[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6WWWNWM8RNG82MB2JD1XYMB":3,"skill-same:01M6WWWNWM8RNG82MB2JD1XYMB":83},{"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":28,"publishedAt":49,"linkOnly":50,"markdownContent":51,"markdownBody":52,"frontMatter":53,"refName":62,"commitSha":63,"skillDirectory":64,"forksCount":14,"repositoryHtmlUrl":65,"repositoryHomepageUrl":66,"ownerHtmlUrl":67,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":68,"install":69,"resources":82},"01M6WWWNWM8RNG82MB2JD1XYMB","docx-authoring",null,"Creating Word documents programmatically with python-docx — headings, styles, tables, lists, images, and sections. Use when generating DOCX reports, proposals, contracts, letters, or any structured Word document from data or templates.","projectious-work\u002Fprocesskit","projectious-work","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F263889726?v=4","01M6N97TJJ118WQ35CHRV8RD0E","projectious.work","01M6N97TPWJPF0BMKYQ4PBY5W8",0,"MIT","https:\u002F\u002Fgithub.com\u002Fprojectious-work\u002Fprocesskit\u002Fblob\u002Fmain\u002Farchive\u002Fprocesskit-install-20261101\u002Fcontext\u002Ftemplates\u002Fprocesskit\u002Fv0.10.0\u002Fcontext\u002Fskills\u002Fdocuments\u002Fdocx-authoring\u002FSKILL.md",[18,23],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000002","文档处理","SCENARIO","使用场景",{"categoryNo":24,"categoryName":25,"taxonomyType":26,"taxonomyTypeDesc":27},"01JBSEEDCAT000000000000034","行政与办公人员","PROFESSION","适用职业",[29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48],"docx authoring","authoring","docx","images","when","v1","python-docx","word documents","with","styles","document","reports","use","proposals","work","Word","templates","data","documents","python","2026-11-10 10:12:30",false,"---\nname: docx-authoring\ndescription: |\n  Creating Word documents programmatically with python-docx — headings, styles, tables, lists, images, and sections. Use when generating DOCX reports, proposals, contracts, letters, or any structured Word document from data or templates.\nmetadata:\n  processkit:\n    apiVersion: processkit.projectious.work\u002Fv1\n    id: SKILL-docx-authoring\n    version: \"1.0.0\"\n    created: 2026-04-08T00:00:00Z\n    category: documents\n    layer: 2\n---\n\n# DOCX Authoring\n\n## Intro\n\nUse `python-docx` to generate Word documents programmatically. The\nlibrary manipulates the underlying Office Open XML directly through a\nPython API. Structure documents with paragraph styles, not ad-hoc\nformatting — styles make documents consistent and editable in Word\nafter generation.\n\n## Overview\n\n### Setup\n\n```python\n# \u002F\u002F\u002F script\n# dependencies = [\"python-docx\"]\n# \u002F\u002F\u002F\nfrom docx import Document\nfrom docx.shared import Inches, Pt, RGBColor\nfrom docx.enum.text import WD_ALIGN_PARAGRAPH\n\ndoc = Document()           # blank document\n# doc = Document(\"template.docx\")  # or start from a template\n```\n\nInstall with `uv add python-docx` or `pip install python-docx`.\n\n### Headings and paragraphs\n\n```python\ndoc.add_heading(\"Document Title\", level=0)   # Title style\ndoc.add_heading(\"Section 1\", level=1)         # Heading 1\ndoc.add_heading(\"Subsection\", level=2)        # Heading 2\n\np = doc.add_paragraph(\"Body text here.\")\np = doc.add_paragraph(\"Intro sentence. \", style=\"Body Text\")\nrun = p.add_run(\"Bold phrase.\")\nrun.bold = True\nrun.font.size = Pt(12)\n```\n\nLevel 0 maps to the built-in \"Title\" style; levels 1-9 map to\n\"Heading 1\" through \"Heading 9\". Always use heading levels for\nstructural hierarchy — never bold a paragraph to fake a heading.\n\n### Paragraph styles\n\nPrefer named styles over inline formatting. Built-in style names\n(case-sensitive): `\"Normal\"`, `\"Body Text\"`, `\"List Bullet\"`,\n`\"List Number\"`, `\"Quote\"`, `\"Intense Quote\"`, `\"Caption\"`.\n\n```python\np = doc.add_paragraph(\"Quoted passage.\", style=\"Quote\")\np = doc.add_paragraph(\"First bullet point.\", style=\"List Bullet\")\ndoc.add_paragraph(\"Second bullet point.\", style=\"List Bullet\")\n```\n\nTo define a custom style, either embed it in a template DOCX or\ncreate it programmatically via `doc.styles.add_style()`.\n\n### Tables\n\n```python\ntable = doc.add_table(rows=1, cols=3, style=\"Table Grid\")\nhdr = table.rows[0].cells\nhdr[0].text = \"Name\"\nhdr[1].text = \"Value\"\nhdr[2].text = \"Unit\"\n\nrow = table.add_row().cells\nrow[0].text = \"Latency p99\"\nrow[1].text = \"42\"\nrow[2].text = \"ms\"\n\n# Merge cells\ntable.rows[0].cells[0].merge(table.rows[0].cells[1])\n```\n\nUse table styles (\"Table Grid\", \"Light Shading\", \"Medium List 1\") for\nconsistent visual treatment. Access cell paragraph properties via\n`cell.paragraphs[0].paragraph_format`.\n\n### Images and sections\n\n```python\ndoc.add_picture(\"chart.png\", width=Inches(5.0))\n\n# Add a page break\ndoc.add_page_break()\n\n# Section properties (portrait → landscape)\nfrom docx.oxml.ns import qn\nfrom docx.oxml import OxmlElement\nsection = doc.sections[-1]\nsection.orientation = WD_ORIENT.LANDSCAPE\nsection.page_width, section.page_height = section.page_height, section.page_width\n```\n\n### Headers, footers, and metadata\n\n```python\nsection = doc.sections[0]\nheader = section.header\nheader.paragraphs[0].text = \"Company Confidential\"\n\nfooter = section.footer\np = footer.paragraphs[0]\np.text = \"Page \"\np.add_run().add_field(\"PAGE\")   # auto-numbered page field via XML injection\n\ndoc.core_properties.author = \"Generated by Agent\"\ndoc.core_properties.title = \"Quarterly Report\"\n```\n\n### Saving\n\n```python\ndoc.save(\"output.docx\")\n```\n\nGenerate to a `BytesIO` buffer to avoid writing to disk:\n```python\nfrom io import BytesIO\nbuf = BytesIO()\ndoc.save(buf)\nbuf.seek(0)\n```\n\n### Document structure checklist\n\nBefore saving, verify:\n1. Title and all heading levels are set via styles, not bold\u002Ffont-size\n2. Tables have a named style (never `style=None`)\n3. Images have explicit widths (Word's default sizing is unreliable)\n4. `core_properties.title` and `core_properties.author` are set\n5. The file opens correctly in Word and LibreOffice\n\n## Gotchas\n\nAgent-specific failure modes — provider-neutral pause-and-self-check items:\n\n- **Applying bold\u002Ffont-size directly instead of using paragraph styles.** A paragraph made bold with `run.bold = True` looks like a heading but is not — it breaks the document outline, navigation pane, and PDF export. Use `doc.add_heading(text, level=N)` or a named paragraph style for every structural element.\n- **Starting from a blank `Document()` when the output must match a corporate template.** A blank document uses Word's default styles, which rarely match a client's brand. When the target is a templated document (letterhead, report cover), always open the template with `Document(\"template.docx\")` and add content into it.\n- **Not specifying image width.** `doc.add_picture(\"chart.png\")` without `width=Inches(...)` inserts at the image's native resolution, which varies wildly. Always supply an explicit `width` or `height` so the image fits predictably within the page margins.\n- **Generating tables with `style=None`.** Unstyled tables render with no borders and no shading, making them hard to read. Always pass a named table style — at minimum `\"Table Grid\"` for a simple bordered table.\n- **Changing page orientation without swapping width and height.** Setting `section.orientation = WD_ORIENT.LANDSCAPE` alone does not resize the page — it just marks the orientation flag. You must also swap `section.page_width` and `section.page_height` for the layout to render correctly.\n- **Saving to the same path the document was opened from without a copy.** `doc.save(\"template.docx\")` overwrites the template used as the base, destroying it for the next run. Always save to a distinct output path, or load the template from a path separate from the output.\n- **Not verifying the output opens in Word and LibreOffice.** `python-docx` can produce XML that is technically valid but triggers repair prompts or rendering differences in specific Word versions. Always open the generated file in at least one consumer before shipping.\n\n## Full reference\n\n### Page margins and layout\n\n```python\nfrom docx.shared import Inches\nsection = doc.sections[0]\nsection.top_margin    = Inches(1)\nsection.bottom_margin = Inches(1)\nsection.left_margin   = Inches(1.25)\nsection.right_margin  = Inches(1.25)\n```\n\n### Cell formatting\n\n```python\nfrom docx.oxml.ns import qn\nfrom docx.oxml import OxmlElement\n\ndef set_cell_background(cell, hex_color):\n    tc = cell._tc\n    tcPr = tc.get_or_add_tcPr()\n    shd = OxmlElement(\"w:shd\")\n    shd.set(qn(\"w:fill\"), hex_color)\n    shd.set(qn(\"w:val\"), \"clear\")\n    tcPr.append(shd)\n\nset_cell_background(table.rows[0].cells[0], \"4472C4\")\n```\n\n### Numbered lists with custom start\n\n```python\nfrom docx.oxml.ns import qn\nfrom docx.oxml import OxmlElement\n\np = doc.add_paragraph(\"Step one.\", style=\"List Number\")\n# To restart numbering or set start: manipulate numPr XML directly\n```\n\n### Hyperlinks\n\npython-docx does not have a native hyperlink API. Inject via XML:\n\n```python\nfrom docx.opc.constants import RELATIONSHIP_TYPE as RT\n\ndef add_hyperlink(paragraph, text, url):\n    part = paragraph.part\n    r_id = part.relate_to(url, RT.HYPERLINK, is_external=True)\n    hyperlink = OxmlElement(\"w:hyperlink\")\n    hyperlink.set(qn(\"r:id\"), r_id)\n    run = OxmlElement(\"w:r\")\n    rPr = OxmlElement(\"w:rPr\")\n    rStyle = OxmlElement(\"w:rStyle\")\n    rStyle.set(qn(\"w:val\"), \"Hyperlink\")\n    rPr.append(rStyle)\n    run.append(rPr)\n    t = OxmlElement(\"w:t\")\n    t.text = text\n    run.append(t)\n    hyperlink.append(run)\n    paragraph._p.append(hyperlink)\n    return hyperlink\n```\n\n### Conversion to PDF\n\npython-docx cannot produce PDF directly. Options:\n- `libreoffice --headless --convert-to pdf output.docx` (requires LibreOffice)\n- `docx2pdf` library (requires Word on macOS\u002FWindows)\n- Upload to Google Docs API and export as PDF\n","# DOCX Authoring\n\n## Intro\n\nUse `python-docx` to generate Word documents programmatically. The\nlibrary manipulates the underlying Office Open XML directly through a\nPython API. Structure documents with paragraph styles, not ad-hoc\nformatting — styles make documents consistent and editable in Word\nafter generation.\n\n## Overview\n\n### Setup\n\n```python\n# \u002F\u002F\u002F script\n# dependencies = [\"python-docx\"]\n# \u002F\u002F\u002F\nfrom docx import Document\nfrom docx.shared import Inches, Pt, RGBColor\nfrom docx.enum.text import WD_ALIGN_PARAGRAPH\n\ndoc = Document()           # blank document\n# doc = Document(\"template.docx\")  # or start from a template\n```\n\nInstall with `uv add python-docx` or `pip install python-docx`.\n\n### Headings and paragraphs\n\n```python\ndoc.add_heading(\"Document Title\", level=0)   # Title style\ndoc.add_heading(\"Section 1\", level=1)         # Heading 1\ndoc.add_heading(\"Subsection\", level=2)        # Heading 2\n\np = doc.add_paragraph(\"Body text here.\")\np = doc.add_paragraph(\"Intro sentence. \", style=\"Body Text\")\nrun = p.add_run(\"Bold phrase.\")\nrun.bold = True\nrun.font.size = Pt(12)\n```\n\nLevel 0 maps to the built-in \"Title\" style; levels 1-9 map to\n\"Heading 1\" through \"Heading 9\". Always use heading levels for\nstructural hierarchy — never bold a paragraph to fake a heading.\n\n### Paragraph styles\n\nPrefer named styles over inline formatting. Built-in style names\n(case-sensitive): `\"Normal\"`, `\"Body Text\"`, `\"List Bullet\"`,\n`\"List Number\"`, `\"Quote\"`, `\"Intense Quote\"`, `\"Caption\"`.\n\n```python\np = doc.add_paragraph(\"Quoted passage.\", style=\"Quote\")\np = doc.add_paragraph(\"First bullet point.\", style=\"List Bullet\")\ndoc.add_paragraph(\"Second bullet point.\", style=\"List Bullet\")\n```\n\nTo define a custom style, either embed it in a template DOCX or\ncreate it programmatically via `doc.styles.add_style()`.\n\n### Tables\n\n```python\ntable = doc.add_table(rows=1, cols=3, style=\"Table Grid\")\nhdr = table.rows[0].cells\nhdr[0].text = \"Name\"\nhdr[1].text = \"Value\"\nhdr[2].text = \"Unit\"\n\nrow = table.add_row().cells\nrow[0].text = \"Latency p99\"\nrow[1].text = \"42\"\nrow[2].text = \"ms\"\n\n# Merge cells\ntable.rows[0].cells[0].merge(table.rows[0].cells[1])\n```\n\nUse table styles (\"Table Grid\", \"Light Shading\", \"Medium List 1\") for\nconsistent visual treatment. Access cell paragraph properties via\n`cell.paragraphs[0].paragraph_format`.\n\n### Images and sections\n\n```python\ndoc.add_picture(\"chart.png\", width=Inches(5.0))\n\n# Add a page break\ndoc.add_page_break()\n\n# Section properties (portrait → landscape)\nfrom docx.oxml.ns import qn\nfrom docx.oxml import OxmlElement\nsection = doc.sections[-1]\nsection.orientation = WD_ORIENT.LANDSCAPE\nsection.page_width, section.page_height = section.page_height, section.page_width\n```\n\n### Headers, footers, and metadata\n\n```python\nsection = doc.sections[0]\nheader = section.header\nheader.paragraphs[0].text = \"Company Confidential\"\n\nfooter = section.footer\np = footer.paragraphs[0]\np.text = \"Page \"\np.add_run().add_field(\"PAGE\")   # auto-numbered page field via XML injection\n\ndoc.core_properties.author = \"Generated by Agent\"\ndoc.core_properties.title = \"Quarterly Report\"\n```\n\n### Saving\n\n```python\ndoc.save(\"output.docx\")\n```\n\nGenerate to a `BytesIO` buffer to avoid writing to disk:\n```python\nfrom io import BytesIO\nbuf = BytesIO()\ndoc.save(buf)\nbuf.seek(0)\n```\n\n### Document structure checklist\n\nBefore saving, verify:\n1. Title and all heading levels are set via styles, not bold\u002Ffont-size\n2. Tables have a named style (never `style=None`)\n3. Images have explicit widths (Word's default sizing is unreliable)\n4. `core_properties.title` and `core_properties.author` are set\n5. The file opens correctly in Word and LibreOffice\n\n## Gotchas\n\nAgent-specific failure modes — provider-neutral pause-and-self-check items:\n\n- **Applying bold\u002Ffont-size directly instead of using paragraph styles.** A paragraph made bold with `run.bold = True` looks like a heading but is not — it breaks the document outline, navigation pane, and PDF export. Use `doc.add_heading(text, level=N)` or a named paragraph style for every structural element.\n- **Starting from a blank `Document()` when the output must match a corporate template.** A blank document uses Word's default styles, which rarely match a client's brand. When the target is a templated document (letterhead, report cover), always open the template with `Document(\"template.docx\")` and add content into it.\n- **Not specifying image width.** `doc.add_picture(\"chart.png\")` without `width=Inches(...)` inserts at the image's native resolution, which varies wildly. Always supply an explicit `width` or `height` so the image fits predictably within the page margins.\n- **Generating tables with `style=None`.** Unstyled tables render with no borders and no shading, making them hard to read. Always pass a named table style — at minimum `\"Table Grid\"` for a simple bordered table.\n- **Changing page orientation without swapping width and height.** Setting `section.orientation = WD_ORIENT.LANDSCAPE` alone does not resize the page — it just marks the orientation flag. You must also swap `section.page_width` and `section.page_height` for the layout to render correctly.\n- **Saving to the same path the document was opened from without a copy.** `doc.save(\"template.docx\")` overwrites the template used as the base, destroying it for the next run. Always save to a distinct output path, or load the template from a path separate from the output.\n- **Not verifying the output opens in Word and LibreOffice.** `python-docx` can produce XML that is technically valid but triggers repair prompts or rendering differences in specific Word versions. Always open the generated file in at least one consumer before shipping.\n\n## Full reference\n\n### Page margins and layout\n\n```python\nfrom docx.shared import Inches\nsection = doc.sections[0]\nsection.top_margin    = Inches(1)\nsection.bottom_margin = Inches(1)\nsection.left_margin   = Inches(1.25)\nsection.right_margin  = Inches(1.25)\n```\n\n### Cell formatting\n\n```python\nfrom docx.oxml.ns import qn\nfrom docx.oxml import OxmlElement\n\ndef set_cell_background(cell, hex_color):\n    tc = cell._tc\n    tcPr = tc.get_or_add_tcPr()\n    shd = OxmlElement(\"w:shd\")\n    shd.set(qn(\"w:fill\"), hex_color)\n    shd.set(qn(\"w:val\"), \"clear\")\n    tcPr.append(shd)\n\nset_cell_background(table.rows[0].cells[0], \"4472C4\")\n```\n\n### Numbered lists with custom start\n\n```python\nfrom docx.oxml.ns import qn\nfrom docx.oxml import OxmlElement\n\np = doc.add_paragraph(\"Step one.\", style=\"List Number\")\n# To restart numbering or set start: manipulate numPr XML directly\n```\n\n### Hyperlinks\n\npython-docx does not have a native hyperlink API. Inject via XML:\n\n```python\nfrom docx.opc.constants import RELATIONSHIP_TYPE as RT\n\ndef add_hyperlink(paragraph, text, url):\n    part = paragraph.part\n    r_id = part.relate_to(url, RT.HYPERLINK, is_external=True)\n    hyperlink = OxmlElement(\"w:hyperlink\")\n    hyperlink.set(qn(\"r:id\"), r_id)\n    run = OxmlElement(\"w:r\")\n    rPr = OxmlElement(\"w:rPr\")\n    rStyle = OxmlElement(\"w:rStyle\")\n    rStyle.set(qn(\"w:val\"), \"Hyperlink\")\n    rPr.append(rStyle)\n    run.append(rPr)\n    t = OxmlElement(\"w:t\")\n    t.text = text\n    run.append(t)\n    hyperlink.append(run)\n    paragraph._p.append(hyperlink)\n    return hyperlink\n```\n\n### Conversion to PDF\n\npython-docx cannot produce PDF directly. Options:\n- `libreoffice --headless --convert-to pdf output.docx` (requires LibreOffice)\n- `docx2pdf` library (requires Word on macOS\u002FWindows)\n- Upload to Google Docs API and export as PDF\n",{"name":5,"metadata":54,"description":61},{"processkit":55},{"id":56,"layer":57,"created":58,"version":59,"category":47,"apiVersion":60},"SKILL-docx-authoring",2,1775606400000,"1.0.0","processkit.projectious.work\u002Fv1","Creating Word documents programmatically with python-docx — headings, styles, tables, lists, images, and sections. Use when generating DOCX reports, proposals, contracts, letters, or any structured Word document from data or templates.\n","main","4876a92620ee792aac2ac9a1a806322d8a572367","archive\u002Fprocesskit-install-20261101\u002Fcontext\u002Ftemplates\u002Fprocesskit\u002Fv0.10.0\u002Fcontext\u002Fskills\u002Fdocuments\u002Fdocx-authoring","https:\u002F\u002Fgithub.com\u002Fprojectious-work\u002Fprocesskit","https:\u002F\u002Fprojectious-work.github.io\u002Fprocesskit\u002F","https:\u002F\u002Fgithub.com\u002Fprojectious-work","2026-11-11 23:24:18",{"source":8,"skillName":5,"commands":70,"prompt":80,"zipAvailable":81},[71,74,77],{"tool":72,"command":73},"npx","npx skills add projectious-work\u002Fprocesskit --skill docx-authoring",{"tool":75,"command":76},"bunx","bunx skills add projectious-work\u002Fprocesskit --skill docx-authoring",{"tool":78,"command":79},"pnpm","pnpm dlx skills add projectious-work\u002Fprocesskit --skill docx-authoring","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fprojectious-work\u002Fprocesskit\u002Fblob\u002Fmain\u002Farchive\u002Fprocesskit-install-20261101\u002Fcontext\u002Ftemplates\u002Fprocesskit\u002Fv0.10.0\u002Fcontext\u002Fskills\u002Fdocuments\u002Fdocx-authoring\u002FSKILL.md",true,[],[84,91,98,104,128,148],{"skillNo":85,"name":86,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":87,"categories":88,"keywords":89,"publishedAt":90},"01M7665G2ED3624R3X93304265","standard-ui-design","https:\u002F\u002Fgithub.com\u002Fprojectious-work\u002Fprocesskit\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fstandard-ui-design\u002FSKILL.md",[],[],"2026-11-12 13:55:43",{"skillNo":92,"name":93,"nameZh":6,"description":94,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":95,"categories":96,"keywords":97,"publishedAt":90},"01M76651QTC6W0HJ4AFW2MMR3V","standard-agent-use","Company standard for working with AI agents. Use when deciding what to delegate to agents, capturing open work, keeping agent memory or knowledge notes, improving an agent workflow, or introducing agent work in a team or for a client.","https:\u002F\u002Fgithub.com\u002Fprojectious-work\u002Fprocesskit\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fstandard-agent-use\u002FSKILL.md",[],[],{"skillNo":99,"name":100,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":101,"categories":102,"keywords":103,"publishedAt":90},"01M76650NN4T8P241021NBR64S","standard-agent-building","https:\u002F\u002Fgithub.com\u002Fprojectious-work\u002Fprocesskit\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fstandard-agent-building\u002FSKILL.md",[],[],{"skillNo":105,"name":106,"nameZh":6,"description":107,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":108,"categories":109,"keywords":113,"publishedAt":49},"01M6X5MTC89B4ZGXW3JVSQCPF8","skill-management","Manage Skill package manifests as v1 ontology entities.","https:\u002F\u002Fgithub.com\u002Fprojectious-work\u002Fprocesskit\u002Fblob\u002Fmain\u002Fsrc\u002Fcontext\u002Fskills\u002Fprocesskit\u002Fskill-management\u002FSKILL.md",[110],{"categoryNo":111,"categoryName":112,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发",[114,115,116,34,117,118,43,119,120,121,122,123,106,124,125,126,127],"management","skill management","ontology","create","as","transition","get","manage","update","alpha","list","package","skill package","manifests",{"skillNo":129,"name":130,"nameZh":6,"description":131,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":132,"categories":133,"keywords":135,"publishedAt":49},"01M6X5MCV74NHW5MEDNHZRF2C8","schema-management","Manage generated processkit schema contracts through deterministic MCP rebuild and inspection workflows.","https:\u002F\u002Fgithub.com\u002Fprojectious-work\u002Fprocesskit\u002Fblob\u002Fmain\u002Fsrc\u002Fcontext\u002Fskills\u002Fprocesskit\u002Fschema-management\u002FSKILL.md",[134],{"categoryNo":111,"categoryName":112,"taxonomyType":21,"taxonomyTypeDesc":22},[136,137,114,138,139,140,141,142,143,144,145,146,43,120,121,123,147],"schema","schema management","contract","rebuild","contracts","workflows","wed","generated","MCP","validation","deterministic","mode",{"skillNo":149,"name":150,"nameZh":6,"description":151,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":152,"categories":153,"keywords":154,"publishedAt":49},"01M6X5M5G6YJ96AMZGSCZJ1D13","proposition-management","Record claims, risks, beliefs, world facts, WSJF estimates, and assumptions through the Proposition interface.","https:\u002F\u002Fgithub.com\u002Fprojectious-work\u002Fprocesskit\u002Fblob\u002Fmain\u002Fsrc\u002Fcontext\u002Fskills\u002Fprocesskit\u002Fproposition-management\u002FSKILL.md",[],[155,114,156,157,117,158,159,160,43,120,161,162,122,163,123,164,165,166,167,168],"proposition management","proposition","interface","claims","record","world","creation","event","WSJF","index","updates","query","facts","log"]