paperjsx – Documents & Office skill for AI agents
Generate PPTX presentations, DOCX documents, XLSX spreadsheets, and PDF reports from structured JSON input using PaperJSX.
Install the paperjsx skill with one command
Pick the tool you use, copy the command and paste it in your terminal. The skill lands in that tool's skills folder and is ready in your next session.
Claude Code
mkdir -p ~/.claude/skills && curl -fsSL https://skill.dn1nguoi.com/z/paperjsx-23bb8.tgz | tar xz -C ~/.claude/skills
Call it in Claude Code: /paperjsx – then describe the task you want done.
Codex
mkdir -p ~/.codex/skills && curl -fsSL https://skill.dn1nguoi.com/z/paperjsx-23bb8.tgz | tar xz -C ~/.codex/skills
Call it in Codex: $paperjsx – then describe the task you want done.
Hermes Agent
mkdir -p ~/.hermes/skills && curl -fsSL https://skill.dn1nguoi.com/z/paperjsx-23bb8.tgz | tar xz -C ~/.hermes/skills
Call it in Hermes Agent: /paperjsx – then describe the task you want done.
DeepSeek
mkdir -p ~/.deepcode/skills && curl -fsSL https://skill.dn1nguoi.com/z/paperjsx-23bb8.tgz | tar xz -C ~/.deepcode/skills
Call it in DeepSeek: /paperjsx – then describe the task you want done.
SKILL.md content
PaperJSX Document Generation
Generate professional documents from JSON layout specs. PaperJSX is generation-only — it creates new files, it does not edit existing ones.
Triggers
Use this skill when the user asks to:
- Create a presentation or generate slides
- Make a PPTX or PowerPoint file
- Create a Word document or DOCX
- Generate an Excel spreadsheet with charts
- Create a JSON to PPTX, JSON to DOCX, or JSON to XLSX file
- Generate a PDF invoice, report, or chart document
Install
Install the format-appropriate package:
# Presentations
npm install @paperjsx/json-to-pptx
# Word documents
npm install @paperjsx/json-to-docx
# Spreadsheets
npm install @paperjsx/json-to-xlsx
# PDF documents
npm install @paperjsx/json-to-pdfHow it works
1. Build a JSON layout spec matching the schema in references/json-schema.md
2. Write a Node.js script that passes the JSON to the PaperJSX engine
3. Run the script to generate the output file
4. Validate the output file exists and is non-zero bytes
Do not write imperative PaperJSX API code. The execution model is always: JSON spec in, document file out.
Example: PPTX generation
import { PaperEngine } from "@paperjsx/json-to-pptx";
import fs from "node:fs";
const spec = {
type: "Document",
meta: { title: "Q4 Review" },
slides: [
{
type: "Slide",
children: [
{ type: "Text", content: "Q4 2025 Business Review", style: { fontSize: 36, bold: true } }
]
}
]
};
const buffer = await PaperEngine.render(spec);
fs.writeFileSync("presentation.pptx", buffer);
console.log("Generated presentation.pptx");Example: DOCX generation
import { renderToDocx } from "@paperjsx/json-to-docx";
import fs from "node:fs";
const result = await renderToDocx({
type: "DocxDocument",
pageSize: "a4",
orientation: "portrait",
pages: [
{
elements: [
{ type: "heading", level: 1, text: "Quarterly Report" },
{ type: "paragraph", text: "Section content here." }
]
}
]
});
fs.writeFileSync("report.docx", result.buffer);
console.log("Generated report.docx");Example: XLSX generation
import { SpreadsheetEngine } from "@paperjsx/json-to-xlsx";
import fs from "node:fs";
const spec = {
meta: { title: "Revenue Data", creator: "PaperJSX" },
sheets: [{
name: "Revenue",
rows: [
{ cells: [{ value: "Quarter" }, { value: "Revenue" }] },
{ cells: [{ value: "Q1 2026" }, { value: 420000 }] },
{ cells: [{ value: "Q2 2026" }, { value: 510000 }] }
]
}]
};
const buffer = await SpreadsheetEngine.render(spec);
fs.writeFileSync("revenue.xlsx", buffer);
console.log("Generated revenue.xlsx");Validation
After generating any file, always verify:
import fs from "node:fs";
const stats = fs.statSync("output.pptx");
if (stats.size === 0) {
throw new Error("Generated file is empty");
}
console.log(`Output file: ${stats.size} bytes`);If the engine throws an error, surface the full error message to the user.
Schema reference
See references/json-schema.md for the complete JSON layout spec schema for all supported formats.
Related skills
- akf-trust-metadata – The AI native file format. EXIF for AI — stamps every file with trust scores, source…
- board-prep – Board meeting preparation for the adversarial scenario, not the friendly one. Forces…
- book-to-skill – Converts books, documentation folders, and source collections (PDF, EPUB, DOCX, HTML…
- deepspot-m – Generates transcriptome-wide virtual spatial transcriptomics from H&E histology with…
- baoyu-slide-deck – Generates professional slide deck images from content. Creates outlines with style…
- baoyu-url-to-markdown – Fetch any URL and convert to markdown using baoyu-fetch CLI (Chrome CDP with…
- pdf – Use when tasks involve reading, creating, or reviewing PDF files where rendering and…
- dcf-model – Build discounted cash flow valuation workbooks in Excel.