[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6XEBTVGE86HTG043Y09G4XV":3,"skill-same:01M6XEBTVGE86HTG043Y09G4XV":74},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":15,"categories":16,"keywords":22,"publishedAt":42,"linkOnly":43,"markdownContent":44,"markdownBody":45,"frontMatter":46,"refName":47,"commitSha":48,"skillDirectory":49,"forksCount":13,"repositoryHtmlUrl":50,"repositoryHomepageUrl":6,"ownerHtmlUrl":51,"ownerBlogUrl":6,"ownerDescription":52,"updatedAt":53,"install":54,"resources":67},"01M6XEBTVGE86HTG043Y09G4XV","marker",null,"Convert PDF documents to Markdown using marker_single. Use when Claude needs to extract text content from PDFs while preserving LaTeX formulas, equations, and document structure. Ideal for academic papers and technical documents containing mathematical notation.","Waaaalnut\u002Fskillsbench","Waaaalnut","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F103995656?v=4","01M6XCS9K1V51EY3JMB7DGMX24","01M6XCS9Q4WPW88W62C55G1H44",0,"Apache-2.0","https:\u002F\u002Fgithub.com\u002FWaaaalnut\u002Fskillsbench\u002Fblob\u002Fmain\u002Ftasks\u002Flatex-formula-extraction\u002Fenvironment\u002Fskills\u002Fmarker\u002FSKILL.md",[17],{"categoryNo":18,"categoryName":19,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000002","文档处理","SCENARIO","使用场景",[5,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41],"structure","when","single","for","notation","papers","formulas","Mathematical","Academic","PDF","document","use","extract","technical","text","convert","markdown","content","documents","2026-11-10 10:12:30",false,"---\nname: marker\ndescription: Convert PDF documents to Markdown using marker_single. Use when Claude needs to extract text content from PDFs while preserving LaTeX formulas, equations, and document structure. Ideal for academic papers and technical documents containing mathematical notation.\n---\n\n# Marker PDF-to-Markdown Converter\n\nConvert PDFs to Markdown while preserving LaTeX formulas and document structure. Uses the `marker_single` CLI from the marker-pdf package.\n\n## Dependencies\n- `marker_single` on PATH (`pip install marker-pdf` if missing)\n- Python 3.10+ (available in the task image)\n\n## Quick Start\n\n```python\nfrom scripts.marker_to_markdown import pdf_to_markdown\n\nmarkdown_text = pdf_to_markdown(\"paper.pdf\")\nprint(markdown_text)\n```\n\n## Python API\n\n- `pdf_to_markdown(pdf_path, *, timeout=600, cleanup=True) -> str`\n  - Runs `marker_single --output_format markdown --disable_image_extraction`\n  - `cleanup=True`: use a temp directory and delete after reading the Markdown\n  - `cleanup=False`: keep outputs in `\u003Cpdf_stem>_marker\u002F` next to the PDF\n  - Exceptions: `FileNotFoundError` if the PDF is missing, `RuntimeError` for marker failures, `TimeoutError` if it exceeds the timeout\n- Tips: bump `timeout` for large PDFs; set `cleanup=False` to inspect intermediate files\n\n## Command-Line Usage\n\n```bash\n# Basic conversion (prints markdown to stdout)\npython scripts\u002Fmarker_to_markdown.py paper.pdf\n\n# Keep temporary files\npython scripts\u002Fmarker_to_markdown.py paper.pdf --keep-temp\n\n# Custom timeout\npython scripts\u002Fmarker_to_markdown.py paper.pdf --timeout 600\n```\n\n## Output Locations\n- `cleanup=True`: outputs stored in a temporary directory and removed automatically\n- `cleanup=False`: outputs saved to `\u003Cpdf_stem>_marker\u002F`; markdown lives at `\u003Cpdf_stem>_marker\u002F\u003Cpdf_stem>\u002F\u003Cpdf_stem>.md` when present (otherwise the first `.md` file is used)\n\n## Troubleshooting\n- `marker_single` not found: install `marker-pdf` or ensure the CLI is on PATH\n- No Markdown output: re-run with `--keep-temp`\u002F`cleanup=False` and check `stdout`\u002F`stderr` saved in the output folder\n","# Marker PDF-to-Markdown Converter\n\nConvert PDFs to Markdown while preserving LaTeX formulas and document structure. Uses the `marker_single` CLI from the marker-pdf package.\n\n## Dependencies\n- `marker_single` on PATH (`pip install marker-pdf` if missing)\n- Python 3.10+ (available in the task image)\n\n## Quick Start\n\n```python\nfrom scripts.marker_to_markdown import pdf_to_markdown\n\nmarkdown_text = pdf_to_markdown(\"paper.pdf\")\nprint(markdown_text)\n```\n\n## Python API\n\n- `pdf_to_markdown(pdf_path, *, timeout=600, cleanup=True) -> str`\n  - Runs `marker_single --output_format markdown --disable_image_extraction`\n  - `cleanup=True`: use a temp directory and delete after reading the Markdown\n  - `cleanup=False`: keep outputs in `\u003Cpdf_stem>_marker\u002F` next to the PDF\n  - Exceptions: `FileNotFoundError` if the PDF is missing, `RuntimeError` for marker failures, `TimeoutError` if it exceeds the timeout\n- Tips: bump `timeout` for large PDFs; set `cleanup=False` to inspect intermediate files\n\n## Command-Line Usage\n\n```bash\n# Basic conversion (prints markdown to stdout)\npython scripts\u002Fmarker_to_markdown.py paper.pdf\n\n# Keep temporary files\npython scripts\u002Fmarker_to_markdown.py paper.pdf --keep-temp\n\n# Custom timeout\npython scripts\u002Fmarker_to_markdown.py paper.pdf --timeout 600\n```\n\n## Output Locations\n- `cleanup=True`: outputs stored in a temporary directory and removed automatically\n- `cleanup=False`: outputs saved to `\u003Cpdf_stem>_marker\u002F`; markdown lives at `\u003Cpdf_stem>_marker\u002F\u003Cpdf_stem>\u002F\u003Cpdf_stem>.md` when present (otherwise the first `.md` file is used)\n\n## Troubleshooting\n- `marker_single` not found: install `marker-pdf` or ensure the CLI is on PATH\n- No Markdown output: re-run with `--keep-temp`\u002F`cleanup=False` and check `stdout`\u002F`stderr` saved in the output folder\n",{"name":5,"description":7},"main","7eeb258ada72b7f58119b0e7a2c00ea89d9beedd","tasks\u002Flatex-formula-extraction\u002Fenvironment\u002Fskills\u002Fmarker","https:\u002F\u002Fgithub.com\u002FWaaaalnut\u002Fskillsbench","https:\u002F\u002Fgithub.com\u002FWaaaalnut","student of Zhejiang University","2026-04-21 23:16:23",{"source":8,"skillName":5,"commands":55,"prompt":65,"zipAvailable":66},[56,59,62],{"tool":57,"command":58},"npx","npx skills add Waaaalnut\u002Fskillsbench --skill marker",{"tool":60,"command":61},"bunx","bunx skills add Waaaalnut\u002Fskillsbench --skill marker",{"tool":63,"command":64},"pnpm","pnpm dlx skills add Waaaalnut\u002Fskillsbench --skill marker","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FWaaaalnut\u002Fskillsbench\u002Fblob\u002Fmain\u002Ftasks\u002Flatex-formula-extraction\u002Fenvironment\u002Fskills\u002Fmarker\u002FSKILL.md",true,[68],{"path":69,"resourceType":70,"resourceTypeDesc":71,"sizeBytes":72,"sourceHtmlUrl":73},"scripts\u002Fmarker_to_markdown.py","SCRIPT","脚本",4156,"https:\u002F\u002Fgithub.com\u002FWaaaalnut\u002Fskillsbench\u002Fblob\u002Fmain\u002Ftasks\u002Flatex-formula-extraction\u002Fenvironment\u002Fskills\u002Fmarker\u002Fscripts\u002Fmarker_to_markdown.py",[75,89,103,127,149,167],{"skillNo":76,"name":77,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":78,"categories":79,"keywords":85,"publishedAt":42},"01M6XEWMJ6VY3ZC53MPDCPG3GH","data-reconciliation","https:\u002F\u002Fgithub.com\u002FWaaaalnut\u002Fskillsbench\u002Fblob\u002Fmain\u002Ftasks\u002Fxlsx-recover-data\u002Fenvironment\u002Fskills\u002Fdata-reconciliation\u002FSKILL.md",[80],{"categoryNo":81,"categoryName":82,"taxonomyType":83,"taxonomyTypeDesc":84},"01JBSEEDCAT000000000000033","数据分析师","PROFESSION","适用职业",[86,87,88],"data reconciliation","reconciliation","data",{"skillNo":90,"name":91,"nameZh":6,"description":92,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":93,"categories":94,"keywords":95,"publishedAt":42},"01M6XEW8MNPMF1KRXV6ATGFRQF","speech-to-text","Transcribe video to timestamped text using Whisper tiny model (pre-installed).","https:\u002F\u002Fgithub.com\u002FWaaaalnut\u002Fskillsbench\u002Fblob\u002Fmain\u002Ftasks\u002Fvideo-tutorial-indexer\u002Fenvironment\u002Fskills\u002Fspeech-to-text\u002FSKILL.md",[],[96,37,97,98,99,100,101,102],"speech","speech to text","transcribe video","whisper","model","Video","transcribe",{"skillNo":104,"name":105,"nameZh":6,"description":106,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":107,"categories":108,"keywords":112,"publishedAt":42},"01M6XEW3FQZP0T1RKQQJFXVY9T","video-processor","Process videos by removing segments and concatenating remaining parts. Use when you need to remove detected pauses\u002Fopenings from videos, create highlight reels, or batch process segment removals using ffmpeg filter_complex.","https:\u002F\u002Fgithub.com\u002FWaaaalnut\u002Fskillsbench\u002Fblob\u002Fmain\u002Ftasks\u002Fvideo-silence-remover\u002Fenvironment\u002Fskills\u002Fvideo-processor\u002FSKILL.md",[109],{"categoryNo":110,"categoryName":111,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000016","图像与多媒体",[101,113,114,115,116,117,24,118,119,120,121,122,123,124,125,34,126],"processor","video processor","batch","create","reels","parts","segments","process","videos","you","segment","filter","ffmpeg","remove",{"skillNo":128,"name":129,"nameZh":6,"description":130,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":131,"categories":132,"keywords":134,"publishedAt":42},"01M6XEVXJ5KZ0NTY3XZKRY4AS1","silence-detector","Detect initial silence segments in audio\u002Fvideo using energy-based analysis. Use when you need to find low-energy periods at the start of recordings (title slides, setup time, pre-roll silence).","https:\u002F\u002Fgithub.com\u002FWaaaalnut\u002Fskillsbench\u002Fblob\u002Fmain\u002Ftasks\u002Fvideo-silence-remover\u002Fenvironment\u002Fskills\u002Fsilence-detector\u002FSKILL.md",[133],{"categoryNo":110,"categoryName":111,"taxonomyType":20,"taxonomyTypeDesc":21},[135,136,137,138,24,122,139,140,141,142,143,119,144,145,101,146,147,148,34],"detector","silence detector","title","slides","time","energy","at","recordings","detect","find","Audio","analysis","start","setup",{"skillNo":150,"name":151,"nameZh":6,"description":152,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":153,"categories":154,"keywords":155,"publishedAt":42},"01M6XEVT3NGRN1FT7JPMAPXS6M","segment-combiner","Combine multiple segment detection results into a unified list. Use when you need to merge segments from different detectors, prepare removal lists for video processing, or consolidate detection outputs.","https:\u002F\u002Fgithub.com\u002FWaaaalnut\u002Fskillsbench\u002Fblob\u002Fmain\u002Ftasks\u002Fvideo-silence-remover\u002Fenvironment\u002Fskills\u002Fsegment-combiner\u002FSKILL.md",[],[123,156,101,157,158,159,160,26,24,161,162,119,122,163,164,34,165,166],"segment combiner","detection","prepare","merge","video processing","outputs","combine","processing","consolidate","results","list",{"skillNo":168,"name":169,"nameZh":6,"description":170,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":171,"categories":172,"keywords":176,"publishedAt":42},"01M6XEVMPVASGS2KX86QK4FMT7","report-generator","Generate compression reports for video processing. Use when you need to create structured JSON reports with duration statistics, compression ratios, and segment details after video processing.","https:\u002F\u002Fgithub.com\u002FWaaaalnut\u002Fskillsbench\u002Fblob\u002Fmain\u002Ftasks\u002Fvideo-silence-remover\u002Fenvironment\u002Fskills\u002Freport-generator\u002FSKILL.md",[173],{"categoryNo":174,"categoryName":175,"taxonomyType":83,"taxonomyTypeDesc":84},"01JBSEEDCAT000000000000034","行政与办公人员",[177,178,179,123,24,26,122,180,163,181,182,183,34,160,184,101,185,186,116],"generator","report generator","report","with","statistics","structured","reports","json","compression","generate"]