[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill-anthropic-xlsx":3,"mdc--h0d34q-key":35,"related-org-anthropic-xlsx":1327,"related-repo-anthropic-xlsx":1514},{"slug":4,"name":4,"fn":5,"description":6,"org":7,"tags":12,"stars":23,"repoUrl":24,"updatedAt":25,"license":26,"forks":27,"topics":28,"repo":30,"sourceUrl":33,"mdContent":34},"xlsx","create and edit Excel spreadsheets","Use this skill any time a spreadsheet file is the primary input or output. This means any task where the user wants to: open, read, edit, or fix an existing .xlsx, .xlsm, .xltx, .csv, or .tsv file (e.g., adding columns, computing formulas, formatting, charting, cleaning messy data); create a new spreadsheet from scratch or from other data sources; or convert between tabular file formats. Trigger especially when the user references a spreadsheet file by name or path — even casually (like \"the xlsx in my downloads\") — and wants something done to it or produced from it. Also trigger for cleaning or restructuring messy tabular data files (malformed rows, misplaced headers, junk data) into proper spreadsheets. The deliverable must be a spreadsheet file. Do NOT trigger when the primary deliverable is a Word document, HTML report, standalone Python script, database pipeline, or Google Sheets API integration, even if tabular data is involved.",{"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],{"name":14,"slug":15,"type":16},"Excel","excel","tag",{"name":18,"slug":19,"type":16},"Spreadsheets","spreadsheets",{"name":21,"slug":22,"type":16},"Data Cleaning","data-cleaning",161831,"https:\u002F\u002Fgithub.com\u002Fanthropics\u002Fskills","2026-07-18T05:16:22.148742","Proprietary. LICENSE.txt has complete terms",19131,[29],"agent-skills",{"repoUrl":24,"stars":23,"forks":27,"topics":31,"description":32},[29],"Public repository for Agent Skills","https:\u002F\u002Fgithub.com\u002Fanthropics\u002Fskills\u002Ftree\u002FHEAD\u002Fskills\u002Fxlsx","---\nname: xlsx\ndescription: \"Use this skill any time a spreadsheet file is the primary input or output. This means any task where the user wants to: open, read, edit, or fix an existing .xlsx, .xlsm, .xltx, .csv, or .tsv file (e.g., adding columns, computing formulas, formatting, charting, cleaning messy data); create a new spreadsheet from scratch or from other data sources; or convert between tabular file formats. Trigger especially when the user references a spreadsheet file by name or path — even casually (like \\\"the xlsx in my downloads\\\") — and wants something done to it or produced from it. Also trigger for cleaning or restructuring messy tabular data files (malformed rows, misplaced headers, junk data) into proper spreadsheets. The deliverable must be a spreadsheet file. Do NOT trigger when the primary deliverable is a Word document, HTML report, standalone Python script, database pipeline, or Google Sheets API integration, even if tabular data is involved.\"\nlicense: Proprietary. LICENSE.txt has complete terms\n---\n\n# XLSX creation, editing, and analysis\n\n| Task | Approach |\n|---|---|\n| **Create** or **edit** with formulas\u002Fformatting | `openpyxl` — see gotchas below |\n| **Bulk data** in or out | `pandas` (`read_excel`, `to_excel`) |\n| **Quick look** at a sheet | `markitdown file.xlsx` — `## SheetName` per sheet; reads `.xlsm` too. No cell coordinates, so don't plan edits from it |\n| **Read** a model (formulas *and* values) | two `load_workbook` passes — see gotchas |\n\n> `openpyxl`, `pandas`, and `markitdown` are preinstalled — do not run `pip install` first; write the script and import directly. Only if an import fails (or the `markitdown` command is missing): `pip install` the missing package.\n\n> Script paths below are relative to this skill's directory.\n\n## Requirements for every output\n\n- **Professional font** (Arial, Times New Roman) throughout, unless the user says otherwise.\n- **Zero formula errors.** Never ship while `recalc.py` reports `errors_found`. If you think an error predates you, prove it: load the *original* with `data_only=True` and look at that cell. An error you introduced looks exactly like one you inherited.\n- **Use formulas, never hardcoded results.** Write `sheet['B10'] = '=SUM(B2:B9)'`, not the Python-computed total. The sheet must recalculate when its inputs change.\n- **Follow the user's spec literally.** Exact tab names, exact column headers, and the formula they spelled out. A redesign that computes something else fails, however elegant.\n- **Document every assumption and hardcoded number** where the reader will see it — a cell comment, or an adjacent cell at a table's end. Cite a real source when one exists (`Source: Company 10-K, FY2024, Page 45, Revenue Note, [SEC EDGAR URL]`); when the number came from the user, say so plainly.\n- **A workbook *you create* for someone to fill in** needs a short legend naming which cells to edit, and one example row of realistic values showing the expected format. Never add such a row to a file you were asked to edit.\n- **Editing an existing file: match its conventions exactly.** They override every guideline here. Find its designated input cells first — a distinct font color, fill, or shading marks them — write only there, and leave every existing formula untouched.\n\n## Recalculate (mandatory whenever the file contains formulas)\n\nopenpyxl writes formulas as strings with **no cached values**. Until you recalculate, every\nformula cell reads back as `None` to anything reading cached values — `pandas`,\n`load_workbook(data_only=True)`, and most previewers.\n\n```bash\npython scripts\u002Frecalc.py output.xlsx [timeout_seconds]   # default 30\n```\n\nLibreOffice computes every formula, the file is **rewritten in place**, and you get JSON:\n`status` (`success` | `errors_found`), `total_formulas`, `total_errors`, and an\n`error_summary` naming up to 100 cells per error type (`locations_truncated` says how many it\nwithheld — trust `total_errors`, not the length of the list). Fix what it names and run it\nagain. **JSON with an `error` key instead of a `status` means nothing was recalculated**, and\nonly that case exits non-zero — `errors_found` exits 0, so never treat a clean exit as a clean\nworkbook.\n\n**A green recalc proves your formulas *evaluate*, not that they are *right*.** An off-by-one\nrange or a reference to the wrong row yields a clean, error-free file with wrong numbers.\nWrite 2–3 formulas first and check they pull the values you expect, before building out a grid.\n\n**A workbook that links to another file loses those links** if you re-save it with openpyxl and\nthen recalculate. Such a formula reads `='[1]Returns Analysis'!$B$2` — the `[1]` is an index\ninto the workbook's external-reference list, naming a *separate file on disk*, not a sheet.\nThat file is rarely present here, so the cell's cached value is the only thing holding its\ndata. openpyxl strips that value on save; LibreOffice then has to resolve the reference for\nreal, fails, writes `#NAME?`, and deletes every link. `recalc.py` refuses to run in that state\n— copy those cells' values out of the original before you save over them (`--force` overrides,\nand accepts the loss).\n\n## Choosing formulas that survive verification\n\nLibreOffice implements fewer functions than Excel, and one it cannot evaluate becomes a\nliteral `#NAME?` baked into the file you deliver.\n\n- **Prefer Excel-2007-era functions** — `SUMIFS`, `INDEX`, `MATCH`, `IFERROR`, `SUMPRODUCT` — which need no prefix.\n- **Six post-2007 functions work, but only with an `_xlfn.` prefix**, because openpyxl writes your formula into the XML verbatim and Excel stores post-2007 names prefixed (its UI hides the prefix): `_xlfn.TEXTJOIN`, `_xlfn.CONCAT`, `_xlfn.IFS`, `_xlfn.SWITCH`, `_xlfn.MAXIFS`, `_xlfn.MINIFS`. Written bare, each yields `#NAME?`.\n- **Never use `XLOOKUP`, `XMATCH`, `SORT`, `FILTER`, `UNIQUE`, or `SEQUENCE`.** The runtime's LibreOffice cannot evaluate them under *any* prefix. Newer builds do evaluate them, but they are spilling array functions and an openpyxl-written file has no spill metadata, so only the top-left cell of the range gets a value — and `recalc.py` reports `total_errors: 0` on the truncated result. Use `INDEX`\u002F`MATCH` for lookups, and sort, filter, and de-duplicate in Python before writing the cells.\n- A formula LibreOffice could not parse is written back **lowercased** — a quick tell beside a `#NAME?`.\n\n## openpyxl gotchas\n\n- **Reading a model takes two loads.** `data_only=True` yields cached values with the formulas gone; the default yields formula strings with no values. One pass cannot give you both.\n- **`data_only=True` is destructive if you save.** That workbook has no formulas left, so saving replaces every one with a literal — permanently.\n- **`data_only=True` on a file openpyxl just wrote returns `None` everywhere** — run `recalc.py` first. (A formula whose result is `\"\"` also reads back as `None`.)\n- **Merged cells: write the top-left anchor only.** Every other cell in the range is a `MergedCell` whose `.value` is read-only.\n- **`.xlsm` loses its macros unless you pass `keep_vba=True`** to `load_workbook`.\n- **A sheet name containing a space must be quoted** in a cross-sheet reference: `='Assumptions Inputs'!$B$5`. Unquoted, it evaluates to `#VALUE!`.\n\n## Financial models\n\nUnless the user says otherwise, or the existing file already does something else.\n\n**Color:** blue text (`0,0,255`) for hardcoded inputs and scenario levers · black for formulas ·\ngreen (`0,128,0`) for links to another sheet · red (`255,0,0`) for links to another file ·\nyellow fill (`255,255,0`) for key assumptions and cells the user should fill in.\n\n**Numbers:** currency `$#,##0`, with the unit named in the header (`Revenue ($mm)`) · zeros\nrender as `-`, including in percentages (`$#,##0;($#,##0);-`) · negatives in parentheses ·\npercentages `0.0%`, **stored as fractions** (`0.15` renders `15.0%`; storing `15` renders\n`1500.0%`) · valuation multiples `0.0x` · years as text (`\"2024\"`, never `2,024`).\n\n**Structure:** every assumption in its own labeled cell, referenced by the formulas that use it\n(`=B5*(1+$B$6)`, never `=B5*1.05`) · formulas consistent across every projection period, since a\nlone edited cell mid-row is the commonest silent error · guard denominators that can be zero.\n\n## Dependencies\n\n`openpyxl`, `pandas`, `markitdown` (pip, preinstalled — install only if an import fails or the command is missing) · LibreOffice (`soffice`, auto-configured for sandboxed environments via `scripts\u002Foffice\u002Fsoffice.py`)\n",{"data":36,"body":37},{"name":4,"description":6,"license":26},{"type":38,"children":39},"root",[40,49,224,275,283,290,419,425,460,506,607,631,687,693,705,926,932,1089,1095,1100,1142,1253,1278,1284,1321],{"type":41,"tag":42,"props":43,"children":45},"element","h1",{"id":44},"xlsx-creation-editing-and-analysis",[46],{"type":47,"value":48},"text","XLSX creation, editing, and analysis",{"type":41,"tag":50,"props":51,"children":52},"table",{},[53,72],{"type":41,"tag":54,"props":55,"children":56},"thead",{},[57],{"type":41,"tag":58,"props":59,"children":60},"tr",{},[61,67],{"type":41,"tag":62,"props":63,"children":64},"th",{},[65],{"type":47,"value":66},"Task",{"type":41,"tag":62,"props":68,"children":69},{},[70],{"type":47,"value":71},"Approach",{"type":41,"tag":73,"props":74,"children":75},"tbody",{},[76,110,150,190],{"type":41,"tag":58,"props":77,"children":78},{},[79,98],{"type":41,"tag":80,"props":81,"children":82},"td",{},[83,89,91,96],{"type":41,"tag":84,"props":85,"children":86},"strong",{},[87],{"type":47,"value":88},"Create",{"type":47,"value":90}," or ",{"type":41,"tag":84,"props":92,"children":93},{},[94],{"type":47,"value":95},"edit",{"type":47,"value":97}," with formulas\u002Fformatting",{"type":41,"tag":80,"props":99,"children":100},{},[101,108],{"type":41,"tag":102,"props":103,"children":105},"code",{"className":104},[],[106],{"type":47,"value":107},"openpyxl",{"type":47,"value":109}," — see gotchas below",{"type":41,"tag":58,"props":111,"children":112},{},[113,123],{"type":41,"tag":80,"props":114,"children":115},{},[116,121],{"type":41,"tag":84,"props":117,"children":118},{},[119],{"type":47,"value":120},"Bulk data",{"type":47,"value":122}," in or out",{"type":41,"tag":80,"props":124,"children":125},{},[126,132,134,140,142,148],{"type":41,"tag":102,"props":127,"children":129},{"className":128},[],[130],{"type":47,"value":131},"pandas",{"type":47,"value":133}," (",{"type":41,"tag":102,"props":135,"children":137},{"className":136},[],[138],{"type":47,"value":139},"read_excel",{"type":47,"value":141},", ",{"type":41,"tag":102,"props":143,"children":145},{"className":144},[],[146],{"type":47,"value":147},"to_excel",{"type":47,"value":149},")",{"type":41,"tag":58,"props":151,"children":152},{},[153,163],{"type":41,"tag":80,"props":154,"children":155},{},[156,161],{"type":41,"tag":84,"props":157,"children":158},{},[159],{"type":47,"value":160},"Quick look",{"type":47,"value":162}," at a sheet",{"type":41,"tag":80,"props":164,"children":165},{},[166,172,174,180,182,188],{"type":41,"tag":102,"props":167,"children":169},{"className":168},[],[170],{"type":47,"value":171},"markitdown file.xlsx",{"type":47,"value":173}," — ",{"type":41,"tag":102,"props":175,"children":177},{"className":176},[],[178],{"type":47,"value":179},"## SheetName",{"type":47,"value":181}," per sheet; reads ",{"type":41,"tag":102,"props":183,"children":185},{"className":184},[],[186],{"type":47,"value":187},".xlsm",{"type":47,"value":189}," too. No cell coordinates, so don't plan edits from it",{"type":41,"tag":58,"props":191,"children":192},{},[193,211],{"type":41,"tag":80,"props":194,"children":195},{},[196,201,203,209],{"type":41,"tag":84,"props":197,"children":198},{},[199],{"type":47,"value":200},"Read",{"type":47,"value":202}," a model (formulas ",{"type":41,"tag":204,"props":205,"children":206},"em",{},[207],{"type":47,"value":208},"and",{"type":47,"value":210}," values)",{"type":41,"tag":80,"props":212,"children":213},{},[214,216,222],{"type":47,"value":215},"two ",{"type":41,"tag":102,"props":217,"children":219},{"className":218},[],[220],{"type":47,"value":221},"load_workbook",{"type":47,"value":223}," passes — see gotchas",{"type":41,"tag":225,"props":226,"children":227},"blockquote",{},[228],{"type":41,"tag":229,"props":230,"children":231},"p",{},[232,237,238,243,245,251,253,259,261,266,268,273],{"type":41,"tag":102,"props":233,"children":235},{"className":234},[],[236],{"type":47,"value":107},{"type":47,"value":141},{"type":41,"tag":102,"props":239,"children":241},{"className":240},[],[242],{"type":47,"value":131},{"type":47,"value":244},", and ",{"type":41,"tag":102,"props":246,"children":248},{"className":247},[],[249],{"type":47,"value":250},"markitdown",{"type":47,"value":252}," are preinstalled — do not run ",{"type":41,"tag":102,"props":254,"children":256},{"className":255},[],[257],{"type":47,"value":258},"pip install",{"type":47,"value":260}," first; write the script and import directly. Only if an import fails (or the ",{"type":41,"tag":102,"props":262,"children":264},{"className":263},[],[265],{"type":47,"value":250},{"type":47,"value":267}," command is missing): ",{"type":41,"tag":102,"props":269,"children":271},{"className":270},[],[272],{"type":47,"value":258},{"type":47,"value":274}," the missing package.",{"type":41,"tag":225,"props":276,"children":277},{},[278],{"type":41,"tag":229,"props":279,"children":280},{},[281],{"type":47,"value":282},"Script paths below are relative to this skill's directory.",{"type":41,"tag":284,"props":285,"children":287},"h2",{"id":286},"requirements-for-every-output",[288],{"type":47,"value":289},"Requirements for every output",{"type":41,"tag":291,"props":292,"children":293},"ul",{},[294,305,346,364,374,392,409],{"type":41,"tag":295,"props":296,"children":297},"li",{},[298,303],{"type":41,"tag":84,"props":299,"children":300},{},[301],{"type":47,"value":302},"Professional font",{"type":47,"value":304}," (Arial, Times New Roman) throughout, unless the user says otherwise.",{"type":41,"tag":295,"props":306,"children":307},{},[308,313,315,321,323,329,331,336,338,344],{"type":41,"tag":84,"props":309,"children":310},{},[311],{"type":47,"value":312},"Zero formula errors.",{"type":47,"value":314}," Never ship while ",{"type":41,"tag":102,"props":316,"children":318},{"className":317},[],[319],{"type":47,"value":320},"recalc.py",{"type":47,"value":322}," reports ",{"type":41,"tag":102,"props":324,"children":326},{"className":325},[],[327],{"type":47,"value":328},"errors_found",{"type":47,"value":330},". If you think an error predates you, prove it: load the ",{"type":41,"tag":204,"props":332,"children":333},{},[334],{"type":47,"value":335},"original",{"type":47,"value":337}," with ",{"type":41,"tag":102,"props":339,"children":341},{"className":340},[],[342],{"type":47,"value":343},"data_only=True",{"type":47,"value":345}," and look at that cell. An error you introduced looks exactly like one you inherited.",{"type":41,"tag":295,"props":347,"children":348},{},[349,354,356,362],{"type":41,"tag":84,"props":350,"children":351},{},[352],{"type":47,"value":353},"Use formulas, never hardcoded results.",{"type":47,"value":355}," Write ",{"type":41,"tag":102,"props":357,"children":359},{"className":358},[],[360],{"type":47,"value":361},"sheet['B10'] = '=SUM(B2:B9)'",{"type":47,"value":363},", not the Python-computed total. The sheet must recalculate when its inputs change.",{"type":41,"tag":295,"props":365,"children":366},{},[367,372],{"type":41,"tag":84,"props":368,"children":369},{},[370],{"type":47,"value":371},"Follow the user's spec literally.",{"type":47,"value":373}," Exact tab names, exact column headers, and the formula they spelled out. A redesign that computes something else fails, however elegant.",{"type":41,"tag":295,"props":375,"children":376},{},[377,382,384,390],{"type":41,"tag":84,"props":378,"children":379},{},[380],{"type":47,"value":381},"Document every assumption and hardcoded number",{"type":47,"value":383}," where the reader will see it — a cell comment, or an adjacent cell at a table's end. Cite a real source when one exists (",{"type":41,"tag":102,"props":385,"children":387},{"className":386},[],[388],{"type":47,"value":389},"Source: Company 10-K, FY2024, Page 45, Revenue Note, [SEC EDGAR URL]",{"type":47,"value":391},"); when the number came from the user, say so plainly.",{"type":41,"tag":295,"props":393,"children":394},{},[395,407],{"type":41,"tag":84,"props":396,"children":397},{},[398,400,405],{"type":47,"value":399},"A workbook ",{"type":41,"tag":204,"props":401,"children":402},{},[403],{"type":47,"value":404},"you create",{"type":47,"value":406}," for someone to fill in",{"type":47,"value":408}," needs a short legend naming which cells to edit, and one example row of realistic values showing the expected format. Never add such a row to a file you were asked to edit.",{"type":41,"tag":295,"props":410,"children":411},{},[412,417],{"type":41,"tag":84,"props":413,"children":414},{},[415],{"type":47,"value":416},"Editing an existing file: match its conventions exactly.",{"type":47,"value":418}," They override every guideline here. Find its designated input cells first — a distinct font color, fill, or shading marks them — write only there, and leave every existing formula untouched.",{"type":41,"tag":284,"props":420,"children":422},{"id":421},"recalculate-mandatory-whenever-the-file-contains-formulas",[423],{"type":47,"value":424},"Recalculate (mandatory whenever the file contains formulas)",{"type":41,"tag":229,"props":426,"children":427},{},[428,430,435,437,443,445,450,452,458],{"type":47,"value":429},"openpyxl writes formulas as strings with ",{"type":41,"tag":84,"props":431,"children":432},{},[433],{"type":47,"value":434},"no cached values",{"type":47,"value":436},". Until you recalculate, every\nformula cell reads back as ",{"type":41,"tag":102,"props":438,"children":440},{"className":439},[],[441],{"type":47,"value":442},"None",{"type":47,"value":444}," to anything reading cached values — ",{"type":41,"tag":102,"props":446,"children":448},{"className":447},[],[449],{"type":47,"value":131},{"type":47,"value":451},",\n",{"type":41,"tag":102,"props":453,"children":455},{"className":454},[],[456],{"type":47,"value":457},"load_workbook(data_only=True)",{"type":47,"value":459},", and most previewers.",{"type":41,"tag":461,"props":462,"children":467},"pre",{"className":463,"code":464,"language":465,"meta":466,"style":466},"language-bash shiki shiki-themes material-theme-lighter material-theme material-theme-palenight","python scripts\u002Frecalc.py output.xlsx [timeout_seconds]   # default 30\n","bash","",[468],{"type":41,"tag":102,"props":469,"children":470},{"__ignoreMap":466},[471],{"type":41,"tag":472,"props":473,"children":476},"span",{"class":474,"line":475},"line",1,[477,483,489,494,500],{"type":41,"tag":472,"props":478,"children":480},{"style":479},"--shiki-light:#E2931D;--shiki-default:#FFCB6B;--shiki-dark:#FFCB6B",[481],{"type":47,"value":482},"python",{"type":41,"tag":472,"props":484,"children":486},{"style":485},"--shiki-light:#91B859;--shiki-default:#C3E88D;--shiki-dark:#C3E88D",[487],{"type":47,"value":488}," scripts\u002Frecalc.py",{"type":41,"tag":472,"props":490,"children":491},{"style":485},[492],{"type":47,"value":493}," output.xlsx",{"type":41,"tag":472,"props":495,"children":497},{"style":496},"--shiki-light:#90A4AE;--shiki-default:#EEFFFF;--shiki-dark:#BABED8",[498],{"type":47,"value":499}," [timeout_seconds]   ",{"type":41,"tag":472,"props":501,"children":503},{"style":502},"--shiki-light:#90A4AE;--shiki-light-font-style:italic;--shiki-default:#546E7A;--shiki-default-font-style:italic;--shiki-dark:#676E95;--shiki-dark-font-style:italic",[504],{"type":47,"value":505},"# default 30\n",{"type":41,"tag":229,"props":507,"children":508},{},[509,511,516,518,524,525,531,533,538,540,546,547,553,555,561,563,569,571,576,578,598,600,605],{"type":47,"value":510},"LibreOffice computes every formula, the file is ",{"type":41,"tag":84,"props":512,"children":513},{},[514],{"type":47,"value":515},"rewritten in place",{"type":47,"value":517},", and you get JSON:\n",{"type":41,"tag":102,"props":519,"children":521},{"className":520},[],[522],{"type":47,"value":523},"status",{"type":47,"value":133},{"type":41,"tag":102,"props":526,"children":528},{"className":527},[],[529],{"type":47,"value":530},"success",{"type":47,"value":532}," | ",{"type":41,"tag":102,"props":534,"children":536},{"className":535},[],[537],{"type":47,"value":328},{"type":47,"value":539},"), ",{"type":41,"tag":102,"props":541,"children":543},{"className":542},[],[544],{"type":47,"value":545},"total_formulas",{"type":47,"value":141},{"type":41,"tag":102,"props":548,"children":550},{"className":549},[],[551],{"type":47,"value":552},"total_errors",{"type":47,"value":554},", and an\n",{"type":41,"tag":102,"props":556,"children":558},{"className":557},[],[559],{"type":47,"value":560},"error_summary",{"type":47,"value":562}," naming up to 100 cells per error type (",{"type":41,"tag":102,"props":564,"children":566},{"className":565},[],[567],{"type":47,"value":568},"locations_truncated",{"type":47,"value":570}," says how many it\nwithheld — trust ",{"type":41,"tag":102,"props":572,"children":574},{"className":573},[],[575],{"type":47,"value":552},{"type":47,"value":577},", not the length of the list). Fix what it names and run it\nagain. ",{"type":41,"tag":84,"props":579,"children":580},{},[581,583,589,591,596],{"type":47,"value":582},"JSON with an ",{"type":41,"tag":102,"props":584,"children":586},{"className":585},[],[587],{"type":47,"value":588},"error",{"type":47,"value":590}," key instead of a ",{"type":41,"tag":102,"props":592,"children":594},{"className":593},[],[595],{"type":47,"value":523},{"type":47,"value":597}," means nothing was recalculated",{"type":47,"value":599},", and\nonly that case exits non-zero — ",{"type":41,"tag":102,"props":601,"children":603},{"className":602},[],[604],{"type":47,"value":328},{"type":47,"value":606}," exits 0, so never treat a clean exit as a clean\nworkbook.",{"type":41,"tag":229,"props":608,"children":609},{},[610,629],{"type":41,"tag":84,"props":611,"children":612},{},[613,615,620,622,627],{"type":47,"value":614},"A green recalc proves your formulas ",{"type":41,"tag":204,"props":616,"children":617},{},[618],{"type":47,"value":619},"evaluate",{"type":47,"value":621},", not that they are ",{"type":41,"tag":204,"props":623,"children":624},{},[625],{"type":47,"value":626},"right",{"type":47,"value":628},".",{"type":47,"value":630}," An off-by-one\nrange or a reference to the wrong row yields a clean, error-free file with wrong numbers.\nWrite 2–3 formulas first and check they pull the values you expect, before building out a grid.",{"type":41,"tag":229,"props":632,"children":633},{},[634,639,641,647,649,655,657,662,664,670,672,677,679,685],{"type":41,"tag":84,"props":635,"children":636},{},[637],{"type":47,"value":638},"A workbook that links to another file loses those links",{"type":47,"value":640}," if you re-save it with openpyxl and\nthen recalculate. Such a formula reads ",{"type":41,"tag":102,"props":642,"children":644},{"className":643},[],[645],{"type":47,"value":646},"='[1]Returns Analysis'!$B$2",{"type":47,"value":648}," — the ",{"type":41,"tag":102,"props":650,"children":652},{"className":651},[],[653],{"type":47,"value":654},"[1]",{"type":47,"value":656}," is an index\ninto the workbook's external-reference list, naming a ",{"type":41,"tag":204,"props":658,"children":659},{},[660],{"type":47,"value":661},"separate file on disk",{"type":47,"value":663},", not a sheet.\nThat file is rarely present here, so the cell's cached value is the only thing holding its\ndata. openpyxl strips that value on save; LibreOffice then has to resolve the reference for\nreal, fails, writes ",{"type":41,"tag":102,"props":665,"children":667},{"className":666},[],[668],{"type":47,"value":669},"#NAME?",{"type":47,"value":671},", and deletes every link. ",{"type":41,"tag":102,"props":673,"children":675},{"className":674},[],[676],{"type":47,"value":320},{"type":47,"value":678}," refuses to run in that state\n— copy those cells' values out of the original before you save over them (",{"type":41,"tag":102,"props":680,"children":682},{"className":681},[],[683],{"type":47,"value":684},"--force",{"type":47,"value":686}," overrides,\nand accepts the loss).",{"type":41,"tag":284,"props":688,"children":690},{"id":689},"choosing-formulas-that-survive-verification",[691],{"type":47,"value":692},"Choosing formulas that survive verification",{"type":41,"tag":229,"props":694,"children":695},{},[696,698,703],{"type":47,"value":697},"LibreOffice implements fewer functions than Excel, and one it cannot evaluate becomes a\nliteral ",{"type":41,"tag":102,"props":699,"children":701},{"className":700},[],[702],{"type":47,"value":669},{"type":47,"value":704}," baked into the file you deliver.",{"type":41,"tag":291,"props":706,"children":707},{},[708,753,820,908],{"type":41,"tag":295,"props":709,"children":710},{},[711,716,717,723,724,730,731,737,738,744,745,751],{"type":41,"tag":84,"props":712,"children":713},{},[714],{"type":47,"value":715},"Prefer Excel-2007-era functions",{"type":47,"value":173},{"type":41,"tag":102,"props":718,"children":720},{"className":719},[],[721],{"type":47,"value":722},"SUMIFS",{"type":47,"value":141},{"type":41,"tag":102,"props":725,"children":727},{"className":726},[],[728],{"type":47,"value":729},"INDEX",{"type":47,"value":141},{"type":41,"tag":102,"props":732,"children":734},{"className":733},[],[735],{"type":47,"value":736},"MATCH",{"type":47,"value":141},{"type":41,"tag":102,"props":739,"children":741},{"className":740},[],[742],{"type":47,"value":743},"IFERROR",{"type":47,"value":141},{"type":41,"tag":102,"props":746,"children":748},{"className":747},[],[749],{"type":47,"value":750},"SUMPRODUCT",{"type":47,"value":752}," — which need no prefix.",{"type":41,"tag":295,"props":754,"children":755},{},[756,769,771,777,778,784,785,791,792,798,799,805,806,812,814,819],{"type":41,"tag":84,"props":757,"children":758},{},[759,761,767],{"type":47,"value":760},"Six post-2007 functions work, but only with an ",{"type":41,"tag":102,"props":762,"children":764},{"className":763},[],[765],{"type":47,"value":766},"_xlfn.",{"type":47,"value":768}," prefix",{"type":47,"value":770},", because openpyxl writes your formula into the XML verbatim and Excel stores post-2007 names prefixed (its UI hides the prefix): ",{"type":41,"tag":102,"props":772,"children":774},{"className":773},[],[775],{"type":47,"value":776},"_xlfn.TEXTJOIN",{"type":47,"value":141},{"type":41,"tag":102,"props":779,"children":781},{"className":780},[],[782],{"type":47,"value":783},"_xlfn.CONCAT",{"type":47,"value":141},{"type":41,"tag":102,"props":786,"children":788},{"className":787},[],[789],{"type":47,"value":790},"_xlfn.IFS",{"type":47,"value":141},{"type":41,"tag":102,"props":793,"children":795},{"className":794},[],[796],{"type":47,"value":797},"_xlfn.SWITCH",{"type":47,"value":141},{"type":41,"tag":102,"props":800,"children":802},{"className":801},[],[803],{"type":47,"value":804},"_xlfn.MAXIFS",{"type":47,"value":141},{"type":41,"tag":102,"props":807,"children":809},{"className":808},[],[810],{"type":47,"value":811},"_xlfn.MINIFS",{"type":47,"value":813},". Written bare, each yields ",{"type":41,"tag":102,"props":815,"children":817},{"className":816},[],[818],{"type":47,"value":669},{"type":47,"value":628},{"type":41,"tag":295,"props":821,"children":822},{},[823,871,873,878,880,885,886,892,894,899,901,906],{"type":41,"tag":84,"props":824,"children":825},{},[826,828,834,835,841,842,848,849,855,856,862,864,870],{"type":47,"value":827},"Never use ",{"type":41,"tag":102,"props":829,"children":831},{"className":830},[],[832],{"type":47,"value":833},"XLOOKUP",{"type":47,"value":141},{"type":41,"tag":102,"props":836,"children":838},{"className":837},[],[839],{"type":47,"value":840},"XMATCH",{"type":47,"value":141},{"type":41,"tag":102,"props":843,"children":845},{"className":844},[],[846],{"type":47,"value":847},"SORT",{"type":47,"value":141},{"type":41,"tag":102,"props":850,"children":852},{"className":851},[],[853],{"type":47,"value":854},"FILTER",{"type":47,"value":141},{"type":41,"tag":102,"props":857,"children":859},{"className":858},[],[860],{"type":47,"value":861},"UNIQUE",{"type":47,"value":863},", or ",{"type":41,"tag":102,"props":865,"children":867},{"className":866},[],[868],{"type":47,"value":869},"SEQUENCE",{"type":47,"value":628},{"type":47,"value":872}," The runtime's LibreOffice cannot evaluate them under ",{"type":41,"tag":204,"props":874,"children":875},{},[876],{"type":47,"value":877},"any",{"type":47,"value":879}," prefix. Newer builds do evaluate them, but they are spilling array functions and an openpyxl-written file has no spill metadata, so only the top-left cell of the range gets a value — and ",{"type":41,"tag":102,"props":881,"children":883},{"className":882},[],[884],{"type":47,"value":320},{"type":47,"value":322},{"type":41,"tag":102,"props":887,"children":889},{"className":888},[],[890],{"type":47,"value":891},"total_errors: 0",{"type":47,"value":893}," on the truncated result. Use ",{"type":41,"tag":102,"props":895,"children":897},{"className":896},[],[898],{"type":47,"value":729},{"type":47,"value":900},"\u002F",{"type":41,"tag":102,"props":902,"children":904},{"className":903},[],[905],{"type":47,"value":736},{"type":47,"value":907}," for lookups, and sort, filter, and de-duplicate in Python before writing the cells.",{"type":41,"tag":295,"props":909,"children":910},{},[911,913,918,920,925],{"type":47,"value":912},"A formula LibreOffice could not parse is written back ",{"type":41,"tag":84,"props":914,"children":915},{},[916],{"type":47,"value":917},"lowercased",{"type":47,"value":919}," — a quick tell beside a ",{"type":41,"tag":102,"props":921,"children":923},{"className":922},[],[924],{"type":47,"value":669},{"type":47,"value":628},{"type":41,"tag":284,"props":927,"children":929},{"id":928},"openpyxl-gotchas",[930],{"type":47,"value":931},"openpyxl gotchas",{"type":41,"tag":291,"props":933,"children":934},{},[935,952,967,1011,1037,1064],{"type":41,"tag":295,"props":936,"children":937},{},[938,943,945,950],{"type":41,"tag":84,"props":939,"children":940},{},[941],{"type":47,"value":942},"Reading a model takes two loads.",{"type":47,"value":944}," ",{"type":41,"tag":102,"props":946,"children":948},{"className":947},[],[949],{"type":47,"value":343},{"type":47,"value":951}," yields cached values with the formulas gone; the default yields formula strings with no values. One pass cannot give you both.",{"type":41,"tag":295,"props":953,"children":954},{},[955,965],{"type":41,"tag":84,"props":956,"children":957},{},[958,963],{"type":41,"tag":102,"props":959,"children":961},{"className":960},[],[962],{"type":47,"value":343},{"type":47,"value":964}," is destructive if you save.",{"type":47,"value":966}," That workbook has no formulas left, so saving replaces every one with a literal — permanently.",{"type":41,"tag":295,"props":968,"children":969},{},[970,987,989,994,996,1002,1004,1009],{"type":41,"tag":84,"props":971,"children":972},{},[973,978,980,985],{"type":41,"tag":102,"props":974,"children":976},{"className":975},[],[977],{"type":47,"value":343},{"type":47,"value":979}," on a file openpyxl just wrote returns ",{"type":41,"tag":102,"props":981,"children":983},{"className":982},[],[984],{"type":47,"value":442},{"type":47,"value":986}," everywhere",{"type":47,"value":988}," — run ",{"type":41,"tag":102,"props":990,"children":992},{"className":991},[],[993],{"type":47,"value":320},{"type":47,"value":995}," first. (A formula whose result is ",{"type":41,"tag":102,"props":997,"children":999},{"className":998},[],[1000],{"type":47,"value":1001},"\"\"",{"type":47,"value":1003}," also reads back as ",{"type":41,"tag":102,"props":1005,"children":1007},{"className":1006},[],[1008],{"type":47,"value":442},{"type":47,"value":1010},".)",{"type":41,"tag":295,"props":1012,"children":1013},{},[1014,1019,1021,1027,1029,1035],{"type":41,"tag":84,"props":1015,"children":1016},{},[1017],{"type":47,"value":1018},"Merged cells: write the top-left anchor only.",{"type":47,"value":1020}," Every other cell in the range is a ",{"type":41,"tag":102,"props":1022,"children":1024},{"className":1023},[],[1025],{"type":47,"value":1026},"MergedCell",{"type":47,"value":1028}," whose ",{"type":41,"tag":102,"props":1030,"children":1032},{"className":1031},[],[1033],{"type":47,"value":1034},".value",{"type":47,"value":1036}," is read-only.",{"type":41,"tag":295,"props":1038,"children":1039},{},[1040,1056,1058,1063],{"type":41,"tag":84,"props":1041,"children":1042},{},[1043,1048,1050],{"type":41,"tag":102,"props":1044,"children":1046},{"className":1045},[],[1047],{"type":47,"value":187},{"type":47,"value":1049}," loses its macros unless you pass ",{"type":41,"tag":102,"props":1051,"children":1053},{"className":1052},[],[1054],{"type":47,"value":1055},"keep_vba=True",{"type":47,"value":1057}," to ",{"type":41,"tag":102,"props":1059,"children":1061},{"className":1060},[],[1062],{"type":47,"value":221},{"type":47,"value":628},{"type":41,"tag":295,"props":1065,"children":1066},{},[1067,1072,1074,1080,1082,1088],{"type":41,"tag":84,"props":1068,"children":1069},{},[1070],{"type":47,"value":1071},"A sheet name containing a space must be quoted",{"type":47,"value":1073}," in a cross-sheet reference: ",{"type":41,"tag":102,"props":1075,"children":1077},{"className":1076},[],[1078],{"type":47,"value":1079},"='Assumptions Inputs'!$B$5",{"type":47,"value":1081},". Unquoted, it evaluates to ",{"type":41,"tag":102,"props":1083,"children":1085},{"className":1084},[],[1086],{"type":47,"value":1087},"#VALUE!",{"type":47,"value":628},{"type":41,"tag":284,"props":1090,"children":1092},{"id":1091},"financial-models",[1093],{"type":47,"value":1094},"Financial models",{"type":41,"tag":229,"props":1096,"children":1097},{},[1098],{"type":47,"value":1099},"Unless the user says otherwise, or the existing file already does something else.",{"type":41,"tag":229,"props":1101,"children":1102},{},[1103,1108,1110,1116,1118,1124,1126,1132,1134,1140],{"type":41,"tag":84,"props":1104,"children":1105},{},[1106],{"type":47,"value":1107},"Color:",{"type":47,"value":1109}," blue text (",{"type":41,"tag":102,"props":1111,"children":1113},{"className":1112},[],[1114],{"type":47,"value":1115},"0,0,255",{"type":47,"value":1117},") for hardcoded inputs and scenario levers · black for formulas ·\ngreen (",{"type":41,"tag":102,"props":1119,"children":1121},{"className":1120},[],[1122],{"type":47,"value":1123},"0,128,0",{"type":47,"value":1125},") for links to another sheet · red (",{"type":41,"tag":102,"props":1127,"children":1129},{"className":1128},[],[1130],{"type":47,"value":1131},"255,0,0",{"type":47,"value":1133},") for links to another file ·\nyellow fill (",{"type":41,"tag":102,"props":1135,"children":1137},{"className":1136},[],[1138],{"type":47,"value":1139},"255,255,0",{"type":47,"value":1141},") for key assumptions and cells the user should fill in.",{"type":41,"tag":229,"props":1143,"children":1144},{},[1145,1150,1152,1158,1160,1166,1168,1174,1176,1182,1184,1190,1191,1196,1197,1203,1205,1211,1213,1219,1221,1227,1229,1235,1237,1243,1245,1251],{"type":41,"tag":84,"props":1146,"children":1147},{},[1148],{"type":47,"value":1149},"Numbers:",{"type":47,"value":1151}," currency ",{"type":41,"tag":102,"props":1153,"children":1155},{"className":1154},[],[1156],{"type":47,"value":1157},"$#,##0",{"type":47,"value":1159},", with the unit named in the header (",{"type":41,"tag":102,"props":1161,"children":1163},{"className":1162},[],[1164],{"type":47,"value":1165},"Revenue ($mm)",{"type":47,"value":1167},") · zeros\nrender as ",{"type":41,"tag":102,"props":1169,"children":1171},{"className":1170},[],[1172],{"type":47,"value":1173},"-",{"type":47,"value":1175},", including in percentages (",{"type":41,"tag":102,"props":1177,"children":1179},{"className":1178},[],[1180],{"type":47,"value":1181},"$#,##0;($#,##0);-",{"type":47,"value":1183},") · negatives in parentheses ·\npercentages ",{"type":41,"tag":102,"props":1185,"children":1187},{"className":1186},[],[1188],{"type":47,"value":1189},"0.0%",{"type":47,"value":141},{"type":41,"tag":84,"props":1192,"children":1193},{},[1194],{"type":47,"value":1195},"stored as fractions",{"type":47,"value":133},{"type":41,"tag":102,"props":1198,"children":1200},{"className":1199},[],[1201],{"type":47,"value":1202},"0.15",{"type":47,"value":1204}," renders ",{"type":41,"tag":102,"props":1206,"children":1208},{"className":1207},[],[1209],{"type":47,"value":1210},"15.0%",{"type":47,"value":1212},"; storing ",{"type":41,"tag":102,"props":1214,"children":1216},{"className":1215},[],[1217],{"type":47,"value":1218},"15",{"type":47,"value":1220}," renders\n",{"type":41,"tag":102,"props":1222,"children":1224},{"className":1223},[],[1225],{"type":47,"value":1226},"1500.0%",{"type":47,"value":1228},") · valuation multiples ",{"type":41,"tag":102,"props":1230,"children":1232},{"className":1231},[],[1233],{"type":47,"value":1234},"0.0x",{"type":47,"value":1236}," · years as text (",{"type":41,"tag":102,"props":1238,"children":1240},{"className":1239},[],[1241],{"type":47,"value":1242},"\"2024\"",{"type":47,"value":1244},", never ",{"type":41,"tag":102,"props":1246,"children":1248},{"className":1247},[],[1249],{"type":47,"value":1250},"2,024",{"type":47,"value":1252},").",{"type":41,"tag":229,"props":1254,"children":1255},{},[1256,1261,1263,1269,1270,1276],{"type":41,"tag":84,"props":1257,"children":1258},{},[1259],{"type":47,"value":1260},"Structure:",{"type":47,"value":1262}," every assumption in its own labeled cell, referenced by the formulas that use it\n(",{"type":41,"tag":102,"props":1264,"children":1266},{"className":1265},[],[1267],{"type":47,"value":1268},"=B5*(1+$B$6)",{"type":47,"value":1244},{"type":41,"tag":102,"props":1271,"children":1273},{"className":1272},[],[1274],{"type":47,"value":1275},"=B5*1.05",{"type":47,"value":1277},") · formulas consistent across every projection period, since a\nlone edited cell mid-row is the commonest silent error · guard denominators that can be zero.",{"type":41,"tag":284,"props":1279,"children":1281},{"id":1280},"dependencies",[1282],{"type":47,"value":1283},"Dependencies",{"type":41,"tag":229,"props":1285,"children":1286},{},[1287,1292,1293,1298,1299,1304,1306,1312,1314,1320],{"type":41,"tag":102,"props":1288,"children":1290},{"className":1289},[],[1291],{"type":47,"value":107},{"type":47,"value":141},{"type":41,"tag":102,"props":1294,"children":1296},{"className":1295},[],[1297],{"type":47,"value":131},{"type":47,"value":141},{"type":41,"tag":102,"props":1300,"children":1302},{"className":1301},[],[1303],{"type":47,"value":250},{"type":47,"value":1305}," (pip, preinstalled — install only if an import fails or the command is missing) · LibreOffice (",{"type":41,"tag":102,"props":1307,"children":1309},{"className":1308},[],[1310],{"type":47,"value":1311},"soffice",{"type":47,"value":1313},", auto-configured for sandboxed environments via ",{"type":41,"tag":102,"props":1315,"children":1317},{"className":1316},[],[1318],{"type":47,"value":1319},"scripts\u002Foffice\u002Fsoffice.py",{"type":47,"value":149},{"type":41,"tag":1322,"props":1323,"children":1324},"style",{},[1325],{"type":47,"value":1326},"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":1328,"total":1513},[1329,1348,1362,1374,1393,1406,1427,1447,1461,1476,1484,1497],{"slug":1330,"name":1330,"fn":1331,"description":1332,"org":1333,"tags":1334,"stars":23,"repoUrl":24,"updatedAt":1347},"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},[1335,1338,1341,1344],{"name":1336,"slug":1337,"type":16},"Creative","creative",{"name":1339,"slug":1340,"type":16},"Design","design",{"name":1342,"slug":1343,"type":16},"Generative Art","generative-art",{"name":1345,"slug":1346,"type":16},"JavaScript","javascript","2026-04-06T17:56:15.455818",{"slug":1349,"name":1349,"fn":1350,"description":1351,"org":1352,"tags":1353,"stars":23,"repoUrl":24,"updatedAt":1361},"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},[1354,1357,1358],{"name":1355,"slug":1356,"type":16},"Branding","branding",{"name":1339,"slug":1340,"type":16},{"name":1359,"slug":1360,"type":16},"Typography","typography","2026-04-06T17:56:05.042852",{"slug":1363,"name":1363,"fn":1364,"description":1365,"org":1366,"tags":1367,"stars":23,"repoUrl":24,"updatedAt":1373},"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},[1368,1369,1370],{"name":1336,"slug":1337,"type":16},{"name":1339,"slug":1340,"type":16},{"name":1371,"slug":1372,"type":16},"PDF","pdf","2026-04-06T17:56:03.794732",{"slug":1375,"name":1375,"fn":1376,"description":1377,"org":1378,"tags":1379,"stars":23,"repoUrl":24,"updatedAt":1392},"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},[1380,1383,1384,1387,1389],{"name":1381,"slug":1382,"type":16},"Agents","agents",{"name":9,"slug":8,"type":16},{"name":1385,"slug":1386,"type":16},"Anthropic SDK","anthropic-sdk",{"name":1388,"slug":1375,"type":16},"Claude API",{"name":1390,"slug":1391,"type":16},"LLM","llm","2026-07-28T05:36:08.213335",{"slug":1394,"name":1394,"fn":1395,"description":1396,"org":1397,"tags":1398,"stars":23,"repoUrl":24,"updatedAt":1405},"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},[1399,1402],{"name":1400,"slug":1401,"type":16},"Documentation","documentation",{"name":1403,"slug":1404,"type":16},"Technical Writing","technical-writing","2026-04-06T17:56:14.18897",{"slug":1407,"name":1407,"fn":1408,"description":1409,"org":1410,"tags":1411,"stars":23,"repoUrl":24,"updatedAt":1426},"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},[1412,1415,1417,1420,1423],{"name":1413,"slug":1414,"type":16},"Documents","documents",{"name":1416,"slug":1407,"type":16},"DOCX",{"name":1418,"slug":1419,"type":16},"Office","office",{"name":1421,"slug":1422,"type":16},"Templates","templates",{"name":1424,"slug":1425,"type":16},"Word","word","2026-07-18T05:16:23.136271",{"slug":1428,"name":1428,"fn":1429,"description":1430,"org":1431,"tags":1432,"stars":23,"repoUrl":24,"updatedAt":1446},"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},[1433,1434,1437,1440,1443],{"name":1339,"slug":1340,"type":16},{"name":1435,"slug":1436,"type":16},"Frontend","frontend",{"name":1438,"slug":1439,"type":16},"React","react",{"name":1441,"slug":1442,"type":16},"Tailwind CSS","tailwind-css",{"name":1444,"slug":1445,"type":16},"UI Components","ui-components","2026-04-06T17:56:16.723469",{"slug":1448,"name":1448,"fn":1449,"description":1450,"org":1451,"tags":1452,"stars":23,"repoUrl":24,"updatedAt":1460},"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},[1453,1456,1457],{"name":1454,"slug":1455,"type":16},"Communications","communications",{"name":1421,"slug":1422,"type":16},{"name":1458,"slug":1459,"type":16},"Writing","writing","2026-04-06T17:56:20.695522",{"slug":1462,"name":1462,"fn":1463,"description":1464,"org":1465,"tags":1466,"stars":23,"repoUrl":24,"updatedAt":1475},"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},[1467,1468,1471,1472],{"name":1381,"slug":1382,"type":16},{"name":1469,"slug":1470,"type":16},"API Development","api-development",{"name":1390,"slug":1391,"type":16},{"name":1473,"slug":1474,"type":16},"MCP","mcp","2026-04-06T17:56:10.357665",{"slug":1372,"name":1372,"fn":1477,"description":1478,"org":1479,"tags":1480,"stars":23,"repoUrl":24,"updatedAt":1483},"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},[1481,1482],{"name":1413,"slug":1414,"type":16},{"name":1371,"slug":1372,"type":16},"2026-04-06T17:56:02.483316",{"slug":1485,"name":1485,"fn":1486,"description":1487,"org":1488,"tags":1489,"stars":23,"repoUrl":24,"updatedAt":1496},"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},[1490,1493],{"name":1491,"slug":1492,"type":16},"PowerPoint","powerpoint",{"name":1494,"slug":1495,"type":16},"Presentations","presentations","2026-07-18T05:16:24.1471",{"slug":1498,"name":1498,"fn":1499,"description":1500,"org":1501,"tags":1502,"stars":23,"repoUrl":24,"updatedAt":1512},"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},[1503,1504,1505,1508,1511],{"name":1381,"slug":1382,"type":16},{"name":1400,"slug":1401,"type":16},{"name":1506,"slug":1507,"type":16},"Evals","evals",{"name":1509,"slug":1510,"type":16},"Performance","performance",{"name":1403,"slug":1404,"type":16},"2026-04-19T06:45:40.804",490,{"items":1515,"total":1564},[1516,1523,1529,1535,1543,1548,1556],{"slug":1330,"name":1330,"fn":1331,"description":1332,"org":1517,"tags":1518,"stars":23,"repoUrl":24,"updatedAt":1347},{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[1519,1520,1521,1522],{"name":1336,"slug":1337,"type":16},{"name":1339,"slug":1340,"type":16},{"name":1342,"slug":1343,"type":16},{"name":1345,"slug":1346,"type":16},{"slug":1349,"name":1349,"fn":1350,"description":1351,"org":1524,"tags":1525,"stars":23,"repoUrl":24,"updatedAt":1361},{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[1526,1527,1528],{"name":1355,"slug":1356,"type":16},{"name":1339,"slug":1340,"type":16},{"name":1359,"slug":1360,"type":16},{"slug":1363,"name":1363,"fn":1364,"description":1365,"org":1530,"tags":1531,"stars":23,"repoUrl":24,"updatedAt":1373},{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[1532,1533,1534],{"name":1336,"slug":1337,"type":16},{"name":1339,"slug":1340,"type":16},{"name":1371,"slug":1372,"type":16},{"slug":1375,"name":1375,"fn":1376,"description":1377,"org":1536,"tags":1537,"stars":23,"repoUrl":24,"updatedAt":1392},{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[1538,1539,1540,1541,1542],{"name":1381,"slug":1382,"type":16},{"name":9,"slug":8,"type":16},{"name":1385,"slug":1386,"type":16},{"name":1388,"slug":1375,"type":16},{"name":1390,"slug":1391,"type":16},{"slug":1394,"name":1394,"fn":1395,"description":1396,"org":1544,"tags":1545,"stars":23,"repoUrl":24,"updatedAt":1405},{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[1546,1547],{"name":1400,"slug":1401,"type":16},{"name":1403,"slug":1404,"type":16},{"slug":1407,"name":1407,"fn":1408,"description":1409,"org":1549,"tags":1550,"stars":23,"repoUrl":24,"updatedAt":1426},{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[1551,1552,1553,1554,1555],{"name":1413,"slug":1414,"type":16},{"name":1416,"slug":1407,"type":16},{"name":1418,"slug":1419,"type":16},{"name":1421,"slug":1422,"type":16},{"name":1424,"slug":1425,"type":16},{"slug":1428,"name":1428,"fn":1429,"description":1430,"org":1557,"tags":1558,"stars":23,"repoUrl":24,"updatedAt":1446},{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[1559,1560,1561,1562,1563],{"name":1339,"slug":1340,"type":16},{"name":1435,"slug":1436,"type":16},{"name":1438,"slug":1439,"type":16},{"name":1441,"slug":1442,"type":16},{"name":1444,"slug":1445,"type":16},17]