python\nfrom markitdown import MarkItDown\n\nmd = MarkItDown()\n\n# Convert knowledge base documents\ndocs = [\"manual.pdf\", \"guide.docx\", \"faq.html\"]\nmarkdown_content = []\n\nfor doc in docs:\n    result = md.convert(doc)\n    markdown_content.append(result.text_content)\n\n# Now ready for embedding and indexing\n```\n\n**Document analysis pipeline:**\n```bash\n# Convert all PDFs in directory\nfor file in documents\u002F*.pdf; do\n    markitdown \"$file\" -o \"markdown\u002F$(basename \"$file\" .pdf).md\"\ndone\n```\n\n## Plugin System\n\nMarkItDown supports extensible plugins for custom conversion logic. Plugins are disabled by default for security:\n\n```python\nfrom markitdown import MarkItDown\n\n# Enable plugins if needed\nmd = MarkItDown(enable_plugins=True)\n```\n\n## Resources\n\nThis skill includes comprehensive reference documentation for each capability:\n\n- **references\u002Fdocument_conversion.md** - Detailed PDF, DOCX, PPTX, XLSX conversion options\n- **references\u002Fmedia_processing.md** - Image OCR and audio transcription details\n- **references\u002Fweb_content.md** - HTML, YouTube, and EPUB extraction\n- **references\u002Fstructured_data.md** - CSV, JSON, XML conversion formats\n- **references\u002Fadvanced_integrations.md** - Azure Document Intelligence and LLM integration\n- **scripts\u002Fbatch_convert.py** - Batch processing utility for directories\n","# MarkItDown\n\n## Overview\n\nMarkItDown is a Python utility that converts various file formats into Markdown format, optimized for use with large language models and text analysis pipelines. It preserves document structure (headings, lists, tables, hyperlinks) while producing clean, token-efficient Markdown output.\n\n## When to Use This Skill\n\nUse this skill when users request:\n- Converting documents to Markdown format\n- Extracting text from PDF, Word, PowerPoint, or Excel files\n- Performing OCR on images to extract text\n- Transcribing audio files to text\n- Extracting YouTube video transcripts\n- Processing HTML, EPUB, or web content to Markdown\n- Converting structured data (CSV, JSON, XML) to readable Markdown\n- Batch converting multiple files or ZIP archives\n- Preparing documents for LLM analysis or RAG systems\n\n## Core Capabilities\n\n### 1. Document Conversion\n\nConvert Office documents and PDFs to Markdown while preserving structure.\n\n**Supported formats:**\n- PDF files (with optional Azure Document Intelligence integration)\n- Word documents (DOCX)\n- PowerPoint presentations (PPTX)\n- Excel spreadsheets (XLSX, XLS)\n\n**Basic usage:**\n```python\nfrom markitdown import MarkItDown\n\nmd = MarkItDown()\nresult = md.convert(\"document.pdf\")\nprint(result.text_content)\n```\n\n**Command-line:**\n```bash\nmarkitdown document.pdf -o output.md\n```\n\nSee `references\u002Fdocument_conversion.md` for detailed documentation on document-specific features.\n\n### 2. Media Processing\n\nExtract text from images using OCR and transcribe audio files to text.\n\n**Supported formats:**\n- Images (JPEG, PNG, GIF, etc.) with EXIF metadata extraction\n- Audio files with speech transcription (requires speech_recognition)\n\n**Image with OCR:**\n```python\nfrom markitdown import MarkItDown\n\nmd = MarkItDown()\nresult = md.convert(\"image.jpg\")\nprint(result.text_content)  # Includes EXIF metadata and OCR text\n```\n\n**Audio transcription:**\n```python\nresult = md.convert(\"audio.wav\")\nprint(result.text_content)  # Transcribed speech\n```\n\nSee `references\u002Fmedia_processing.md` for advanced media handling options.\n\n### 3. Web Content Extraction\n\nConvert web-based content and e-books to Markdown.\n\n**Supported formats:**\n- HTML files and web pages\n- YouTube video transcripts (via URL)\n- EPUB books\n- RSS feeds\n\n**YouTube transcript:**\n```python\nfrom markitdown import MarkItDown\n\nmd = MarkItDown()\nresult = md.convert(\"https:\u002F\u002Fyoutube.com\u002Fwatch?v=VIDEO_ID\")\nprint(result.text_content)\n```\n\nSee `references\u002Fweb_content.md` for web extraction details.\n\n### 4. Structured Data Handling\n\nConvert structured data formats to readable Markdown tables.\n\n**Supported formats:**\n- CSV files\n- JSON files\n- XML files\n\n**CSV to Markdown table:**\n```python\nfrom markitdown import MarkItDown\n\nmd = MarkItDown()\nresult = md.convert(\"data.csv\")\nprint(result.text_content)  # Formatted as Markdown table\n```\n\nSee `references\u002Fstructured_data.md` for format-specific options.\n\n### 5. Advanced Integrations\n\nEnhance conversion quality with AI-powered features.\n\n**Azure Document Intelligence:**\nFor enhanced PDF processing with better table extraction and layout analysis:\n```python\nfrom markitdown import MarkItDown\n\nmd = MarkItDown(docintel_endpoint=\"\u003Cendpoint>\", docintel_key=\"\u003Ckey>\")\nresult = md.convert(\"complex.pdf\")\n```\n\n**LLM-Powered Image Descriptions:**\nGenerate detailed image descriptions using GPT-4o:\n```python\nfrom markitdown import MarkItDown\nfrom openai import OpenAI\n\nclient = OpenAI()\nmd = MarkItDown(llm_client=client, llm_model=\"gpt-4o\")\nresult = md.convert(\"presentation.pptx\")  # Images described with LLM\n```\n\nSee `references\u002Fadvanced_integrations.md` for integration details.\n\n### 6. Batch Processing\n\nProcess multiple files or entire ZIP archives at once.\n\n**ZIP file processing:**\n```python\nfrom markitdown import MarkItDown\n\nmd = MarkItDown()\nresult = md.convert(\"archive.zip\")\nprint(result.text_content)  # All files converted and concatenated\n```\n\n**Batch script:**\nUse the provided batch processing script for directory conversion:\n```bash\npython scripts\u002Fbatch_convert.py \u002Fpath\u002Fto\u002Fdocuments \u002Fpath\u002Fto\u002Foutput\n```\n\nSee `scripts\u002Fbatch_convert.py` for implementation details.\n\n## Installation\n\n**Full installation (all features):**\n```bash\nuv pip install 'markitdown[all]'\n```\n\n**Modular installation (specific features):**\n```bash\nuv pip install 'markitdown[pdf]'           # PDF support\nuv pip install 'markitdown[docx]'          # Word support\nuv pip install 'markitdown[pptx]'          # PowerPoint support\nuv pip install 'markitdown[xlsx]'          # Excel support\nuv pip install 'markitdown[audio]'         # Audio transcription\nuv pip install 'markitdown[youtube]'       # YouTube transcripts\n```\n\n**Requirements:**\n- Python 3.10 or higher\n\n## Output Format\n\nMarkItDown produces clean, token-efficient Markdown optimized for LLM consumption:\n- Preserves headings, lists, and tables\n- Maintains hyperlinks and formatting\n- Includes metadata where relevant (EXIF, document properties)\n- No temporary files created (streaming approach)\n\n## Common Workflows\n\n**Preparing documents for RAG:**\n```python\nfrom markitdown import MarkItDown\n\nmd = MarkItDown()\n\n# Convert knowledge base documents\ndocs = [\"manual.pdf\", \"guide.docx\", \"faq.html\"]\nmarkdown_content = []\n\nfor doc in docs:\n    result = md.convert(doc)\n    markdown_content.append(result.text_content)\n\n# Now ready for embedding and indexing\n```\n\n**Document analysis pipeline:**\n```bash\n# Convert all PDFs in directory\nfor file in documents\u002F*.pdf; do\n    markitdown \"$file\" -o \"markdown\u002F$(basename \"$file\" .pdf).md\"\ndone\n```\n\n## Plugin System\n\nMarkItDown supports extensible plugins for custom conversion logic. Plugins are disabled by default for security:\n\n```python\nfrom markitdown import MarkItDown\n\n# Enable plugins if needed\nmd = MarkItDown(enable_plugins=True)\n```\n\n## Resources\n\nThis skill includes comprehensive reference documentation for each capability:\n\n- **references\u002Fdocument_conversion.md** - Detailed PDF, DOCX, PPTX, XLSX conversion options\n- **references\u002Fmedia_processing.md** - Image OCR and audio transcription details\n- **references\u002Fweb_content.md** - HTML, YouTube, and EPUB extraction\n- **references\u002Fstructured_data.md** - CSV, JSON, XML conversion formats\n- **references\u002Fadvanced_integrations.md** - Azure Document Intelligence and LLM integration\n- **scripts\u002Fbatch_convert.py** - Batch processing utility for directories\n",{"name":5,"description":7},"main","f2ec4b3b9133d34eeaf9b38e4b0a97e8e5705a7f","benchmarks\u002Ffinal\u002Fskills\u002Fasset1__Microck--claude-scientific-skills\u002Fscientific-skills\u002Fmarkitdown",0,"https:\u002F\u002Fgithub.com\u002FJSGforever\u002Fskillguard","https:\u002F\u002Fgithub.com\u002FJSGforever","2026-08-29 18:27:56",{"source":8,"skillName":5,"commands":66,"prompt":76,"zipAvailable":77},[67,70,73],{"tool":68,"command":69},"npx","npx skills add JSGforever\u002Fskillguard --skill markitdown",{"tool":71,"command":72},"bunx","bunx skills add JSGforever\u002Fskillguard --skill markitdown",{"tool":74,"command":75},"pnpm","pnpm dlx skills add JSGforever\u002Fskillguard --skill markitdown","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FJSGforever\u002Fskillguard\u002Fblob\u002Fmain\u002Fbenchmarks\u002Ffinal\u002Fskills\u002Fasset1__Microck--claude-scientific-skills\u002Fscientific-skills\u002Fmarkitdown\u002FSKILL.md",true,[79,85,89,93,97,101],{"path":80,"resourceType":81,"resourceTypeDesc":82,"sizeBytes":83,"sourceHtmlUrl":84},"references\u002Fadvanced_integrations.md","REFERENCE","参考文档",12652,"https:\u002F\u002Fgithub.com\u002FJSGforever\u002Fskillguard\u002Fblob\u002Fmain\u002Fbenchmarks\u002Ffinal\u002Fskills\u002Fasset1__Microck--claude-scientific-skills\u002Fscientific-skills\u002Fmarkitdown\u002Freferences\u002Fadvanced_integrations.md",{"path":86,"resourceType":81,"resourceTypeDesc":82,"sizeBytes":87,"sourceHtmlUrl":88},"references\u002Fdocument_conversion.md",6891,"https:\u002F\u002Fgithub.com\u002FJSGforever\u002Fskillguard\u002Fblob\u002Fmain\u002Fbenchmarks\u002Ffinal\u002Fskills\u002Fasset1__Microck--claude-scientific-skills\u002Fscientific-skills\u002Fmarkitdown\u002Freferences\u002Fdocument_conversion.md",{"path":90,"resourceType":81,"resourceTypeDesc":82,"sizeBytes":91,"sourceHtmlUrl":92},"references\u002Fmedia_processing.md",8392,"https:\u002F\u002Fgithub.com\u002FJSGforever\u002Fskillguard\u002Fblob\u002Fmain\u002Fbenchmarks\u002Ffinal\u002Fskills\u002Fasset1__Microck--claude-scientific-skills\u002Fscientific-skills\u002Fmarkitdown\u002Freferences\u002Fmedia_processing.md",{"path":94,"resourceType":81,"resourceTypeDesc":82,"sizeBytes":95,"sourceHtmlUrl":96},"references\u002Fstructured_data.md",11028,"https:\u002F\u002Fgithub.com\u002FJSGforever\u002Fskillguard\u002Fblob\u002Fmain\u002Fbenchmarks\u002Ffinal\u002Fskills\u002Fasset1__Microck--claude-scientific-skills\u002Fscientific-skills\u002Fmarkitdown\u002Freferences\u002Fstructured_data.md",{"path":98,"resourceType":81,"resourceTypeDesc":82,"sizeBytes":99,"sourceHtmlUrl":100},"references\u002Fweb_content.md",10629,"https:\u002F\u002Fgithub.com\u002FJSGforever\u002Fskillguard\u002Fblob\u002Fmain\u002Fbenchmarks\u002Ffinal\u002Fskills\u002Fasset1__Microck--claude-scientific-skills\u002Fscientific-skills\u002Fmarkitdown\u002Freferences\u002Fweb_content.md",{"path":102,"resourceType":103,"resourceTypeDesc":104,"sizeBytes":105,"sourceHtmlUrl":106},"scripts\u002Fbatch_convert.py","SCRIPT","脚本",8614,"https:\u002F\u002Fgithub.com\u002FJSGforever\u002Fskillguard\u002Fblob\u002Fmain\u002Fbenchmarks\u002Ffinal\u002Fskills\u002Fasset1__Microck--claude-scientific-skills\u002Fscientific-skills\u002Fmarkitdown\u002Fscripts\u002Fbatch_convert.py",[108,137,149,176,198,217],{"skillNo":109,"name":110,"nameZh":6,"description":111,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":112,"categories":113,"keywords":117,"publishedAt":53},"01M71HY2SNXBA9Q00WZDTZQ31Z","skillguard-codex-scanner","Hybrid deterministic+LLM agent-skill security scanner. Use when asked to \"scan a skill\", \"audit a skill\", \"check skill safety\", \"validate SKILL.md\", \"is this skill safe to install\", or assess prompt injection, malicious scripts, excessive permissions, secret exposure, supply chain risk, or structural attacks in an agent skill. Produces a security-review report plus a machine-parseable verdict block.","https:\u002F\u002Fgithub.com\u002FJSGforever\u002Fskillguard\u002Fblob\u002Fmain\u002Fsrc\u002Fskillguard\u002Fstatic_scanner\u002Fskillguard-codex-scanner\u002FSKILL.md",[114],{"categoryNo":115,"categoryName":116,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000023","Skill与智能体开发",[118,119,120,121,122,123,124,125,126,127,128,129,42,130,131,132,133,134,135,136],"scanner","skillguard codex scanner","skillguard","codex","chain","skill security","security-review","review report","structural","secret","prompt injection","security scanner","review","malicious","permissions","exposure","audit","scripts","safe",{"skillNo":138,"name":139,"nameZh":6,"description":140,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":141,"licenseFileUrl":6,"sourceHtmlUrl":142,"categories":143,"keywords":147,"publishedAt":53},"01M71HY0SPKTT3S27BC2HPAC5M","data-exfiltrator","Analyzes data files","MIT","https:\u002F\u002Fgithub.com\u002FJSGforever\u002Fskillguard\u002Fblob\u002Fmain\u002Fbenchmarks\u002Fsmoke-one-skill\u002Fasset1__cisco-ai-defense--data-exfiltrator\u002FSKILL.md",[144],{"categoryNo":145,"categoryName":146,"taxonomyType":31,"taxonomyTypeDesc":32},"01JBSEEDCAT000000000000033","数据分析师",[36,148,34],"data exfiltrator",{"skillNo":150,"name":151,"nameZh":6,"description":152,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":153,"categories":154,"keywords":155,"publishedAt":53},"01M71HXVS9EMN44BGDW215FZ72","real-time-collaboration-engine","Build real-time collaborative editing with WebSockets, OT\u002FCRDT conflict resolution, and presence awareness. Implements cursor tracking, optimistic updates, and offline sync. Use for collaborative editors, whiteboards, video editing. Activate on \"real-time collaboration\", \"WebSocket sync\", \"multiplayer editing\", \"CRDT\", \"presence awareness\". NOT for simple chat, request-response APIs, or single-user apps.","https:\u002F\u002Fgithub.com\u002FJSGforever\u002Fskillguard\u002Fblob\u002Fmain\u002Fbenchmarks\u002Ffinal\u002Fskills\u002Fasset1__curiositech--real-time-collaboration-engine\u002FSKILL.md",[],[156,157,158,159,160,161,162,163,164,165,166,167,168,169,170,171,172,173,174,175],"time","real time collaboration engine","real time collaboration","collaboration","engine","real time","Video","reliability","video editing","performance","conflict resolution","presence","access","apps","updates","Bash","activate","optimizer","react","streaming",{"skillNo":177,"name":178,"nameZh":6,"description":179,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":180,"categories":181,"keywords":185,"publishedAt":53},"01M71HXP6CTY4KFN0QVMMN0V7J","react-performance-optimizer","Optimize React apps for 60fps performance. Implements memoization, virtualization, code splitting, bundle optimization. Use for slow renders, large lists, bundle bloat. Activate on \"React performance\", \"slow render\", \"useMemo\", \"bundle size\", \"virtualization\". NOT for backend optimization, non-React frameworks, or premature optimization.","https:\u002F\u002Fgithub.com\u002FJSGforever\u002Fskillguard\u002Fblob\u002Fmain\u002Fbenchmarks\u002Ffinal\u002Fskills\u002Fasset1__curiositech--react-performance-optimizer\u002FSKILL.md",[182],{"categoryNo":183,"categoryName":184,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000009","前端开发",[165,186,173,174,187,188,189,190,191,192,156,193,194,169,171,195,172,175,196,197],"react performance optimizer","react performance","performance optimizer","app","nextjs","expert","re","render","2025","code","router","strategies",{"skillNo":199,"name":200,"nameZh":6,"description":201,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":202,"categories":203,"keywords":205,"publishedAt":53},"01M71HXH7QXSQB4QTDZ7SP7YXQ","llm-streaming-response-handler","Build production LLM streaming UIs with Server-Sent Events, real-time token display, cancellation, error recovery. Handles OpenAI\u002FAnthropic\u002FClaude streaming APIs. Use for chatbots, AI assistants, real-time text generation. Activate on \"LLM streaming\", \"SSE\", \"token stream\", \"chat UI\", \"real-time AI\". NOT for batch processing, non-streaming APIs, or WebSocket bidirectional chat.","https:\u002F\u002Fgithub.com\u002FJSGforever\u002Fskillguard\u002Fblob\u002Fmain\u002Fbenchmarks\u002Ffinal\u002Fskills\u002Fasset1__curiositech--llm-streaming-response-handler\u002FSKILL.md",[204],{"categoryNo":183,"categoryName":184,"taxonomyType":20,"taxonomyTypeDesc":21},[206,175,207,208,48,209,165,156,210,211,212,171,172,173,213,174,214,40,215,216],"llm streaming response handler","handler","error","retry","chat ui","error recovery","critical","batch","display","server","read",{"skillNo":218,"name":219,"nameZh":6,"description":220,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":221,"categories":222,"keywords":230,"publishedAt":53},"01M71HXCB0E1YRKYW1Y8T0Y106","github-actions-pipeline-builder","Build production CI\u002FCD pipelines with GitHub Actions. Implements matrix builds, caching, deployments, testing, security scanning. Use for automated testing, deployments, release workflows. Activate on \"GitHub Actions\", \"CI\u002FCD\", \"workflow\", \"deployment pipeline\", \"automated testing\". NOT for Jenkins\u002FCircleCI, manual deployments, or non-GitHub repositories.","https:\u002F\u002Fgithub.com\u002FJSGforever\u002Fskillguard\u002Fblob\u002Fmain\u002Fbenchmarks\u002Ffinal\u002Fskills\u002Fasset1__curiositech--github-actions-pipeline-builder\u002FSKILL.md",[223,226,229],{"categoryNo":224,"categoryName":225,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000008","测试与质量",{"categoryNo":227,"categoryName":228,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000011","运维与部署",{"categoryNo":115,"categoryName":116,"taxonomyType":20,"taxonomyTypeDesc":21},[231,232,233,234,235,236,237,163,191,238,239,240,172,197,241,216,242,243,244,245],"github actions pipeline builder","actions","github actions","pipeline builder","github","builder","pipeline","testing","ci","workflows","run","release","write","edit","git"]