Use this skill when the user asks to convert a file from one format to another (e.g. csv to xlsx, xlsx to json, pdf text to csv) and you're not sure which library handles that specific pair, or whether it's supported in this environment at all. Dispatches to the right library per format pair and explicitly lists conversions that are NOT supported here so you don't attempt one that will silently fail or produce a wrong result.
インストールする前に、エージェントに与えられる指示の中身を確認できます。
| From | To | Default (Node) | Fallback (Python) |
|---|---|---|---|
| csv | xlsx / json / html | papaparse (parse to array of objects) → exceljs (xlsx) / JSON.stringify (json) / a hand-rolled <table> loop (html — no library needed for this) | pandas.read_csv → .to_excel / .to_json / .to_html — reach for this when the conversion needs real reshaping (pivots, group-by, dtype coercion) along the way, not as a first choice |
| xlsx | csv / json / html | exceljs (read) → papaparse.unparse (csv) / JSON.stringify (json) / hand-rolled html | pandas.read_excel → .to_csv / .to_json / .to_html |
| json (tabular/list-of-records shape) | csv / xlsx | JSON.parse → papaparse.unparse (csv) / exceljs (xlsx) | pandas.read_json → .to_csv / .to_excel |
| image (png/jpg/webp/etc.) | different image format, resize, basic edits | sharp (.toFormat(...), .resize(...)) | Pillow (Image.open(...).save(new_path)) |
| docx | plain text | — (no solid Node equivalent for structured docx parsing) | python-docx / docx2python — extract paragraph and table text |
| plain text / csv (tables) | — (no solid Node equivalent for table-aware extraction) | pdfplumber — extract_text() / extract_tables() → build a DataFrame if tabular |
For plain csv/xlsx/json reshuffling, default to the Node path (an array of plain objects is the common intermediate, playing the same role pandas.DataFrame plays on the Python side) per this environment's Node-first policy — reach for pandas only when the conversion needs real data reshaping along the way. docx/pdf extraction and structure-aware parsing have no solid Node equivalent here, so those stay Python regardless of format on the other end.
These all require a document-rendering engine (LibreOffice) that is not installed in the sandbox yet. Tell the user directly rather than attempting a workaround (e.g. do not try to fake a "pdf" by screenshotting text, and do not claim success on a conversion you didn't actually perform):
docx → pdfpptx → pdfdoc (legacy binary Word format) → docxxlsx → pdfIf the user's underlying goal is "get the numbers out of this PDF/docx into a spreadsheet" rather than literally "convert this file", extracting the relevant data and writing exactly the columns/rows they need is usually a better outcome than a generic whole-file conversion — ask yourself which one they actually need before picking an approach.
まだレビューはありません。使ってみた感想をお寄せください。
概要と使いどころ
Use this skill whenever the user asks you to load, clean, aggregate, join, or otherwise analyze tabular data (csv, xlsx, json, or a database export) — 'what's the total revenue by region', 'clean up this dataset', 'join these two files on customer id'. Establishes a verification discipline so reported numbers are always numbers the code actually printed, never numbers you inferred or estimated.
日本語の概要は準備中です。原文の説明を表示しています。
Use this skill whenever the user asks for a chart, graph, plot, or visualization of data — 'chart this by month', 'show me a breakdown by category', 'visualize the trend'. Covers picking the right chart type for the question being asked, labeling/readability rules, and which plotting library to reach for. Pair with data-analysis for the underlying data prep.
日本語の概要は準備中です。原文の説明を表示しています。
Use this skill whenever the user asks for a Word document, a .docx file, or a report/memo/letter/proposal delivered as one — creating a new document from scratch, editing an existing .docx, or reading/summarizing the contents of one. Covers page layout, headings, tables, numbered/bulleted lists, page breaks, and a table of contents. Does not cover converting a .docx to PDF or .doc to .docx (see file-conversion for what conversions ARE supported in this environment).
日本語の概要は準備中です。原文の説明を表示しています。
Low-level support skill for hand-editing the raw XML inside a .docx or .pptx file (both formats are just ZIP archives of XML parts). Use this directly only when you need to unpack, inspect, or repack Open XML yourself — for example fixing a validation error in generated markup, or making one small targeted edit without regenerating a whole document from scratch. The docx and pptx skills already use this internally for their 'edit an existing file' workflow, so you rarely need to load this on its own.
日本語の概要は準備中です。原文の説明を表示しています。
Use this skill whenever the user asks for a PDF — generating a new one from scratch (reports, invoices, letters), extracting text/tables from an existing PDF, or filling in an existing PDF form. Does not cover converting an existing Word/PowerPoint/Excel file to PDF (that requires LibreOffice, not available in this environment — see file-conversion).
日本語の概要は準備中です。原文の説明を表示しています。
Use this skill whenever the user asks for a PowerPoint presentation, a .pptx file, or slides for a talk/pitch/report — creating a new deck from scratch, editing an existing .pptx, or reading/summarizing an existing deck's content. Covers slide layout, color/typography choices, and a content-quality checklist for professional-looking output. Does not cover rendering slides to images for visual QA (see the 'Not supported' section).
日本語の概要は準備中です。原文の説明を表示しています。