[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill-anthropic-docx":3,"mdc--7q88e2-key":40,"related-repo-anthropic-docx":1442,"related-org-anthropic-docx":1550},{"slug":4,"name":4,"fn":5,"description":6,"org":7,"tags":12,"stars":28,"repoUrl":29,"updatedAt":30,"license":31,"forks":32,"topics":33,"repo":35,"sourceUrl":38,"mdContent":39},"docx","create and edit Word documents","Use this skill whenever the user wants to create, read, edit, or manipulate Word documents (.docx files) or Word templates (.dotx files). Triggers include: any mention of 'Word doc', 'word document', '.docx', '.dotx', or requests to produce professional documents with formatting like tables of contents, headings, page numbers, or letterheads. Also use when extracting or reorganizing content from .docx or .dotx files, inserting or replacing images in documents, performing find-and-replace in Word files, working with tracked changes or comments, or converting content into a polished Word document. If the user asks for a 'report', 'memo', 'letter', 'template', or similar deliverable as a Word or .docx file, use this skill. Do NOT use for PDFs, spreadsheets, Google Docs, or general coding tasks unrelated to document generation.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},"anthropic","Anthropic","https:\u002F\u002Fpexgzepcugksgbtrxkhf.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Forg-logos\u002Fanthropic.png","anthropics",[13,17,20,23,25],{"name":14,"slug":15,"type":16},"Templates","templates","tag",{"name":18,"slug":19,"type":16},"Documents","documents",{"name":21,"slug":22,"type":16},"Office","office",{"name":24,"slug":4,"type":16},"DOCX",{"name":26,"slug":27,"type":16},"Word","word",161831,"https:\u002F\u002Fgithub.com\u002Fanthropics\u002Fskills","2026-07-18T05:16:23.136271","Proprietary. LICENSE.txt has complete terms",19131,[34],"agent-skills",{"repoUrl":29,"stars":28,"forks":32,"topics":36,"description":37},[34],"Public repository for Agent Skills","https:\u002F\u002Fgithub.com\u002Fanthropics\u002Fskills\u002Ftree\u002FHEAD\u002Fskills\u002Fdocx","---\nname: docx\ndescription: \"Use this skill whenever the user wants to create, read, edit, or manipulate Word documents (.docx files) or Word templates (.dotx files). Triggers include: any mention of 'Word doc', 'word document', '.docx', '.dotx', or requests to produce professional documents with formatting like tables of contents, headings, page numbers, or letterheads. Also use when extracting or reorganizing content from .docx or .dotx files, inserting or replacing images in documents, performing find-and-replace in Word files, working with tracked changes or comments, or converting content into a polished Word document. If the user asks for a 'report', 'memo', 'letter', 'template', or similar deliverable as a Word or .docx file, use this skill. Do NOT use for PDFs, spreadsheets, Google Docs, or general coding tasks unrelated to document generation.\"\nlicense: Proprietary. LICENSE.txt has complete terms\n---\n\n# DOCX creation, editing, and analysis\n\nA `.docx` is a ZIP archive of XML files. Choose your approach by task:\n\n| Task | Approach |\n|---|---|\n| **Create** a new document | Write a `docx` (npm) script — see gotchas below |\n| **Edit** an existing document | `unzip` → edit `word\u002Fdocument.xml` → `zip` (docx-js cannot open existing files) |\n| **Read** content | `pandoc -t markdown file.docx` |\n\n> Script paths below are relative to this skill's directory.\n\n## Creating with docx-js — gotchas\n\n`docx` is preinstalled — do not run `npm install` first; write the script and `require('docx')` directly. Only if that require fails: `npm install docx`. The model knows the API; these are the footguns:\n\n- **Page size defaults to A4.** For US Letter set `page: { size: { width: 12240, height: 15840 } }` (DXA; 1440 = 1″).\n- **Landscape:** pass portrait dimensions and `orientation: PageOrientation.LANDSCAPE` — docx-js swaps width\u002Fheight internally.\n- **Tables need dual widths:** set `columnWidths` on the table AND `width` on every cell, both in `WidthType.DXA` (PERCENTAGE breaks in Google Docs). Column widths must sum to the table width.\n- **Table shading:** use `ShadingType.CLEAR`, never `SOLID` (renders black).\n- **Lists:** never insert `•` literally; use a `numbering` config with `LevelFormat.BULLET`.\n- **`ImageRun` requires `type:`** (`\"png\"`, `\"jpg\"`, …).\n- **`PageBreak` must be inside a `Paragraph`.**\n- **Never use `\\n`** — use separate `Paragraph` elements.\n- **TOC:** headings must use built-in `HeadingLevel.*`; custom heading styles need `outlineLevel` set or they won't appear.\n- **Don't use a table as a horizontal rule** — use a paragraph bottom border instead.\n- **Dot-leader \u002F right-aligned-on-same-line:** use `PositionalTab` (`alignment: PositionalTabAlignment.RIGHT`, `leader: PositionalTabLeader.DOT`) inside a `TextRun`, not literal `.` or space padding.\n\n## Verify the output\n\nAfter writing a `.docx`, render it and look at it:\n\n```bash\npython scripts\u002Foffice\u002Fsoffice.py --headless --convert-to pdf output.docx\npdftoppm -jpeg -r 100 output.pdf page\nls page-*.jpg   # then Read the images\n```\n\n`pdftoppm` zero-pads page numbers to the width of the page count (`page-01.jpg`…`page-12.jpg`).\n\n## Editing existing documents\n\nLegacy `.doc` files must be converted first: `python scripts\u002Foffice\u002Fsoffice.py --headless --convert-to docx file.doc`.\n\n```bash\nunzip -q doc.docx -d unpacked\u002F\nfind unpacked -type l -delete   # strip symlink entries — docx from external parties is untrusted\npython scripts\u002Fmerge_runs.py unpacked\u002F   # coalesce fragmented runs so text is findable\n# edit unpacked\u002Fword\u002Fdocument.xml in place — do NOT reformat or pretty-print\n(cd unpacked && rm -f ..\u002Fout.docx && zip -Xr ..\u002Fout.docx .)\npython scripts\u002Foffice\u002Fvalidate.py out.docx --original doc.docx   # XSD checks; --auto-repair fixes common issues\n# redlining? add --author \"\u003Cthe name you redlined under>\" to check every edit is tracked\n```\n\nWord splits text across many `\u003Cw:r>` runs (revision ids, spell-check markers), so a phrase you can see in the document often doesn't exist as a contiguous string in the XML. `merge_runs.py` merges adjacent identically-formatted runs in `word\u002Fdocument.xml` without changing content or rendering; it also accepts a `.docx` directly (`python scripts\u002Fmerge_runs.py doc.docx -o merged.docx`).\n\n**Tracked changes:** when redlining, validate with `--author \"\u003Cthe name you redlined under>\"` (needs `--original`) — it reports any text you changed without a `\u003Cw:ins>`\u002F`\u003Cw:del>` around it, which is easy to do by accident and invisible in the accepted view. Wrap runs in `\u003Cw:ins>`\u002F`\u003Cw:del>` with `w:id`, `w:author`, `w:date` attributes. Inside `\u003Cw:del>`, the text element is `\u003Cw:delText>`, not `\u003Cw:t>`. A deleted paragraph mark (`\u003Cw:pPr>\u003Cw:rPr>\u003Cw:del w:id=\"..\" w:author=\"..\" w:date=\"..\"\u002F>\u003C\u002Fw:rPr>\u003C\u002Fw:pPr>`) means \"merge this paragraph into the next\" — so deleting a paragraph outright is that plus a `\u003Cw:del>` around every run. The `\u003Cw:del\u002F>` must come before the rPr's other children; their order is schema-enforced.\n\nTo produce a clean copy with all tracked changes accepted: `python scripts\u002Faccept_changes.py in.docx out.docx`.\n\nAccepting a deleted paragraph mark should join that paragraph to the one below it, so a paragraph whose runs are *all* deleted vanishes. Word does this; `accept_changes.py` and `pandoc --track-changes=accept` don't always. Both fail the same way — they strip the deleted text but leave the emptied paragraph behind, which reads as a stray empty bullet when it was auto-numbered:\n\n- `pandoc --track-changes=accept` never joins the paragraphs.\n- `accept_changes.py` (LibreOffice) joins them correctly, except when the deleted paragraph is followed by an empty spacer paragraph.\n\nAn empty bullet in either view is an artifact of that view, not a defect in the document. Check paragraph deletions in the XML.\n\n## Comments\n\nComments require six cross-linked files. Use the helper — directory mode when you'll also be editing `document.xml` (saves an unzip\u002Frezip cycle), `.docx`-direct mode otherwise:\n\n```bash\n# Against an already-unpacked directory (preferred when also placing markers)\npython scripts\u002Fcomment.py unpacked\u002F \"Fees & expenses cap is too low\"\npython scripts\u002Fcomment.py unpacked\u002F \"Agreed\" --parent 0\n\n# Against a .docx directly\npython scripts\u002Fcomment.py contract.docx \"This cap is too low\" -o annotated.docx\n```\n\nThe script writes `comments.xml`, `commentsExtended.xml`, `commentsIds.xml`, `commentsExtensible.xml`, the relationships, and the content-type overrides. Comment IDs are auto-assigned. It then prints the `\u003Cw:commentRangeStart>`\u002F`\u003Cw:commentRangeEnd>`\u002F`\u003Cw:commentReference>` snippet to add to `word\u002Fdocument.xml` so the comment anchors to specific text — until you place those markers, the comment exists but is not visible.\n\n## Dependencies\n\n`docx` (npm, preinstalled — install only if `require('docx')` fails) · `pandoc` · LibreOffice (`soffice`) · `pdftoppm` (Poppler)\n",{"data":41,"body":42},{"name":4,"description":6,"license":31},{"type":43,"children":44},"root",[45,54,69,185,194,201,235,534,540,552,667,693,699,719,926,968,1091,1103,1132,1155,1160,1166,1186,1327,1390,1396,1436],{"type":46,"tag":47,"props":48,"children":50},"element","h1",{"id":49},"docx-creation-editing-and-analysis",[51],{"type":52,"value":53},"text","DOCX creation, editing, and analysis",{"type":46,"tag":55,"props":56,"children":57},"p",{},[58,60,67],{"type":52,"value":59},"A ",{"type":46,"tag":61,"props":62,"children":64},"code",{"className":63},[],[65],{"type":52,"value":66},".docx",{"type":52,"value":68}," is a ZIP archive of XML files. Choose your approach by task:",{"type":46,"tag":70,"props":71,"children":72},"table",{},[73,92],{"type":46,"tag":74,"props":75,"children":76},"thead",{},[77],{"type":46,"tag":78,"props":79,"children":80},"tr",{},[81,87],{"type":46,"tag":82,"props":83,"children":84},"th",{},[85],{"type":52,"value":86},"Task",{"type":46,"tag":82,"props":88,"children":89},{},[90],{"type":52,"value":91},"Approach",{"type":46,"tag":93,"props":94,"children":95},"tbody",{},[96,123,163],{"type":46,"tag":78,"props":97,"children":98},{},[99,111],{"type":46,"tag":100,"props":101,"children":102},"td",{},[103,109],{"type":46,"tag":104,"props":105,"children":106},"strong",{},[107],{"type":52,"value":108},"Create",{"type":52,"value":110}," a new document",{"type":46,"tag":100,"props":112,"children":113},{},[114,116,121],{"type":52,"value":115},"Write a ",{"type":46,"tag":61,"props":117,"children":119},{"className":118},[],[120],{"type":52,"value":4},{"type":52,"value":122}," (npm) script — see gotchas below",{"type":46,"tag":78,"props":124,"children":125},{},[126,136],{"type":46,"tag":100,"props":127,"children":128},{},[129,134],{"type":46,"tag":104,"props":130,"children":131},{},[132],{"type":52,"value":133},"Edit",{"type":52,"value":135}," an existing document",{"type":46,"tag":100,"props":137,"children":138},{},[139,145,147,153,155,161],{"type":46,"tag":61,"props":140,"children":142},{"className":141},[],[143],{"type":52,"value":144},"unzip",{"type":52,"value":146}," → edit ",{"type":46,"tag":61,"props":148,"children":150},{"className":149},[],[151],{"type":52,"value":152},"word\u002Fdocument.xml",{"type":52,"value":154}," → ",{"type":46,"tag":61,"props":156,"children":158},{"className":157},[],[159],{"type":52,"value":160},"zip",{"type":52,"value":162}," (docx-js cannot open existing files)",{"type":46,"tag":78,"props":164,"children":165},{},[166,176],{"type":46,"tag":100,"props":167,"children":168},{},[169,174],{"type":46,"tag":104,"props":170,"children":171},{},[172],{"type":52,"value":173},"Read",{"type":52,"value":175}," content",{"type":46,"tag":100,"props":177,"children":178},{},[179],{"type":46,"tag":61,"props":180,"children":182},{"className":181},[],[183],{"type":52,"value":184},"pandoc -t markdown file.docx",{"type":46,"tag":186,"props":187,"children":188},"blockquote",{},[189],{"type":46,"tag":55,"props":190,"children":191},{},[192],{"type":52,"value":193},"Script paths below are relative to this skill's directory.",{"type":46,"tag":195,"props":196,"children":198},"h2",{"id":197},"creating-with-docx-js-gotchas",[199],{"type":52,"value":200},"Creating with docx-js — gotchas",{"type":46,"tag":55,"props":202,"children":203},{},[204,209,211,217,219,225,227,233],{"type":46,"tag":61,"props":205,"children":207},{"className":206},[],[208],{"type":52,"value":4},{"type":52,"value":210}," is preinstalled — do not run ",{"type":46,"tag":61,"props":212,"children":214},{"className":213},[],[215],{"type":52,"value":216},"npm install",{"type":52,"value":218}," first; write the script and ",{"type":46,"tag":61,"props":220,"children":222},{"className":221},[],[223],{"type":52,"value":224},"require('docx')",{"type":52,"value":226}," directly. Only if that require fails: ",{"type":46,"tag":61,"props":228,"children":230},{"className":229},[],[231],{"type":52,"value":232},"npm install docx",{"type":52,"value":234},". The model knows the API; these are the footguns:",{"type":46,"tag":236,"props":237,"children":238},"ul",{},[239,258,276,310,336,370,408,429,452,478,488],{"type":46,"tag":240,"props":241,"children":242},"li",{},[243,248,250,256],{"type":46,"tag":104,"props":244,"children":245},{},[246],{"type":52,"value":247},"Page size defaults to A4.",{"type":52,"value":249}," For US Letter set ",{"type":46,"tag":61,"props":251,"children":253},{"className":252},[],[254],{"type":52,"value":255},"page: { size: { width: 12240, height: 15840 } }",{"type":52,"value":257}," (DXA; 1440 = 1″).",{"type":46,"tag":240,"props":259,"children":260},{},[261,266,268,274],{"type":46,"tag":104,"props":262,"children":263},{},[264],{"type":52,"value":265},"Landscape:",{"type":52,"value":267}," pass portrait dimensions and ",{"type":46,"tag":61,"props":269,"children":271},{"className":270},[],[272],{"type":52,"value":273},"orientation: PageOrientation.LANDSCAPE",{"type":52,"value":275}," — docx-js swaps width\u002Fheight internally.",{"type":46,"tag":240,"props":277,"children":278},{},[279,284,286,292,294,300,302,308],{"type":46,"tag":104,"props":280,"children":281},{},[282],{"type":52,"value":283},"Tables need dual widths:",{"type":52,"value":285}," set ",{"type":46,"tag":61,"props":287,"children":289},{"className":288},[],[290],{"type":52,"value":291},"columnWidths",{"type":52,"value":293}," on the table AND ",{"type":46,"tag":61,"props":295,"children":297},{"className":296},[],[298],{"type":52,"value":299},"width",{"type":52,"value":301}," on every cell, both in ",{"type":46,"tag":61,"props":303,"children":305},{"className":304},[],[306],{"type":52,"value":307},"WidthType.DXA",{"type":52,"value":309}," (PERCENTAGE breaks in Google Docs). Column widths must sum to the table width.",{"type":46,"tag":240,"props":311,"children":312},{},[313,318,320,326,328,334],{"type":46,"tag":104,"props":314,"children":315},{},[316],{"type":52,"value":317},"Table shading:",{"type":52,"value":319}," use ",{"type":46,"tag":61,"props":321,"children":323},{"className":322},[],[324],{"type":52,"value":325},"ShadingType.CLEAR",{"type":52,"value":327},", never ",{"type":46,"tag":61,"props":329,"children":331},{"className":330},[],[332],{"type":52,"value":333},"SOLID",{"type":52,"value":335}," (renders black).",{"type":46,"tag":240,"props":337,"children":338},{},[339,344,346,352,354,360,362,368],{"type":46,"tag":104,"props":340,"children":341},{},[342],{"type":52,"value":343},"Lists:",{"type":52,"value":345}," never insert ",{"type":46,"tag":61,"props":347,"children":349},{"className":348},[],[350],{"type":52,"value":351},"•",{"type":52,"value":353}," literally; use a ",{"type":46,"tag":61,"props":355,"children":357},{"className":356},[],[358],{"type":52,"value":359},"numbering",{"type":52,"value":361}," config with ",{"type":46,"tag":61,"props":363,"children":365},{"className":364},[],[366],{"type":52,"value":367},"LevelFormat.BULLET",{"type":52,"value":369},".",{"type":46,"tag":240,"props":371,"children":372},{},[373,390,392,398,400,406],{"type":46,"tag":104,"props":374,"children":375},{},[376,382,384],{"type":46,"tag":61,"props":377,"children":379},{"className":378},[],[380],{"type":52,"value":381},"ImageRun",{"type":52,"value":383}," requires ",{"type":46,"tag":61,"props":385,"children":387},{"className":386},[],[388],{"type":52,"value":389},"type:",{"type":52,"value":391}," (",{"type":46,"tag":61,"props":393,"children":395},{"className":394},[],[396],{"type":52,"value":397},"\"png\"",{"type":52,"value":399},", ",{"type":46,"tag":61,"props":401,"children":403},{"className":402},[],[404],{"type":52,"value":405},"\"jpg\"",{"type":52,"value":407},", …).",{"type":46,"tag":240,"props":409,"children":410},{},[411],{"type":46,"tag":104,"props":412,"children":413},{},[414,420,422,428],{"type":46,"tag":61,"props":415,"children":417},{"className":416},[],[418],{"type":52,"value":419},"PageBreak",{"type":52,"value":421}," must be inside a ",{"type":46,"tag":61,"props":423,"children":425},{"className":424},[],[426],{"type":52,"value":427},"Paragraph",{"type":52,"value":369},{"type":46,"tag":240,"props":430,"children":431},{},[432,443,445,450],{"type":46,"tag":104,"props":433,"children":434},{},[435,437],{"type":52,"value":436},"Never use ",{"type":46,"tag":61,"props":438,"children":440},{"className":439},[],[441],{"type":52,"value":442},"\\n",{"type":52,"value":444}," — use separate ",{"type":46,"tag":61,"props":446,"children":448},{"className":447},[],[449],{"type":52,"value":427},{"type":52,"value":451}," elements.",{"type":46,"tag":240,"props":453,"children":454},{},[455,460,462,468,470,476],{"type":46,"tag":104,"props":456,"children":457},{},[458],{"type":52,"value":459},"TOC:",{"type":52,"value":461}," headings must use built-in ",{"type":46,"tag":61,"props":463,"children":465},{"className":464},[],[466],{"type":52,"value":467},"HeadingLevel.*",{"type":52,"value":469},"; custom heading styles need ",{"type":46,"tag":61,"props":471,"children":473},{"className":472},[],[474],{"type":52,"value":475},"outlineLevel",{"type":52,"value":477}," set or they won't appear.",{"type":46,"tag":240,"props":479,"children":480},{},[481,486],{"type":46,"tag":104,"props":482,"children":483},{},[484],{"type":52,"value":485},"Don't use a table as a horizontal rule",{"type":52,"value":487}," — use a paragraph bottom border instead.",{"type":46,"tag":240,"props":489,"children":490},{},[491,496,497,503,504,510,511,517,519,525,527,532],{"type":46,"tag":104,"props":492,"children":493},{},[494],{"type":52,"value":495},"Dot-leader \u002F right-aligned-on-same-line:",{"type":52,"value":319},{"type":46,"tag":61,"props":498,"children":500},{"className":499},[],[501],{"type":52,"value":502},"PositionalTab",{"type":52,"value":391},{"type":46,"tag":61,"props":505,"children":507},{"className":506},[],[508],{"type":52,"value":509},"alignment: PositionalTabAlignment.RIGHT",{"type":52,"value":399},{"type":46,"tag":61,"props":512,"children":514},{"className":513},[],[515],{"type":52,"value":516},"leader: PositionalTabLeader.DOT",{"type":52,"value":518},") inside a ",{"type":46,"tag":61,"props":520,"children":522},{"className":521},[],[523],{"type":52,"value":524},"TextRun",{"type":52,"value":526},", not literal ",{"type":46,"tag":61,"props":528,"children":530},{"className":529},[],[531],{"type":52,"value":369},{"type":52,"value":533}," or space padding.",{"type":46,"tag":195,"props":535,"children":537},{"id":536},"verify-the-output",[538],{"type":52,"value":539},"Verify the output",{"type":46,"tag":55,"props":541,"children":542},{},[543,545,550],{"type":52,"value":544},"After writing a ",{"type":46,"tag":61,"props":546,"children":548},{"className":547},[],[549],{"type":52,"value":66},{"type":52,"value":551},", render it and look at it:",{"type":46,"tag":553,"props":554,"children":559},"pre",{"className":555,"code":556,"language":557,"meta":558,"style":558},"language-bash shiki shiki-themes material-theme-lighter material-theme material-theme-palenight","python scripts\u002Foffice\u002Fsoffice.py --headless --convert-to pdf output.docx\npdftoppm -jpeg -r 100 output.pdf page\nls page-*.jpg   # then Read the images\n","bash","",[560],{"type":46,"tag":61,"props":561,"children":562},{"__ignoreMap":558},[563,601,636],{"type":46,"tag":564,"props":565,"children":568},"span",{"class":566,"line":567},"line",1,[569,575,581,586,591,596],{"type":46,"tag":564,"props":570,"children":572},{"style":571},"--shiki-light:#E2931D;--shiki-default:#FFCB6B;--shiki-dark:#FFCB6B",[573],{"type":52,"value":574},"python",{"type":46,"tag":564,"props":576,"children":578},{"style":577},"--shiki-light:#91B859;--shiki-default:#C3E88D;--shiki-dark:#C3E88D",[579],{"type":52,"value":580}," scripts\u002Foffice\u002Fsoffice.py",{"type":46,"tag":564,"props":582,"children":583},{"style":577},[584],{"type":52,"value":585}," --headless",{"type":46,"tag":564,"props":587,"children":588},{"style":577},[589],{"type":52,"value":590}," --convert-to",{"type":46,"tag":564,"props":592,"children":593},{"style":577},[594],{"type":52,"value":595}," pdf",{"type":46,"tag":564,"props":597,"children":598},{"style":577},[599],{"type":52,"value":600}," output.docx\n",{"type":46,"tag":564,"props":602,"children":604},{"class":566,"line":603},2,[605,610,615,620,626,631],{"type":46,"tag":564,"props":606,"children":607},{"style":571},[608],{"type":52,"value":609},"pdftoppm",{"type":46,"tag":564,"props":611,"children":612},{"style":577},[613],{"type":52,"value":614}," -jpeg",{"type":46,"tag":564,"props":616,"children":617},{"style":577},[618],{"type":52,"value":619}," -r",{"type":46,"tag":564,"props":621,"children":623},{"style":622},"--shiki-light:#F76D47;--shiki-default:#F78C6C;--shiki-dark:#F78C6C",[624],{"type":52,"value":625}," 100",{"type":46,"tag":564,"props":627,"children":628},{"style":577},[629],{"type":52,"value":630}," output.pdf",{"type":46,"tag":564,"props":632,"children":633},{"style":577},[634],{"type":52,"value":635}," page\n",{"type":46,"tag":564,"props":637,"children":639},{"class":566,"line":638},3,[640,645,650,656,661],{"type":46,"tag":564,"props":641,"children":642},{"style":571},[643],{"type":52,"value":644},"ls",{"type":46,"tag":564,"props":646,"children":647},{"style":577},[648],{"type":52,"value":649}," page-",{"type":46,"tag":564,"props":651,"children":653},{"style":652},"--shiki-light:#90A4AE;--shiki-default:#EEFFFF;--shiki-dark:#BABED8",[654],{"type":52,"value":655},"*",{"type":46,"tag":564,"props":657,"children":658},{"style":577},[659],{"type":52,"value":660},".jpg",{"type":46,"tag":564,"props":662,"children":664},{"style":663},"--shiki-light:#90A4AE;--shiki-light-font-style:italic;--shiki-default:#546E7A;--shiki-default-font-style:italic;--shiki-dark:#676E95;--shiki-dark-font-style:italic",[665],{"type":52,"value":666},"   # then Read the images\n",{"type":46,"tag":55,"props":668,"children":669},{},[670,675,677,683,685,691],{"type":46,"tag":61,"props":671,"children":673},{"className":672},[],[674],{"type":52,"value":609},{"type":52,"value":676}," zero-pads page numbers to the width of the page count (",{"type":46,"tag":61,"props":678,"children":680},{"className":679},[],[681],{"type":52,"value":682},"page-01.jpg",{"type":52,"value":684},"…",{"type":46,"tag":61,"props":686,"children":688},{"className":687},[],[689],{"type":52,"value":690},"page-12.jpg",{"type":52,"value":692},").",{"type":46,"tag":195,"props":694,"children":696},{"id":695},"editing-existing-documents",[697],{"type":52,"value":698},"Editing existing documents",{"type":46,"tag":55,"props":700,"children":701},{},[702,704,710,712,718],{"type":52,"value":703},"Legacy ",{"type":46,"tag":61,"props":705,"children":707},{"className":706},[],[708],{"type":52,"value":709},".doc",{"type":52,"value":711}," files must be converted first: ",{"type":46,"tag":61,"props":713,"children":715},{"className":714},[],[716],{"type":52,"value":717},"python scripts\u002Foffice\u002Fsoffice.py --headless --convert-to docx file.doc",{"type":52,"value":369},{"type":46,"tag":553,"props":720,"children":722},{"className":555,"code":721,"language":557,"meta":558,"style":558},"unzip -q doc.docx -d unpacked\u002F\nfind unpacked -type l -delete   # strip symlink entries — docx from external parties is untrusted\npython scripts\u002Fmerge_runs.py unpacked\u002F   # coalesce fragmented runs so text is findable\n# edit unpacked\u002Fword\u002Fdocument.xml in place — do NOT reformat or pretty-print\n(cd unpacked && rm -f ..\u002Fout.docx && zip -Xr ..\u002Fout.docx .)\npython scripts\u002Foffice\u002Fvalidate.py out.docx --original doc.docx   # XSD checks; --auto-repair fixes common issues\n# redlining? add --author \"\u003Cthe name you redlined under>\" to check every edit is tracked\n",[723],{"type":46,"tag":61,"props":724,"children":725},{"__ignoreMap":558},[726,753,786,808,817,885,917],{"type":46,"tag":564,"props":727,"children":728},{"class":566,"line":567},[729,733,738,743,748],{"type":46,"tag":564,"props":730,"children":731},{"style":571},[732],{"type":52,"value":144},{"type":46,"tag":564,"props":734,"children":735},{"style":577},[736],{"type":52,"value":737}," -q",{"type":46,"tag":564,"props":739,"children":740},{"style":577},[741],{"type":52,"value":742}," doc.docx",{"type":46,"tag":564,"props":744,"children":745},{"style":577},[746],{"type":52,"value":747}," -d",{"type":46,"tag":564,"props":749,"children":750},{"style":577},[751],{"type":52,"value":752}," unpacked\u002F\n",{"type":46,"tag":564,"props":754,"children":755},{"class":566,"line":603},[756,761,766,771,776,781],{"type":46,"tag":564,"props":757,"children":758},{"style":571},[759],{"type":52,"value":760},"find",{"type":46,"tag":564,"props":762,"children":763},{"style":577},[764],{"type":52,"value":765}," unpacked",{"type":46,"tag":564,"props":767,"children":768},{"style":577},[769],{"type":52,"value":770}," -type",{"type":46,"tag":564,"props":772,"children":773},{"style":577},[774],{"type":52,"value":775}," l",{"type":46,"tag":564,"props":777,"children":778},{"style":577},[779],{"type":52,"value":780}," -delete",{"type":46,"tag":564,"props":782,"children":783},{"style":663},[784],{"type":52,"value":785},"   # strip symlink entries — docx from external parties is untrusted\n",{"type":46,"tag":564,"props":787,"children":788},{"class":566,"line":638},[789,793,798,803],{"type":46,"tag":564,"props":790,"children":791},{"style":571},[792],{"type":52,"value":574},{"type":46,"tag":564,"props":794,"children":795},{"style":577},[796],{"type":52,"value":797}," scripts\u002Fmerge_runs.py",{"type":46,"tag":564,"props":799,"children":800},{"style":577},[801],{"type":52,"value":802}," unpacked\u002F",{"type":46,"tag":564,"props":804,"children":805},{"style":663},[806],{"type":52,"value":807},"   # coalesce fragmented runs so text is findable\n",{"type":46,"tag":564,"props":809,"children":811},{"class":566,"line":810},4,[812],{"type":46,"tag":564,"props":813,"children":814},{"style":663},[815],{"type":52,"value":816},"# edit unpacked\u002Fword\u002Fdocument.xml in place — do NOT reformat or pretty-print\n",{"type":46,"tag":564,"props":818,"children":820},{"class":566,"line":819},5,[821,827,833,837,842,847,852,857,861,866,871,875,880],{"type":46,"tag":564,"props":822,"children":824},{"style":823},"--shiki-light:#39ADB5;--shiki-default:#89DDFF;--shiki-dark:#89DDFF",[825],{"type":52,"value":826},"(",{"type":46,"tag":564,"props":828,"children":830},{"style":829},"--shiki-light:#6182B8;--shiki-default:#82AAFF;--shiki-dark:#82AAFF",[831],{"type":52,"value":832},"cd",{"type":46,"tag":564,"props":834,"children":835},{"style":577},[836],{"type":52,"value":765},{"type":46,"tag":564,"props":838,"children":839},{"style":823},[840],{"type":52,"value":841}," &&",{"type":46,"tag":564,"props":843,"children":844},{"style":571},[845],{"type":52,"value":846}," rm",{"type":46,"tag":564,"props":848,"children":849},{"style":577},[850],{"type":52,"value":851}," -f",{"type":46,"tag":564,"props":853,"children":854},{"style":577},[855],{"type":52,"value":856}," ..\u002Fout.docx",{"type":46,"tag":564,"props":858,"children":859},{"style":823},[860],{"type":52,"value":841},{"type":46,"tag":564,"props":862,"children":863},{"style":571},[864],{"type":52,"value":865}," zip",{"type":46,"tag":564,"props":867,"children":868},{"style":577},[869],{"type":52,"value":870}," -Xr",{"type":46,"tag":564,"props":872,"children":873},{"style":577},[874],{"type":52,"value":856},{"type":46,"tag":564,"props":876,"children":877},{"style":577},[878],{"type":52,"value":879}," .",{"type":46,"tag":564,"props":881,"children":882},{"style":823},[883],{"type":52,"value":884},")\n",{"type":46,"tag":564,"props":886,"children":888},{"class":566,"line":887},6,[889,893,898,903,908,912],{"type":46,"tag":564,"props":890,"children":891},{"style":571},[892],{"type":52,"value":574},{"type":46,"tag":564,"props":894,"children":895},{"style":577},[896],{"type":52,"value":897}," scripts\u002Foffice\u002Fvalidate.py",{"type":46,"tag":564,"props":899,"children":900},{"style":577},[901],{"type":52,"value":902}," out.docx",{"type":46,"tag":564,"props":904,"children":905},{"style":577},[906],{"type":52,"value":907}," --original",{"type":46,"tag":564,"props":909,"children":910},{"style":577},[911],{"type":52,"value":742},{"type":46,"tag":564,"props":913,"children":914},{"style":663},[915],{"type":52,"value":916},"   # XSD checks; --auto-repair fixes common issues\n",{"type":46,"tag":564,"props":918,"children":920},{"class":566,"line":919},7,[921],{"type":46,"tag":564,"props":922,"children":923},{"style":663},[924],{"type":52,"value":925},"# redlining? add --author \"\u003Cthe name you redlined under>\" to check every edit is tracked\n",{"type":46,"tag":55,"props":927,"children":928},{},[929,931,937,939,945,947,952,954,959,961,967],{"type":52,"value":930},"Word splits text across many ",{"type":46,"tag":61,"props":932,"children":934},{"className":933},[],[935],{"type":52,"value":936},"\u003Cw:r>",{"type":52,"value":938}," runs (revision ids, spell-check markers), so a phrase you can see in the document often doesn't exist as a contiguous string in the XML. ",{"type":46,"tag":61,"props":940,"children":942},{"className":941},[],[943],{"type":52,"value":944},"merge_runs.py",{"type":52,"value":946}," merges adjacent identically-formatted runs in ",{"type":46,"tag":61,"props":948,"children":950},{"className":949},[],[951],{"type":52,"value":152},{"type":52,"value":953}," without changing content or rendering; it also accepts a ",{"type":46,"tag":61,"props":955,"children":957},{"className":956},[],[958],{"type":52,"value":66},{"type":52,"value":960}," directly (",{"type":46,"tag":61,"props":962,"children":964},{"className":963},[],[965],{"type":52,"value":966},"python scripts\u002Fmerge_runs.py doc.docx -o merged.docx",{"type":52,"value":692},{"type":46,"tag":55,"props":969,"children":970},{},[971,976,978,984,986,992,994,1000,1002,1008,1010,1015,1016,1021,1023,1029,1030,1036,1037,1043,1045,1050,1052,1058,1060,1066,1068,1074,1076,1081,1083,1089],{"type":46,"tag":104,"props":972,"children":973},{},[974],{"type":52,"value":975},"Tracked changes:",{"type":52,"value":977}," when redlining, validate with ",{"type":46,"tag":61,"props":979,"children":981},{"className":980},[],[982],{"type":52,"value":983},"--author \"\u003Cthe name you redlined under>\"",{"type":52,"value":985}," (needs ",{"type":46,"tag":61,"props":987,"children":989},{"className":988},[],[990],{"type":52,"value":991},"--original",{"type":52,"value":993},") — it reports any text you changed without a ",{"type":46,"tag":61,"props":995,"children":997},{"className":996},[],[998],{"type":52,"value":999},"\u003Cw:ins>",{"type":52,"value":1001},"\u002F",{"type":46,"tag":61,"props":1003,"children":1005},{"className":1004},[],[1006],{"type":52,"value":1007},"\u003Cw:del>",{"type":52,"value":1009}," around it, which is easy to do by accident and invisible in the accepted view. Wrap runs in ",{"type":46,"tag":61,"props":1011,"children":1013},{"className":1012},[],[1014],{"type":52,"value":999},{"type":52,"value":1001},{"type":46,"tag":61,"props":1017,"children":1019},{"className":1018},[],[1020],{"type":52,"value":1007},{"type":52,"value":1022}," with ",{"type":46,"tag":61,"props":1024,"children":1026},{"className":1025},[],[1027],{"type":52,"value":1028},"w:id",{"type":52,"value":399},{"type":46,"tag":61,"props":1031,"children":1033},{"className":1032},[],[1034],{"type":52,"value":1035},"w:author",{"type":52,"value":399},{"type":46,"tag":61,"props":1038,"children":1040},{"className":1039},[],[1041],{"type":52,"value":1042},"w:date",{"type":52,"value":1044}," attributes. Inside ",{"type":46,"tag":61,"props":1046,"children":1048},{"className":1047},[],[1049],{"type":52,"value":1007},{"type":52,"value":1051},", the text element is ",{"type":46,"tag":61,"props":1053,"children":1055},{"className":1054},[],[1056],{"type":52,"value":1057},"\u003Cw:delText>",{"type":52,"value":1059},", not ",{"type":46,"tag":61,"props":1061,"children":1063},{"className":1062},[],[1064],{"type":52,"value":1065},"\u003Cw:t>",{"type":52,"value":1067},". A deleted paragraph mark (",{"type":46,"tag":61,"props":1069,"children":1071},{"className":1070},[],[1072],{"type":52,"value":1073},"\u003Cw:pPr>\u003Cw:rPr>\u003Cw:del w:id=\"..\" w:author=\"..\" w:date=\"..\"\u002F>\u003C\u002Fw:rPr>\u003C\u002Fw:pPr>",{"type":52,"value":1075},") means \"merge this paragraph into the next\" — so deleting a paragraph outright is that plus a ",{"type":46,"tag":61,"props":1077,"children":1079},{"className":1078},[],[1080],{"type":52,"value":1007},{"type":52,"value":1082}," around every run. The ",{"type":46,"tag":61,"props":1084,"children":1086},{"className":1085},[],[1087],{"type":52,"value":1088},"\u003Cw:del\u002F>",{"type":52,"value":1090}," must come before the rPr's other children; their order is schema-enforced.",{"type":46,"tag":55,"props":1092,"children":1093},{},[1094,1096,1102],{"type":52,"value":1095},"To produce a clean copy with all tracked changes accepted: ",{"type":46,"tag":61,"props":1097,"children":1099},{"className":1098},[],[1100],{"type":52,"value":1101},"python scripts\u002Faccept_changes.py in.docx out.docx",{"type":52,"value":369},{"type":46,"tag":55,"props":1104,"children":1105},{},[1106,1108,1114,1116,1122,1124,1130],{"type":52,"value":1107},"Accepting a deleted paragraph mark should join that paragraph to the one below it, so a paragraph whose runs are ",{"type":46,"tag":1109,"props":1110,"children":1111},"em",{},[1112],{"type":52,"value":1113},"all",{"type":52,"value":1115}," deleted vanishes. Word does this; ",{"type":46,"tag":61,"props":1117,"children":1119},{"className":1118},[],[1120],{"type":52,"value":1121},"accept_changes.py",{"type":52,"value":1123}," and ",{"type":46,"tag":61,"props":1125,"children":1127},{"className":1126},[],[1128],{"type":52,"value":1129},"pandoc --track-changes=accept",{"type":52,"value":1131}," don't always. Both fail the same way — they strip the deleted text but leave the emptied paragraph behind, which reads as a stray empty bullet when it was auto-numbered:",{"type":46,"tag":236,"props":1133,"children":1134},{},[1135,1145],{"type":46,"tag":240,"props":1136,"children":1137},{},[1138,1143],{"type":46,"tag":61,"props":1139,"children":1141},{"className":1140},[],[1142],{"type":52,"value":1129},{"type":52,"value":1144}," never joins the paragraphs.",{"type":46,"tag":240,"props":1146,"children":1147},{},[1148,1153],{"type":46,"tag":61,"props":1149,"children":1151},{"className":1150},[],[1152],{"type":52,"value":1121},{"type":52,"value":1154}," (LibreOffice) joins them correctly, except when the deleted paragraph is followed by an empty spacer paragraph.",{"type":46,"tag":55,"props":1156,"children":1157},{},[1158],{"type":52,"value":1159},"An empty bullet in either view is an artifact of that view, not a defect in the document. Check paragraph deletions in the XML.",{"type":46,"tag":195,"props":1161,"children":1163},{"id":1162},"comments",[1164],{"type":52,"value":1165},"Comments",{"type":46,"tag":55,"props":1167,"children":1168},{},[1169,1171,1177,1179,1184],{"type":52,"value":1170},"Comments require six cross-linked files. Use the helper — directory mode when you'll also be editing ",{"type":46,"tag":61,"props":1172,"children":1174},{"className":1173},[],[1175],{"type":52,"value":1176},"document.xml",{"type":52,"value":1178}," (saves an unzip\u002Frezip cycle), ",{"type":46,"tag":61,"props":1180,"children":1182},{"className":1181},[],[1183],{"type":52,"value":66},{"type":52,"value":1185},"-direct mode otherwise:",{"type":46,"tag":553,"props":1187,"children":1189},{"className":555,"code":1188,"language":557,"meta":558,"style":558},"# Against an already-unpacked directory (preferred when also placing markers)\npython scripts\u002Fcomment.py unpacked\u002F \"Fees & expenses cap is too low\"\npython scripts\u002Fcomment.py unpacked\u002F \"Agreed\" --parent 0\n\n# Against a .docx directly\npython scripts\u002Fcomment.py contract.docx \"This cap is too low\" -o annotated.docx\n",[1190],{"type":46,"tag":61,"props":1191,"children":1192},{"__ignoreMap":558},[1193,1201,1232,1271,1280,1288],{"type":46,"tag":564,"props":1194,"children":1195},{"class":566,"line":567},[1196],{"type":46,"tag":564,"props":1197,"children":1198},{"style":663},[1199],{"type":52,"value":1200},"# Against an already-unpacked directory (preferred when also placing markers)\n",{"type":46,"tag":564,"props":1202,"children":1203},{"class":566,"line":603},[1204,1208,1213,1217,1222,1227],{"type":46,"tag":564,"props":1205,"children":1206},{"style":571},[1207],{"type":52,"value":574},{"type":46,"tag":564,"props":1209,"children":1210},{"style":577},[1211],{"type":52,"value":1212}," scripts\u002Fcomment.py",{"type":46,"tag":564,"props":1214,"children":1215},{"style":577},[1216],{"type":52,"value":802},{"type":46,"tag":564,"props":1218,"children":1219},{"style":823},[1220],{"type":52,"value":1221}," \"",{"type":46,"tag":564,"props":1223,"children":1224},{"style":577},[1225],{"type":52,"value":1226},"Fees & expenses cap is too low",{"type":46,"tag":564,"props":1228,"children":1229},{"style":823},[1230],{"type":52,"value":1231},"\"\n",{"type":46,"tag":564,"props":1233,"children":1234},{"class":566,"line":638},[1235,1239,1243,1247,1251,1256,1261,1266],{"type":46,"tag":564,"props":1236,"children":1237},{"style":571},[1238],{"type":52,"value":574},{"type":46,"tag":564,"props":1240,"children":1241},{"style":577},[1242],{"type":52,"value":1212},{"type":46,"tag":564,"props":1244,"children":1245},{"style":577},[1246],{"type":52,"value":802},{"type":46,"tag":564,"props":1248,"children":1249},{"style":823},[1250],{"type":52,"value":1221},{"type":46,"tag":564,"props":1252,"children":1253},{"style":577},[1254],{"type":52,"value":1255},"Agreed",{"type":46,"tag":564,"props":1257,"children":1258},{"style":823},[1259],{"type":52,"value":1260},"\"",{"type":46,"tag":564,"props":1262,"children":1263},{"style":577},[1264],{"type":52,"value":1265}," --parent",{"type":46,"tag":564,"props":1267,"children":1268},{"style":622},[1269],{"type":52,"value":1270}," 0\n",{"type":46,"tag":564,"props":1272,"children":1273},{"class":566,"line":810},[1274],{"type":46,"tag":564,"props":1275,"children":1277},{"emptyLinePlaceholder":1276},true,[1278],{"type":52,"value":1279},"\n",{"type":46,"tag":564,"props":1281,"children":1282},{"class":566,"line":819},[1283],{"type":46,"tag":564,"props":1284,"children":1285},{"style":663},[1286],{"type":52,"value":1287},"# Against a .docx directly\n",{"type":46,"tag":564,"props":1289,"children":1290},{"class":566,"line":887},[1291,1295,1299,1304,1308,1313,1317,1322],{"type":46,"tag":564,"props":1292,"children":1293},{"style":571},[1294],{"type":52,"value":574},{"type":46,"tag":564,"props":1296,"children":1297},{"style":577},[1298],{"type":52,"value":1212},{"type":46,"tag":564,"props":1300,"children":1301},{"style":577},[1302],{"type":52,"value":1303}," contract.docx",{"type":46,"tag":564,"props":1305,"children":1306},{"style":823},[1307],{"type":52,"value":1221},{"type":46,"tag":564,"props":1309,"children":1310},{"style":577},[1311],{"type":52,"value":1312},"This cap is too low",{"type":46,"tag":564,"props":1314,"children":1315},{"style":823},[1316],{"type":52,"value":1260},{"type":46,"tag":564,"props":1318,"children":1319},{"style":577},[1320],{"type":52,"value":1321}," -o",{"type":46,"tag":564,"props":1323,"children":1324},{"style":577},[1325],{"type":52,"value":1326}," annotated.docx\n",{"type":46,"tag":55,"props":1328,"children":1329},{},[1330,1332,1338,1339,1345,1346,1352,1353,1359,1361,1367,1368,1374,1375,1381,1383,1388],{"type":52,"value":1331},"The script writes ",{"type":46,"tag":61,"props":1333,"children":1335},{"className":1334},[],[1336],{"type":52,"value":1337},"comments.xml",{"type":52,"value":399},{"type":46,"tag":61,"props":1340,"children":1342},{"className":1341},[],[1343],{"type":52,"value":1344},"commentsExtended.xml",{"type":52,"value":399},{"type":46,"tag":61,"props":1347,"children":1349},{"className":1348},[],[1350],{"type":52,"value":1351},"commentsIds.xml",{"type":52,"value":399},{"type":46,"tag":61,"props":1354,"children":1356},{"className":1355},[],[1357],{"type":52,"value":1358},"commentsExtensible.xml",{"type":52,"value":1360},", the relationships, and the content-type overrides. Comment IDs are auto-assigned. It then prints the ",{"type":46,"tag":61,"props":1362,"children":1364},{"className":1363},[],[1365],{"type":52,"value":1366},"\u003Cw:commentRangeStart>",{"type":52,"value":1001},{"type":46,"tag":61,"props":1369,"children":1371},{"className":1370},[],[1372],{"type":52,"value":1373},"\u003Cw:commentRangeEnd>",{"type":52,"value":1001},{"type":46,"tag":61,"props":1376,"children":1378},{"className":1377},[],[1379],{"type":52,"value":1380},"\u003Cw:commentReference>",{"type":52,"value":1382}," snippet to add to ",{"type":46,"tag":61,"props":1384,"children":1386},{"className":1385},[],[1387],{"type":52,"value":152},{"type":52,"value":1389}," so the comment anchors to specific text — until you place those markers, the comment exists but is not visible.",{"type":46,"tag":195,"props":1391,"children":1393},{"id":1392},"dependencies",[1394],{"type":52,"value":1395},"Dependencies",{"type":46,"tag":55,"props":1397,"children":1398},{},[1399,1404,1406,1411,1413,1419,1421,1427,1429,1434],{"type":46,"tag":61,"props":1400,"children":1402},{"className":1401},[],[1403],{"type":52,"value":4},{"type":52,"value":1405}," (npm, preinstalled — install only if ",{"type":46,"tag":61,"props":1407,"children":1409},{"className":1408},[],[1410],{"type":52,"value":224},{"type":52,"value":1412}," fails) · ",{"type":46,"tag":61,"props":1414,"children":1416},{"className":1415},[],[1417],{"type":52,"value":1418},"pandoc",{"type":52,"value":1420}," · LibreOffice (",{"type":46,"tag":61,"props":1422,"children":1424},{"className":1423},[],[1425],{"type":52,"value":1426},"soffice",{"type":52,"value":1428},") · ",{"type":46,"tag":61,"props":1430,"children":1432},{"className":1431},[],[1433],{"type":52,"value":609},{"type":52,"value":1435}," (Poppler)",{"type":46,"tag":1437,"props":1438,"children":1439},"style",{},[1440],{"type":52,"value":1441},"html .light .shiki span {color: var(--shiki-light);background: var(--shiki-light-bg);font-style: var(--shiki-light-font-style);font-weight: var(--shiki-light-font-weight);text-decoration: var(--shiki-light-text-decoration);}html.light .shiki span {color: var(--shiki-light);background: var(--shiki-light-bg);font-style: var(--shiki-light-font-style);font-weight: var(--shiki-light-font-weight);text-decoration: var(--shiki-light-text-decoration);}html .default .shiki span {color: var(--shiki-default);background: var(--shiki-default-bg);font-style: var(--shiki-default-font-style);font-weight: var(--shiki-default-font-weight);text-decoration: var(--shiki-default-text-decoration);}html .shiki span {color: var(--shiki-default);background: var(--shiki-default-bg);font-style: var(--shiki-default-font-style);font-weight: var(--shiki-default-font-weight);text-decoration: var(--shiki-default-text-decoration);}html .dark .shiki span {color: var(--shiki-dark);background: var(--shiki-dark-bg);font-style: var(--shiki-dark-font-style);font-weight: var(--shiki-dark-font-weight);text-decoration: var(--shiki-dark-text-decoration);}html.dark .shiki span {color: var(--shiki-dark);background: var(--shiki-dark-bg);font-style: var(--shiki-dark-font-style);font-weight: var(--shiki-dark-font-weight);text-decoration: var(--shiki-dark-text-decoration);}",{"items":1443,"total":1549},[1444,1463,1477,1489,1508,1521,1529],{"slug":1445,"name":1445,"fn":1446,"description":1447,"org":1448,"tags":1449,"stars":28,"repoUrl":29,"updatedAt":1462},"algorithmic-art","create algorithmic art with p5.js","Creating algorithmic art using p5.js with seeded randomness and interactive parameter exploration. Use this when users request creating art using code, generative art, algorithmic art, flow fields, or particle systems. Create original algorithmic art rather than copying existing artists' work to avoid copyright violations.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[1450,1453,1456,1459],{"name":1451,"slug":1452,"type":16},"Creative","creative",{"name":1454,"slug":1455,"type":16},"Design","design",{"name":1457,"slug":1458,"type":16},"Generative Art","generative-art",{"name":1460,"slug":1461,"type":16},"JavaScript","javascript","2026-04-06T17:56:15.455818",{"slug":1464,"name":1464,"fn":1465,"description":1466,"org":1467,"tags":1468,"stars":28,"repoUrl":29,"updatedAt":1476},"brand-guidelines","apply Anthropic brand colors and typography","Applies Anthropic's official brand colors and typography to any sort of artifact that may benefit from having Anthropic's look-and-feel. Use it when brand colors or style guidelines, visual formatting, or company design standards apply.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[1469,1472,1473],{"name":1470,"slug":1471,"type":16},"Branding","branding",{"name":1454,"slug":1455,"type":16},{"name":1474,"slug":1475,"type":16},"Typography","typography","2026-04-06T17:56:05.042852",{"slug":1478,"name":1478,"fn":1479,"description":1480,"org":1481,"tags":1482,"stars":28,"repoUrl":29,"updatedAt":1488},"canvas-design","create posters and visual art as PNG or PDF","Create beautiful visual art in .png and .pdf documents using design philosophy. You should use this skill when the user asks to create a poster, piece of art, design, or other static piece. Create original visual designs, never copying existing artists' work to avoid copyright violations.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[1483,1484,1485],{"name":1451,"slug":1452,"type":16},{"name":1454,"slug":1455,"type":16},{"name":1486,"slug":1487,"type":16},"PDF","pdf","2026-04-06T17:56:03.794732",{"slug":1490,"name":1490,"fn":1491,"description":1492,"org":1493,"tags":1494,"stars":28,"repoUrl":29,"updatedAt":1507},"claude-api","build apps with the Claude API","Reference for the Claude API \u002F Anthropic SDK — model ids, pricing, params, streaming, tool use, MCP, agents, caching, token counting, model migration.\nTRIGGER — read BEFORE opening the target file; don't skip because it \"looks like a one-liner\" — whenever: the prompt names Claude\u002FAnthropic in any form (Claude, Anthropic, Fable, Opus, Sonnet, Haiku, `anthropic`, `@anthropic-ai`, `claude-*`, `us.anthropic.*`, `[1m]`); the user asks about an LLM (pricing\u002Fmodel choice\u002Flimits\u002Fcaching) — never answer from memory; OR the task is LLM-shaped with provider unstated (agent\u002FMCP\u002Ftool-definition\u002Fmulti-agent\u002FRAG\u002FLLM-judge\u002Fcomputer-use; generate\u002Fsummarize\u002Fextract\u002Fclassify\u002Frewrite\u002Fconverse over NL; debugging refusals\u002Fcutoffs\u002Fstreaming\u002Ftool-calls\u002Ftokens).\nSKIP only when another provider is being worked on (overrides all triggers): OpenAI\u002FGPT\u002FGemini\u002FLlama\u002FMistral\u002FCohere\u002FOllama named in the query; OR `grep -rE 'openai|langchain_openai|google.generativeai|genai|mistralai|cohere|ollama'` over the project hits (run this grep FIRST if no provider named — don't Read the file).",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[1495,1498,1499,1502,1504],{"name":1496,"slug":1497,"type":16},"Agents","agents",{"name":9,"slug":8,"type":16},{"name":1500,"slug":1501,"type":16},"Anthropic SDK","anthropic-sdk",{"name":1503,"slug":1490,"type":16},"Claude API",{"name":1505,"slug":1506,"type":16},"LLM","llm","2026-07-28T05:36:08.213335",{"slug":1509,"name":1509,"fn":1510,"description":1511,"org":1512,"tags":1513,"stars":28,"repoUrl":29,"updatedAt":1520},"doc-coauthoring","co-author documentation and technical specs","Guide users through a structured workflow for co-authoring documentation. Use when user wants to write documentation, proposals, technical specs, decision docs, or similar structured content. This workflow helps users efficiently transfer context, refine content through iteration, and verify the doc works for readers. Trigger when user mentions writing docs, creating proposals, drafting specs, or similar documentation tasks.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[1514,1517],{"name":1515,"slug":1516,"type":16},"Documentation","documentation",{"name":1518,"slug":1519,"type":16},"Technical Writing","technical-writing","2026-04-06T17:56:14.18897",{"slug":4,"name":4,"fn":5,"description":6,"org":1522,"tags":1523,"stars":28,"repoUrl":29,"updatedAt":30},{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[1524,1525,1526,1527,1528],{"name":18,"slug":19,"type":16},{"name":24,"slug":4,"type":16},{"name":21,"slug":22,"type":16},{"name":14,"slug":15,"type":16},{"name":26,"slug":27,"type":16},{"slug":1530,"name":1530,"fn":1531,"description":1532,"org":1533,"tags":1534,"stars":28,"repoUrl":29,"updatedAt":1548},"frontend-design","design production-grade frontend interfaces","Guidance for distinctive, intentional visual design when building new UI or reshaping an existing one. Helps with aesthetic direction, typography, and making choices that don't read as templated defaults.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[1535,1536,1539,1542,1545],{"name":1454,"slug":1455,"type":16},{"name":1537,"slug":1538,"type":16},"Frontend","frontend",{"name":1540,"slug":1541,"type":16},"React","react",{"name":1543,"slug":1544,"type":16},"Tailwind CSS","tailwind-css",{"name":1546,"slug":1547,"type":16},"UI Components","ui-components","2026-04-06T17:56:16.723469",17,{"items":1551,"total":1666},[1552,1559,1565,1571,1579,1584,1592,1600,1614,1629,1637,1650],{"slug":1445,"name":1445,"fn":1446,"description":1447,"org":1553,"tags":1554,"stars":28,"repoUrl":29,"updatedAt":1462},{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[1555,1556,1557,1558],{"name":1451,"slug":1452,"type":16},{"name":1454,"slug":1455,"type":16},{"name":1457,"slug":1458,"type":16},{"name":1460,"slug":1461,"type":16},{"slug":1464,"name":1464,"fn":1465,"description":1466,"org":1560,"tags":1561,"stars":28,"repoUrl":29,"updatedAt":1476},{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[1562,1563,1564],{"name":1470,"slug":1471,"type":16},{"name":1454,"slug":1455,"type":16},{"name":1474,"slug":1475,"type":16},{"slug":1478,"name":1478,"fn":1479,"description":1480,"org":1566,"tags":1567,"stars":28,"repoUrl":29,"updatedAt":1488},{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[1568,1569,1570],{"name":1451,"slug":1452,"type":16},{"name":1454,"slug":1455,"type":16},{"name":1486,"slug":1487,"type":16},{"slug":1490,"name":1490,"fn":1491,"description":1492,"org":1572,"tags":1573,"stars":28,"repoUrl":29,"updatedAt":1507},{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[1574,1575,1576,1577,1578],{"name":1496,"slug":1497,"type":16},{"name":9,"slug":8,"type":16},{"name":1500,"slug":1501,"type":16},{"name":1503,"slug":1490,"type":16},{"name":1505,"slug":1506,"type":16},{"slug":1509,"name":1509,"fn":1510,"description":1511,"org":1580,"tags":1581,"stars":28,"repoUrl":29,"updatedAt":1520},{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[1582,1583],{"name":1515,"slug":1516,"type":16},{"name":1518,"slug":1519,"type":16},{"slug":4,"name":4,"fn":5,"description":6,"org":1585,"tags":1586,"stars":28,"repoUrl":29,"updatedAt":30},{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[1587,1588,1589,1590,1591],{"name":18,"slug":19,"type":16},{"name":24,"slug":4,"type":16},{"name":21,"slug":22,"type":16},{"name":14,"slug":15,"type":16},{"name":26,"slug":27,"type":16},{"slug":1530,"name":1530,"fn":1531,"description":1532,"org":1593,"tags":1594,"stars":28,"repoUrl":29,"updatedAt":1548},{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[1595,1596,1597,1598,1599],{"name":1454,"slug":1455,"type":16},{"name":1537,"slug":1538,"type":16},{"name":1540,"slug":1541,"type":16},{"name":1543,"slug":1544,"type":16},{"name":1546,"slug":1547,"type":16},{"slug":1601,"name":1601,"fn":1602,"description":1603,"org":1604,"tags":1605,"stars":28,"repoUrl":29,"updatedAt":1613},"internal-comms","write internal company communications","A set of resources to help me write all kinds of internal communications, using the formats that my company likes to use. Claude should use this skill whenever asked to write some sort of internal communications (status reports, leadership updates, 3P updates, company newsletters, FAQs, incident reports, project updates, etc.).",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[1606,1609,1610],{"name":1607,"slug":1608,"type":16},"Communications","communications",{"name":14,"slug":15,"type":16},{"name":1611,"slug":1612,"type":16},"Writing","writing","2026-04-06T17:56:20.695522",{"slug":1615,"name":1615,"fn":1616,"description":1617,"org":1618,"tags":1619,"stars":28,"repoUrl":29,"updatedAt":1628},"mcp-builder","build MCP servers","Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node\u002FTypeScript (MCP SDK).",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[1620,1621,1624,1625],{"name":1496,"slug":1497,"type":16},{"name":1622,"slug":1623,"type":16},"API Development","api-development",{"name":1505,"slug":1506,"type":16},{"name":1626,"slug":1627,"type":16},"MCP","mcp","2026-04-06T17:56:10.357665",{"slug":1487,"name":1487,"fn":1630,"description":1631,"org":1632,"tags":1633,"stars":28,"repoUrl":29,"updatedAt":1636},"read edit and manipulate PDF files","Use this skill whenever the user wants to do anything with PDF files. This includes reading or extracting text\u002Ftables from PDFs, combining or merging multiple PDFs into one, splitting PDFs apart, rotating pages, adding watermarks, creating new PDFs, filling PDF forms, encrypting\u002Fdecrypting PDFs, extracting images, and OCR on scanned PDFs to make them searchable. If the user mentions a .pdf file or asks to produce one, use this skill.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[1634,1635],{"name":18,"slug":19,"type":16},{"name":1486,"slug":1487,"type":16},"2026-04-06T17:56:02.483316",{"slug":1638,"name":1638,"fn":1639,"description":1640,"org":1641,"tags":1642,"stars":28,"repoUrl":29,"updatedAt":1649},"pptx","create and edit PowerPoint presentations","Use this skill any time a .pptx or .potx file is involved in any way — as input, output, or both. This includes: creating slide decks, pitch decks, or presentations; reading, parsing, or extracting text from any .pptx or .potx file (even if the extracted content will be used elsewhere, like in an email or summary); editing, modifying, or updating existing presentations; combining or splitting slide files; working with templates (.potx), layouts, speaker notes, or comments. Trigger whenever the user mentions \"deck,\" \"slides,\" \"presentation,\" or references a .pptx or .potx filename, regardless of what they plan to do with the content afterward. If a .pptx or .potx file needs to be opened, created, or touched, use this skill.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[1643,1646],{"name":1644,"slug":1645,"type":16},"PowerPoint","powerpoint",{"name":1647,"slug":1648,"type":16},"Presentations","presentations","2026-07-18T05:16:24.1471",{"slug":1651,"name":1651,"fn":1652,"description":1653,"org":1654,"tags":1655,"stars":28,"repoUrl":29,"updatedAt":1665},"skill-creator","create and optimize agent skills","Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[1656,1657,1658,1661,1664],{"name":1496,"slug":1497,"type":16},{"name":1515,"slug":1516,"type":16},{"name":1659,"slug":1660,"type":16},"Evals","evals",{"name":1662,"slug":1663,"type":16},"Performance","performance",{"name":1518,"slug":1519,"type":16},"2026-04-19T06:45:40.804",490]