Use when the user is explicitly working with Quarto, .qmd files, _quarto.yml, Quarto projects, or Quarto features such as callouts, cross-references, citations, Mermaid diagrams, extensions, websites, books, presentations, and reports. Also use for explicit migration from or comparison with R Markdown, bookdown, blogdown, xaringan, distill, or Jupyter notebooks to Quarto. Do not use for general R Markdown or related-format questions unless Quarto or migration to Quarto is explicitly mentioned.
npx skills add https://github.com/posit-dev/skills --skill quarto-authoring
> This skill is based on Quarto CLI v1.9.36 (2026-03-24).
Task: Write a new Quarto document
Use: Follow "QMD Essentials" below, then see specific reference files
Task: Add cross-references
Use: references/cross-references.md
Task: Configure code cells
Use: references/code-cells.md
Task: Add figures with captions
Use: references/figures.md
Task: Create tables
Use: references/tables.md
Task: Add citations and bibliography
Use: references/citations.md
Task: Add callout blocks
Use: references/callouts.md
Task: Add diagrams (Mermaid, Graphviz)
Use: references/diagrams.md
Task: Control page layout
Use: references/layout.md
Task: Use shortcodes
Use: references/shortcodes.md
Task: Add conditional content
Use: references/conditional-content.md
Task: Use divs and spans
Use: references/divs-and-spans.md
Task: Configure YAML front matter
Use: references/yaml-front-matter.md
Task: Find and use extensions
Use: references/extensions.md
Task: Apply markdown linting rules
Use: references/markdown-linting.md
Task: Choose or configure a compute engine (knitr, jupyter, julia)
Use: references/engines.md
Do NOT read these references when writing new Quarto documents.
Only read the one matching the source format when the user explicitly asks to convert or migrate an existing project.
---
title: "Document Title"
author: "Author Name"
date: today
format: html
---
Content goes here.
A Quarto document consists of two main parts:
---.Divs use fenced syntax with three colons:
::: {.class-name}
Content inside the div.
:::
Spans use bracketed syntax:
This is [important text]{.highlight}.
Details: references/divs-and-spans.md
A code cell starts with triple backticks and a language identifier between curly braces.
Code cells are code blocks that can be executed to produce output.
Quarto uses the language's comment symbol + | for cell options. Options use dashes, not dots (e.g., fig-cap not fig.cap).
#|%%|//|
Set document-level defaults in YAML front matter:
execute:
echo: false
warning: false
Caching — critical engine difference: Only suggest #| cache: true for R code cells (knitr engine).
Never suggest it for other language cells — it does not work and will be silently ignored.
The only correct approach is execute: cache: true in the top-level YAML front matter when using engines other than knitr.
Python/Jupyter requires jupyter-cache (pip install jupyter-cache):
execute:
cache: true
Details: references/code-cells.md
Labels must start with a type prefix. Reference with @:
fig- prefix, e.g., #| label: fig-plot → @fig-plottbl- prefix, e.g., #| label: tbl-data → @tbl-datasec- prefix, e.g., {#sec-intro} → @sec-introeq- prefix, e.g., {#eq-model} → @eq-model
See @fig-plot for the results.
Details: references/cross-references.md
Five types: note, warning, important, tip, caution.
::: {.callout-note}
This is a note callout.
:::
::: {.callout-warning}
## Custom Title
This is a warning with a custom title.
:::
Details: references/callouts.md
{#fig-name fig-alt="Alt text"}
Subfigures:
::: {#fig-group layout-ncol=2}
{#fig-sub1}
{#fig-sub2}
Main caption for the group.
:::
Details: references/figures.md
::: {#tbl-example}
| Column 1 | Column 2 |
| -------- | -------- |
| Data 1 | Data 2 |
Table caption.
:::
Details: references/tables.md
According to @smith2020, the results show...
Multiple citations [@smith2020; @jones2021].
Configure in YAML:
bibliography: references.bib
csl: apa.csl
Details: references/citations.md
title: "My Report"
author: "Your Name"
date: today
format:
html:
toc: true
code-fold: true
theme: cosmo
title: "My Report"
format:
pdf:
documentclass: article
papersize: a4
---
title: "My Presentation"
format: revealjs
---
## First Slide
Content here.
## Second Slide
More content.
Create _quarto.yml in the project root:
project:
type: website
website:
title: "My Site"
navbar:
left:
- href: index.qmd
text: Home
- href: about.qmd
text: About
format:
html:
theme: cosmo
Assists in writing high-quality content by conducting research, adding citations, improving hooks, iterating on outlines, and providing real-time feedback on each section. Transforms your writing process from solo effort to collaborative partnership.
Identifies high-quality leads for your product or service by analyzing your business, searching for target companies, and providing actionable contact strategies. Perfect for sales, business development, and marketing professionals.
Use this skill to query your Google NotebookLM notebooks directly from Claude Code for source-grounded, citation-backed answers from Gemini. Browser automation, library management, persistent auth. Drastically reduced hallucinations through document-only responses.
Efficient database search tool for bioRxiv preprint server. Use this skill when searching for life sciences preprints by keywords, authors, date ranges, or categories, retrieving paper metadata, downloading PDFs, or conducting literature reviews.
Query and analyze scholarly literature using the OpenAlex database. This skill should be used when searching for academic papers, analyzing research trends, finding works by authors or institutions, tracking citations, discovering open access publications, or conducting bibliometric analysis across 240M+ scholarly works. Use for literature searches, research output analysis, citation analysis, and academic database queries.
Access USPTO APIs for patent/trademark searches, examination history (PEDS), assignments, citations, office actions, TSDR, for IP analysis and prior art searches.
Multiagent AI system for scientific research assistance that automates research workflows from data analysis to publication. This skill should be used when generating research ideas from datasets, developing research methodologies, executing computational experiments, performing literature searches, or generating publication-ready papers in LaTeX format. Supports end-to-end research pipelines with customizable agent orchestration.
Automated LLM-driven hypothesis generation and testing on tabular datasets. Use when you want to systematically explore hypotheses about patterns in empirical data (e.g., deception detection, content analysis). Combines literature insights with data-driven hypothesis testing. For manual hypothesis formulation use hypothesis-generation; for creative ideation use scientific-brainstorming.
Take posit-dev/quarto-authoring from the repository into ~/.claude/skills for personal
use, or into .claude/skills inside a project.
The agent identifies a skill by the name field in its header. Two skills with the
same name cannot sit side by side — one of them will be ignored.
The instructions reference pip.
Without those the skill loads but fails at the first command.