[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6GEHCWC7N8C3XC5FMBMHT0P":3,"skill-same:01M6GEHCWC7N8C3XC5FMBMHT0P":89},{"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":31,"publishedAt":52,"linkOnly":53,"markdownContent":54,"markdownBody":55,"frontMatter":56,"refName":67,"commitSha":68,"skillDirectory":69,"forksCount":70,"repositoryHtmlUrl":71,"repositoryHomepageUrl":6,"ownerHtmlUrl":72,"ownerBlogUrl":6,"ownerDescription":73,"updatedAt":74,"install":75,"resources":88},"01M6GEHCWC7N8C3XC5FMBMHT0P","pptx-author",null,"Build PowerPoint decks headless with python-pptx. Pairs with excel-author for model-backed decks where every number traces to a workbook cell. Use for pitch decks, IC memos, earnings notes.","zapabob\u002FSkills","zapabob","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F130830376?v=4","01M6DBMYZAGRTFQDSQYW3W764P","峯岸 亮","01M6DBMZ3GKDSJ01NZ9XTZD7JD",2,"Apache-2.0","https:\u002F\u002Fgithub.com\u002Fzapabob\u002FSkills\u002Fblob\u002Fmain\u002Farchive\u002Fskill-md-reviewed\u002Fsha256\u002Fc9\u002Fc9554c83fa5ad0b7e0c1700c2ac8eed6f69979198019464428bc45dd784b5adc\u002FSKILL.md",[18,23,26],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000003","演示文稿","SCENARIO","使用场景",{"categoryNo":24,"categoryName":25,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000004","电子表格",{"categoryNo":27,"categoryName":28,"taxonomyType":29,"taxonomyTypeDesc":30},"01JBSEEDCAT000000000000034","行政与办公人员","PROFESSION","适用职业",[32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48,49,50,51],"pptx author","pptx","use","headless","number","with","pitch","nous research","cell","python-pptx","build","model","finance","powerpoint","notes","windows","research","linux","python","xlsx","2026-11-10 10:12:30",false,"---\r\nname: pptx-author\r\ndescription: Build PowerPoint decks headless with python-pptx. Pairs with excel-author for model-backed decks where every number traces to a workbook cell. Use for pitch decks, IC memos, earnings notes.\r\nversion: 1.0.0\r\nauthor: Anthropic (adapted by Nous Research)\r\nlicense: Apache-2.0\r\nplatforms: [linux, macos, windows]\r\nmetadata:\r\n  hermes:\r\n    tags: [powerpoint, pptx, python-pptx, presentation, finance]\r\n    related_skills: [excel-author, powerpoint]\r\n---\r\n\r\n# pptx-author\r\n\r\nProduce a .pptx file on disk using `python-pptx`. Use when you need to deliver a deck as a file artifact, not drive a live PowerPoint session.\r\n\r\nAdapted from Anthropic's `pptx-author` and `pitch-deck` skills in [anthropics\u002Ffinancial-services](https:\u002F\u002Fgithub.com\u002Fanthropics\u002Ffinancial-services). The MCP \u002F Office-JS branches of the originals are dropped — this assumes headless Python.\r\n\r\nFor the broader, already-shipped PowerPoint authoring skill (slides, speaker notes, embeds, media), see the built-in `powerpoint` skill. This skill is a lighter-weight pattern tuned for model-backed decks (pitch decks, IC memos, earnings notes) where every number must trace to a source workbook.\r\n\r\n## Output contract\r\n\r\n- Write to `.\u002Fout\u002F\u003Cname>.pptx`. Create `.\u002Fout\u002F` if it does not exist.\r\n- Return the relative path in your final message.\r\n\r\n## Setup\r\n\r\n```bash\r\npip install \"python-pptx>=0.6\"\r\n```\r\n\r\n## Core conventions\r\n\r\n### One idea per slide\r\nTitle states the takeaway; body supports it. A slide titled \"Q3 Revenue\" is weak; \"Revenue growth accelerated to 14% Y\u002FY in Q3\" is strong.\r\n\r\n### Every number traces to the model\r\nIf a figure on a slide came from `.\u002Fout\u002Fmodel.xlsx`, footnote the sheet and cell.\r\n\r\n```\r\nRevenue: $1,250M  (Source: model.xlsx, Inputs!C3)\r\n```\r\n\r\nNever transcribe numbers from memory or from a summary — open the workbook, read the named range, and bind the deck value to it programmatically when you can.\r\n\r\n### Use the firm template when one is mounted\r\nIf `.\u002Ftemplates\u002Ffirm-template.pptx` exists, load it so the deck inherits branded colors, fonts, and master layouts.\r\n\r\n```python\r\nfrom pptx import Presentation\r\nfrom pathlib import Path\r\n\r\ntemplate = Path(\".\u002Ftemplates\u002Ffirm-template.pptx\")\r\nprs = Presentation(str(template)) if template.exists() else Presentation()\r\n```\r\n\r\n### Charts: PNG-from-model beats native pptx charts\r\nWhen fidelity matters (the model's chart styling must match the deck exactly), render the chart to PNG from the source workbook and embed the image. Native `pptx.chart` charts are fragile and often don't match firm conventions.\r\n\r\n```python\r\nfrom pptx.util import Inches\r\nslide.shapes.add_picture(\".\u002Fout\u002Fcharts\u002Ffootball_field.png\",\r\n                         Inches(1), Inches(2),\r\n                         width=Inches(8))\r\n```\r\n\r\n### No external sends\r\nThis skill writes a file. It never emails, uploads, or posts. Orchestration layers handle delivery.\r\n\r\n## Skeleton\r\n\r\n```python\r\nfrom pptx import Presentation\r\nfrom pptx.util import Inches, Pt\r\nfrom pptx.dml.color import RGBColor\r\nfrom pathlib import Path\r\n\r\ntemplate = Path(\".\u002Ftemplates\u002Ffirm-template.pptx\")\r\nprs = Presentation(str(template)) if template.exists() else Presentation()\r\n\r\n# Title slide\r\nslide = prs.slides.add_slide(prs.slide_layouts[0])\r\nslide.shapes.title.text = \"Project Aurora — Strategic Alternatives\"\r\nslide.placeholders[1].text = \"Preliminary Discussion Materials\"\r\n\r\n# Valuation summary slide (title-only layout)\r\nslide = prs.slides.add_slide(prs.slide_layouts[5])\r\nslide.shapes.title.text = \"Valuation implies $38–$52 per share across methodologies\"\r\n\r\n# Add a table bound to model outputs\r\nrows, cols = 5, 4\r\ntbl_shape = slide.shapes.add_table(rows, cols,\r\n                                   Inches(0.5), Inches(1.5),\r\n                                   Inches(9), Inches(3))\r\ntbl = tbl_shape.table\r\nheaders = [\"Methodology\", \"Low ($)\", \"Mid ($)\", \"High ($)\"]\r\nfor c, h in enumerate(headers):\r\n    tbl.cell(0, c).text = h\r\n\r\n# In a real deck, read these from the model workbook with openpyxl\r\ndata = [\r\n    (\"Trading comps\",     \"35\", \"41\", \"48\"),\r\n    (\"Precedent M&A\",     \"39\", \"45\", \"52\"),\r\n    (\"DCF (base)\",        \"36\", \"43\", \"51\"),\r\n    (\"LBO (10% IRR)\",     \"33\", \"38\", \"44\"),\r\n]\r\nfor r, row in enumerate(data, start=1):\r\n    for c, val in enumerate(row):\r\n        tbl.cell(r, c).text = val\r\n\r\n# Embed a chart rendered from the model\r\nslide = prs.slides.add_slide(prs.slide_layouts[5])\r\nslide.shapes.title.text = \"Football field — current price $42\"\r\nslide.shapes.add_picture(\".\u002Fout\u002Fcharts\u002Ffootball_field.png\",\r\n                         Inches(1), Inches(1.8), width=Inches(8))\r\n\r\nPath(\".\u002Fout\").mkdir(exist_ok=True)\r\nprs.save(\".\u002Fout\u002Fpitch-aurora.pptx\")\r\n```\r\n\r\n## Binding deck numbers to the source workbook\r\n\r\nRead named ranges or specific cells from your Excel model so deck numbers never drift.\r\n\r\n```python\r\nfrom openpyxl import load_workbook\r\n\r\nwb = load_workbook(\".\u002Fout\u002Fmodel.xlsx\", data_only=True)\r\ndef nr(name):\r\n    \"\"\"Resolve a named range to its current computed value.\"\"\"\r\n    rng = wb.defined_names[name]\r\n    sheet, coord = next(rng.destinations)\r\n    return wb[sheet][coord].value\r\n\r\nrevenue_fy24 = nr(\"RevenueFY24\")\r\nimplied_mid  = nr(\"ImpliedSharePriceBase\")\r\n```\r\n\r\nThen build deck content using those values:\r\n```python\r\nslide.shapes.title.text = f\"Implied share price of ${implied_mid:.2f} (base case)\"\r\n```\r\n\r\nRemember to recalculate the workbook before reading it — openpyxl only sees computed values if something has already calculated the sheet. Run the recalc helper in the `excel-author` skill first, or open\u002Fsave through a real Excel session.\r\n\r\n## Slide-type checklist for pitch decks\r\n\r\nA typical banking pitch deck follows this structure. Not prescriptive, but useful as a starting skeleton:\r\n\r\n1. Cover \u002F title\r\n2. Disclaimer\r\n3. Table of contents\r\n4. Situation overview\r\n5. Company snapshot (the target)\r\n6. Market \u002F sector context\r\n7. Valuation summary (football field) — the money slide\r\n8. Trading comps detail\r\n9. Precedent transactions detail\r\n10. DCF summary\r\n11. Illustrative LBO \u002F sponsor case\r\n12. Process considerations\r\n13. Appendix\r\n\r\n## When NOT to use this skill\r\n\r\n- Users in a live PowerPoint session with an Office MCP available — drive their live doc instead.\r\n- Non-financial slideware (quarterly all-hands, marketing decks) — use the broader `powerpoint` skill.\r\n- Decks with heavy animation, transitions, or speaker notes — use the broader `powerpoint` skill.\r\n\r\n## Attribution\r\n\r\nConventions adapted from Anthropic's Claude for Financial Services plugin suite, Apache-2.0 licensed. Original: https:\u002F\u002Fgithub.com\u002Fanthropics\u002Ffinancial-services\u002Ftree\u002Fmain\u002Fplugins\u002Fagent-plugins\u002Fpitch-agent\u002Fskills\u002Fpptx-author\r\n","# pptx-author\r\n\r\nProduce a .pptx file on disk using `python-pptx`. Use when you need to deliver a deck as a file artifact, not drive a live PowerPoint session.\r\n\r\nAdapted from Anthropic's `pptx-author` and `pitch-deck` skills in [anthropics\u002Ffinancial-services](https:\u002F\u002Fgithub.com\u002Fanthropics\u002Ffinancial-services). The MCP \u002F Office-JS branches of the originals are dropped — this assumes headless Python.\r\n\r\nFor the broader, already-shipped PowerPoint authoring skill (slides, speaker notes, embeds, media), see the built-in `powerpoint` skill. This skill is a lighter-weight pattern tuned for model-backed decks (pitch decks, IC memos, earnings notes) where every number must trace to a source workbook.\r\n\r\n## Output contract\r\n\r\n- Write to `.\u002Fout\u002F\u003Cname>.pptx`. Create `.\u002Fout\u002F` if it does not exist.\r\n- Return the relative path in your final message.\r\n\r\n## Setup\r\n\r\n```bash\r\npip install \"python-pptx>=0.6\"\r\n```\r\n\r\n## Core conventions\r\n\r\n### One idea per slide\r\nTitle states the takeaway; body supports it. A slide titled \"Q3 Revenue\" is weak; \"Revenue growth accelerated to 14% Y\u002FY in Q3\" is strong.\r\n\r\n### Every number traces to the model\r\nIf a figure on a slide came from `.\u002Fout\u002Fmodel.xlsx`, footnote the sheet and cell.\r\n\r\n```\r\nRevenue: $1,250M  (Source: model.xlsx, Inputs!C3)\r\n```\r\n\r\nNever transcribe numbers from memory or from a summary — open the workbook, read the named range, and bind the deck value to it programmatically when you can.\r\n\r\n### Use the firm template when one is mounted\r\nIf `.\u002Ftemplates\u002Ffirm-template.pptx` exists, load it so the deck inherits branded colors, fonts, and master layouts.\r\n\r\n```python\r\nfrom pptx import Presentation\r\nfrom pathlib import Path\r\n\r\ntemplate = Path(\".\u002Ftemplates\u002Ffirm-template.pptx\")\r\nprs = Presentation(str(template)) if template.exists() else Presentation()\r\n```\r\n\r\n### Charts: PNG-from-model beats native pptx charts\r\nWhen fidelity matters (the model's chart styling must match the deck exactly), render the chart to PNG from the source workbook and embed the image. Native `pptx.chart` charts are fragile and often don't match firm conventions.\r\n\r\n```python\r\nfrom pptx.util import Inches\r\nslide.shapes.add_picture(\".\u002Fout\u002Fcharts\u002Ffootball_field.png\",\r\n                         Inches(1), Inches(2),\r\n                         width=Inches(8))\r\n```\r\n\r\n### No external sends\r\nThis skill writes a file. It never emails, uploads, or posts. Orchestration layers handle delivery.\r\n\r\n## Skeleton\r\n\r\n```python\r\nfrom pptx import Presentation\r\nfrom pptx.util import Inches, Pt\r\nfrom pptx.dml.color import RGBColor\r\nfrom pathlib import Path\r\n\r\ntemplate = Path(\".\u002Ftemplates\u002Ffirm-template.pptx\")\r\nprs = Presentation(str(template)) if template.exists() else Presentation()\r\n\r\n# Title slide\r\nslide = prs.slides.add_slide(prs.slide_layouts[0])\r\nslide.shapes.title.text = \"Project Aurora — Strategic Alternatives\"\r\nslide.placeholders[1].text = \"Preliminary Discussion Materials\"\r\n\r\n# Valuation summary slide (title-only layout)\r\nslide = prs.slides.add_slide(prs.slide_layouts[5])\r\nslide.shapes.title.text = \"Valuation implies $38–$52 per share across methodologies\"\r\n\r\n# Add a table bound to model outputs\r\nrows, cols = 5, 4\r\ntbl_shape = slide.shapes.add_table(rows, cols,\r\n                                   Inches(0.5), Inches(1.5),\r\n                                   Inches(9), Inches(3))\r\ntbl = tbl_shape.table\r\nheaders = [\"Methodology\", \"Low ($)\", \"Mid ($)\", \"High ($)\"]\r\nfor c, h in enumerate(headers):\r\n    tbl.cell(0, c).text = h\r\n\r\n# In a real deck, read these from the model workbook with openpyxl\r\ndata = [\r\n    (\"Trading comps\",     \"35\", \"41\", \"48\"),\r\n    (\"Precedent M&A\",     \"39\", \"45\", \"52\"),\r\n    (\"DCF (base)\",        \"36\", \"43\", \"51\"),\r\n    (\"LBO (10% IRR)\",     \"33\", \"38\", \"44\"),\r\n]\r\nfor r, row in enumerate(data, start=1):\r\n    for c, val in enumerate(row):\r\n        tbl.cell(r, c).text = val\r\n\r\n# Embed a chart rendered from the model\r\nslide = prs.slides.add_slide(prs.slide_layouts[5])\r\nslide.shapes.title.text = \"Football field — current price $42\"\r\nslide.shapes.add_picture(\".\u002Fout\u002Fcharts\u002Ffootball_field.png\",\r\n                         Inches(1), Inches(1.8), width=Inches(8))\r\n\r\nPath(\".\u002Fout\").mkdir(exist_ok=True)\r\nprs.save(\".\u002Fout\u002Fpitch-aurora.pptx\")\r\n```\r\n\r\n## Binding deck numbers to the source workbook\r\n\r\nRead named ranges or specific cells from your Excel model so deck numbers never drift.\r\n\r\n```python\r\nfrom openpyxl import load_workbook\r\n\r\nwb = load_workbook(\".\u002Fout\u002Fmodel.xlsx\", data_only=True)\r\ndef nr(name):\r\n    \"\"\"Resolve a named range to its current computed value.\"\"\"\r\n    rng = wb.defined_names[name]\r\n    sheet, coord = next(rng.destinations)\r\n    return wb[sheet][coord].value\r\n\r\nrevenue_fy24 = nr(\"RevenueFY24\")\r\nimplied_mid  = nr(\"ImpliedSharePriceBase\")\r\n```\r\n\r\nThen build deck content using those values:\r\n```python\r\nslide.shapes.title.text = f\"Implied share price of ${implied_mid:.2f} (base case)\"\r\n```\r\n\r\nRemember to recalculate the workbook before reading it — openpyxl only sees computed values if something has already calculated the sheet. Run the recalc helper in the `excel-author` skill first, or open\u002Fsave through a real Excel session.\r\n\r\n## Slide-type checklist for pitch decks\r\n\r\nA typical banking pitch deck follows this structure. Not prescriptive, but useful as a starting skeleton:\r\n\r\n1. Cover \u002F title\r\n2. Disclaimer\r\n3. Table of contents\r\n4. Situation overview\r\n5. Company snapshot (the target)\r\n6. Market \u002F sector context\r\n7. Valuation summary (football field) — the money slide\r\n8. Trading comps detail\r\n9. Precedent transactions detail\r\n10. DCF summary\r\n11. Illustrative LBO \u002F sponsor case\r\n12. Process considerations\r\n13. Appendix\r\n\r\n## When NOT to use this skill\r\n\r\n- Users in a live PowerPoint session with an Office MCP available — drive their live doc instead.\r\n- Non-financial slideware (quarterly all-hands, marketing decks) — use the broader `powerpoint` skill.\r\n- Decks with heavy animation, transitions, or speaker notes — use the broader `powerpoint` skill.\r\n\r\n## Attribution\r\n\r\nConventions adapted from Anthropic's Claude for Financial Services plugin suite, Apache-2.0 licensed. Original: https:\u002F\u002Fgithub.com\u002Fanthropics\u002Ffinancial-services\u002Ftree\u002Fmain\u002Fplugins\u002Fagent-plugins\u002Fpitch-agent\u002Fskills\u002Fpptx-author\r\n",{"name":5,"author":57,"license":15,"version":58,"metadata":59,"platforms":65,"description":7},"Anthropic (adapted by Nous Research)","1.0.0",{"hermes":60},{"tags":61,"related_skills":63},[45,33,41,62,44],"presentation",[64,45],"excel-author",[49,66,47],"macos","main","0d1434f89f4bc6b07e9d272accd8c1013768820f","archive\u002Fskill-md-reviewed\u002Fsha256\u002Fc9\u002Fc9554c83fa5ad0b7e0c1700c2ac8eed6f69979198019464428bc45dd784b5adc",0,"https:\u002F\u002Fgithub.com\u002Fzapabob\u002FSkills","https:\u002F\u002Fgithub.com\u002Fzapabob","The Open University of JAPAN　2019-now\r\n\r\nTokyo University of Science　2007-2010","2026-10-26 16:29:01",{"source":8,"skillName":5,"commands":76,"prompt":86,"zipAvailable":87},[77,80,83],{"tool":78,"command":79},"npx","npx skills add zapabob\u002FSkills --skill pptx-author",{"tool":81,"command":82},"bunx","bunx skills add zapabob\u002FSkills --skill pptx-author",{"tool":84,"command":85},"pnpm","pnpm dlx skills add zapabob\u002FSkills --skill pptx-author","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fzapabob\u002FSkills\u002Fblob\u002Fmain\u002Farchive\u002Fskill-md-reviewed\u002Fsha256\u002Fc9\u002Fc9554c83fa5ad0b7e0c1700c2ac8eed6f69979198019464428bc45dd784b5adc\u002FSKILL.md",true,[],[90,122,157,182,209,225],{"skillNo":91,"name":92,"nameZh":6,"description":93,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":94,"licenseFileUrl":6,"sourceHtmlUrl":95,"categories":96,"keywords":106,"publishedAt":52},"01M6GJTE1GESGGF9K028Y7753E","xurl","X\u002FTwitter via xurl CLI: post, search, DM, media, v2 API.","MIT","https:\u002F\u002Fgithub.com\u002Fzapabob\u002FSkills\u002Fblob\u002Fmain\u002Fregistry\u002Fskills\u002Fxurl\u002Fvariants\u002Fhermes-agent\u002FSKILL.md",[97,100,103],{"categoryNo":98,"categoryName":99,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000010","后端与接口",{"categoryNo":101,"categoryName":102,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发",{"categoryNo":104,"categoryName":105,"taxonomyType":29,"taxonomyTypeDesc":30},"01JBSEEDCAT000000000000030","开发工程师",[92,107,66,108,109,49,47,110,111,112,113,114,115,116,117,118,67,119,120,121],"openclaw","cli","github","official","search","https","social-media","api","Media","hermes","hermes agent","twitter","social","via","post",{"skillNo":123,"name":124,"nameZh":6,"description":125,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":94,"licenseFileUrl":6,"sourceHtmlUrl":126,"categories":127,"keywords":139,"publishedAt":52},"01M6GJT8S1PXQ8WPXT1HSNBWH2","writing-plans","Write implementation plans: bite-sized tasks, paths, code.","https:\u002F\u002Fgithub.com\u002Fzapabob\u002FSkills\u002Fblob\u002Fmain\u002Fregistry\u002Fskills\u002Fwriting-plans\u002Fvariants\u002Fhermes-agent\u002FSKILL.md",[128,131,134,135,136],{"categoryNo":129,"categoryName":130,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000015","视觉设计",{"categoryNo":132,"categoryName":133,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000018","写作与文案",{"categoryNo":101,"categoryName":102,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":104,"categoryName":105,"taxonomyType":29,"taxonomyTypeDesc":30},{"categoryNo":137,"categoryName":138,"taxonomyType":29,"taxonomyTypeDesc":30},"01JBSEEDCAT000000000000036","内容创作者",[140,141,142,143,66,144,49,145,47,146,147,148,149,150,151,152,153,154,155,156],"writing","writing plans","plans","design","review","workflow","documentation","tasks","development","code","planning","code-review","subagent","write","superpowers","paths","test-driven-development",{"skillNo":158,"name":159,"nameZh":6,"description":160,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":94,"licenseFileUrl":6,"sourceHtmlUrl":161,"categories":162,"keywords":166,"publishedAt":52},"01M6GJST0H5X7WHBJ3BZK0DVKH","whisper","OpenAI's general-purpose speech recognition model. Supports 99 languages, transcription, translation to English, and language identification. Six model sizes from tiny (39M params) to large (1550M params). Use for speech-to-text, podcast transcription, or multilingual audio processing. Best for robust, multilingual ASR.","https:\u002F\u002Fgithub.com\u002Fzapabob\u002FSkills\u002Fblob\u002Fmain\u002Fregistry\u002Fskills\u002Fwhisper\u002Fvariants\u002Fhermes-agent-optional\u002FSKILL.md",[163],{"categoryNo":164,"categoryName":165,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000016","图像与多媒体",[159,66,49,167,168,169,170,171,172,173,43,174,34,175,176,177,178,179,180,181],"openai","speech","multimodal","Transformers","ASR","Audio","text","speech recognition","general","multilingual","translation","english","identification","processing","Audio Processing",{"skillNo":183,"name":184,"nameZh":6,"description":185,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":94,"licenseFileUrl":6,"sourceHtmlUrl":186,"categories":187,"keywords":191,"publishedAt":52},"01M6GJSMRQ8EETZTYMG72P70EA","weights-and-biases","W&B: log ML experiments, sweeps, model registry, dashboards.","https:\u002F\u002Fgithub.com\u002Fzapabob\u002FSkills\u002Fblob\u002Fmain\u002Fregistry\u002Fskills\u002Fweights-and-biases\u002Fvariants\u002Fhermes-agent\u002FSKILL.md",[188],{"categoryNo":189,"categoryName":190,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000013","分析与可视化",[192,66,193,194,47,195,196,197,198,199,200,43,201,202,203,204,205,206,207,208],"weights and biases","tensorflow","experiments","pytorch","visualization","registry","real-time","tuning","dashboards","experiment","log","time","Experiment Tracking","Model Registry","Hyperparameter Tuning","WandB","Real-Time Visualization",{"skillNo":210,"name":211,"nameZh":6,"description":212,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":94,"licenseFileUrl":6,"sourceHtmlUrl":213,"categories":214,"keywords":216,"publishedAt":52},"01M6GJS19KDPRY112JTR326S06","watchers","Poll RSS, JSON APIs, and GitHub with watermark dedup.","https:\u002F\u002Fgithub.com\u002Fzapabob\u002FSkills\u002Fblob\u002Fmain\u002Fregistry\u002Fskills\u002Fwatchers\u002Fvariants\u002Fhermes-agent-optional\u002FSKILL.md",[215],{"categoryNo":101,"categoryName":102,"taxonomyType":21,"taxonomyTypeDesc":22},[211,66,217,109,49,218,219,220,221,222,223,116,117,224,37],"terminal","automation","http","monitoring","cron","json","rss","devops",{"skillNo":226,"name":227,"nameZh":6,"description":228,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":94,"licenseFileUrl":6,"sourceHtmlUrl":229,"categories":230,"keywords":233,"publishedAt":52},"01M6GJRHJD2A6Q830SWF9W48BC","serving-llms-vllm","vLLM: high-throughput LLM serving, OpenAI API, quantization.","https:\u002F\u002Fgithub.com\u002Fzapabob\u002FSkills\u002Fblob\u002Fmain\u002Fregistry\u002Fskills\u002Fvllm\u002Fvariants\u002Fhermes-agent\u002FSKILL.md",[231,232],{"categoryNo":98,"categoryName":99,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":104,"categoryName":105,"taxonomyType":29,"taxonomyTypeDesc":30},[234,235,236,49,48,167,237,238,239,170,240,114,241,242,243,244,245,246,247,248],"llms","vLLM","serving llms vllm","openai api","tensor","Inference Serving","Production","llm serving","High Throughput","PagedAttention","Continuous Batching","Quantization","Tensor Parallelism","high-throughput","throughput"]