Documents Claude Code skills

The four production document skills that power Claude's file creation: read/create/edit Word, PDF, PowerPoint and Excel files with proper formatting, tracked changes, formulas and charts.

Anthropic's official skill repo and Agent Skills spec home: the canonical document skills (docx, pdf, pptx, xlsx), artifacts-builder, mcp-builder, canvas-design, frontend-design, plus the /template and /spec folders that define the format.

Create, read, edit, and manipulate Word documents (.docx), including tracked changes, comments, images, find-and-replace, and polished formatted deliverables like reports and letters.

Full PDF toolbox: extract text and tables, merge/split, rotate, watermark, fill forms, encrypt/decrypt, extract images, and OCR scanned PDFs.

Create, read, and edit PowerPoint decks: build presentations from scratch or templates, extract slide text, and work with layouts, speaker notes, and comments.

Open, create, and fix spreadsheets (.xlsx/.xlsm/.csv/.tsv): formulas, formatting, charts, and cleaning messy tabular data, with a zero-formula-error delivery standard.

Structured three-stage workflow (context gathering, refinement, reader testing) for co-authoring docs, proposals, specs, and decision documents.

Builds HTML slide decks and converts them to PPTX.

Long-form writing that avoids generic AI tone.

Generate polished HTML presentations using the Reveal.js framework instead of PowerPoint.

Convert markdown documents, chat summaries, or research reports into downloadable EPUB files for Kindle and e-readers.

Audit and rewrite content to remove 21 categories of telltale AI writing patterns.

Scans a project's structure and generates a complete README.md (features, setup, usage).

Create and edit JSON Canvas files (.canvas) with nodes, edges, groups, and connections. Use when working with .canvas files, creating visual canvases, mind maps, flowcharts, or when the user mentions Canvas files in Obsidian.