create-quarto-report
About
This skill creates Quarto documents for reproducible reports, presentations, and websites. It handles YAML configuration, code chunks, output formats, and rendering to HTML/PDF/Word. Use it for analyses with embedded code or migrating from R Markdown.
Quick Install
Claude Code
Recommendednpx skills add pjt222/agent-almanac -a claude-code/plugin add https://github.com/pjt222/agent-almanacgit clone https://github.com/pjt222/agent-almanac.git ~/.claude/skills/create-quarto-reportCopy and paste this command in Claude Code to install this skill
Documentation
Create Quarto Report
Repro Quarto doc → reports / presentations / websites.
Use When
- Repro analysis report
- Presentation w/ embedded code
- Gen HTML/PDF/Word from code
- Migrate R Markdown → Quarto
In
- Required: Topic + audience
- Required: Out fmt (html, pdf, docx, revealjs)
- Optional: Data + analysis code
- Optional: Bib (.bib)
Do
Step 1: Create Doc
report.qmd:
---
title: "Analysis Report"
author: "Author Name"
date: today
format:
html:
toc: true
toc-depth: 3
code-fold: true
theme: cosmo
self-contained: true
execute:
echo: true
warning: false
message: false
bibliography: references.bib
---
Got: report.qmd exists w/ valid YAML (title, author, date, format, exec).
If err: Validate YAML header — --- delimiters match, indent correct. format: = supported (html, pdf, docx, revealjs).
Step 2: Content + Chunks
## Introduction
This report analyzes the relationship between variables X and Y.
## Data
```{r}
#| label: load-data
library(dplyr)
library(ggplot2)
data <- read.csv("data.csv")
glimpse(data)
```
## Analysis
```{r}
#| label: fig-scatter
#| fig-cap: "Scatter plot of X vs Y"
#| fig-width: 8
#| fig-height: 6
ggplot(data, aes(x = x_var, y = y_var)) +
geom_point(alpha = 0.6) +
geom_smooth(method = "lm") +
theme_minimal()
```
As shown in @fig-scatter, there is a positive relationship.
## Results
```{r}
#| label: tbl-summary
#| tbl-cap: "Summary statistics"
data |>
summarise(
mean_x = mean(x_var),
sd_x = sd(x_var),
mean_y = mean(y_var),
sd_y = sd(y_var)
) |>
knitr::kable(digits = 2)
```
See @tbl-summary for descriptive statistics.
Got: Sections w/ {r} chunks + #| opts (labels, captions, dims).
If err: Verify ```{r} syntax (not inline). #| inside chunk (not YAML). Label prefix matches xref type (fig-, tbl-).
Step 3: Chunk Opts
Common (#|):
#| label: chunk-name # Required for cross-references
#| echo: false # Hide code
#| eval: false # Show but don't run
#| output: false # Run but hide output
#| fig-width: 8 # Figure dimensions
#| fig-height: 6
#| fig-cap: "Caption text" # Enable @fig-name references
#| tbl-cap: "Caption text" # Enable @tbl-name references
#| cache: true # Cache expensive computations
Got: Opts via #| syntax, labels = xref naming conv.
If err: #| (Quarto-native), not legacy {r, option=value}. Labels alphanumeric + hyphens only.
Step 4: Xrefs + Citations
See @fig-scatter for the visualization and @tbl-summary for statistics.
This approach follows @smith2023 methodology.
::: {#fig-combined layout-ncol=2}
{#fig-plotA}
{#fig-plotB}
Combined figure caption
:::
Got: Xrefs (@fig-name, @tbl-name) resolve. Citations (@key) match .bib.
If err: Verify labels exist w/ correct prefix (fig-, tbl-). .bib keys exact (case-sensitive). bibliography: in YAML.
Step 5: Render
quarto render report.qmd
# Specific format
quarto render report.qmd --to pdf
quarto render report.qmd --to docx
# Preview with live reload
quarto preview report.qmd
Got: Out file in fmt.
If err:
- No quarto → install https://quarto.org/docs/get-started/
- PDF err →
quarto install tinytex - R pkg err → install
Step 6: Multi-Fmt Out
format:
html:
toc: true
theme: cosmo
pdf:
documentclass: article
geometry: margin=1in
docx:
reference-doc: template.docx
Render all: quarto render report.qmd
Got: All fmts gen, correct styling per target.
If err: 1 fail, others OK → check fmt-specific. PDF → LaTeX engine (quarto install tinytex). DOCX → valid ref template if set. Fmt opts nested under each format key.
Check
- Renders no err
- All chunks execute
- Xrefs resolve (fig, tbl, cite)
- TOC accurate
- Out fmt fits audience
Traps
- No label prefix: Fig xref needs
fig-, tbl needstbl- - Cache invalid: Cached chunks don't re-run on upstream change. Delete
_cache/→ force. - PDF no LaTeX: Install TinyTeX OR
pdf-engine: weasyprint(CSS-based) - RMD syntax in Quarto: Use
#|not{r, echo=FALSE}
→
format-apa-report— APA academic reportsbuild-parameterized-report— param multi-reportsgenerate-statistical-tables— pub-ready tableswrite-vignette— Quarto vignettes in R pkgs
GitHub Repository
Related Skills
content-collections
MetaThis skill provides a production-tested setup for Content Collections, a TypeScript-first tool that transforms Markdown/MDX files into type-safe data collections with Zod validation. Use it when building blogs, documentation sites, or content-heavy Vite + React applications to ensure type safety and automatic content validation. It covers everything from Vite plugin configuration and MDX compilation to deployment optimization and schema validation.
polymarket
MetaThis skill enables developers to build applications with the Polymarket prediction markets platform, including API integration for trading and market data. It also provides real-time data streaming via WebSocket to monitor live trades and market activity. Use it for implementing trading strategies or creating tools that process live market updates.
creating-opencode-plugins
MetaThis skill helps developers create OpenCode plugins that hook into 25+ event types like commands, files, and LSP operations. It provides the plugin structure, event API specifications, and implementation patterns for JavaScript/TypeScript modules. Use it when you need to intercept, monitor, or extend the OpenCode AI assistant's lifecycle with custom event-driven logic.
sglang
MetaSGLang is a high-performance LLM serving framework that specializes in fast, structured generation for JSON, regex, and agentic workflows using its RadixAttention prefix caching. It delivers significantly faster inference, especially for tasks with repeated prefixes, making it ideal for complex, structured outputs and multi-turn conversations. Choose SGLang over alternatives like vLLM when you need constrained decoding or are building applications with extensive prefix sharing.
