CLI

What it does

When your agent uses it

• Working with R code that needs to:
• Format console output with inline markup and colors
• Messages with cliabort/cliwarn/cliinform
• Show progress indicators for long-running operations

Example prompts

• “/cli”

What it can do on your machine

Read from SKILL.md and the folder at commit bd2329a. It shows what the files ask for, not the result of running them.

• Tool permissions

  Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

  From allowed-tools in the SKILL.md frontmatter.

• Runs code

  No scripts in the folder and no shell commands in SKILL.md (its code samples are r).

  From the folder's file list and the shell code blocks in SKILL.md.

• Network

  Links to these hosts (documentation or services it may open):

  • cli.r-lib.org
  • github.com

  From URLs in SKILL.md, links to its own repository left out.

• Credentials

  Names no API keys, tokens, secrets or passwords.

  From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

CLI loads about 2.8k tokens when it runs, and up to ~26k if it reads all its reference files. Until then it costs about 173 tokens; SKILL.md has 467 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~173

When it runs · the whole SKILL.md, loaded when a task matches

~2.8k

With references · SKILL.md plus every file in references/, read only if the agent opens them

~26k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from quarto-dev/quarto-r at commit bd2329a, republished under its MIT licence (© quarto-dev). 467 words, ~2,804 tokens.

name

cli

description

Comprehensive R package for command-line interface styling, semantic messaging, and user communication. Use this skill when working with R code that needs to: (1) Format console output with inline markup and colors, (2) Display errors, warnings, or messages with cli_abort/cli_warn/cli_inform, (3) Show progress indicators for long-running operations, (4) Create semantic CLI elements (headers, lists, alerts, code blocks), (5) Apply themes and customize output styling, (6) Handle pluralization in user-facing text, (7) Work with ANSI strings, hyperlinks, or custom containers. Also use when migrating from base R message/warning/stop, debugging cli code, or improving existing cli usage.

metadata.author

Garrick Aden-Buie (@gadenbuie)

metadata.version

1.0

license

MIT

# Basic formatting
cli_text("Function {.fn mean} calculates averages")
cli_text("Install package {.pkg dplyr}")
cli_text("See file {.file ~/.Rprofile}")
cli_text("{.var x} must be numeric, not {.obj_type_of {x}}")
cli_text("Got value {.val {x}}"))

# Code formatting
cli_text("Use {.code sum(x, na.rm = TRUE)}")

# Paths and arguments
cli_text("Reading from {.path /data/file.csv}")
cli_text("Set {.arg na.rm} to TRUE")

# Types and classes
cli_text("Object is {.cls data.frame}")

# Emphasis
cli_text("This is {.emph important}")
cli_text("This is {.strong critical}")

# Fields
cli_text("The {.field name} field is required")

pkgs <- c("dplyr", "tidyr", "ggplot2")
cli_text("Installing packages: {.pkg {pkgs}}")
#> Installing packages: dplyr, tidyr, and ggplot2

files <- c("data.csv", "script.R")
cli_text("Found {length(files)} file{?s}: {.file {files}}")
#> Found 2 files: data.csv and script.R

cli_text("Use {{variable}} syntax in glue")
#> Use {variable} syntax in glue

nfile <- 1
cli_text("Found {nfile} file{?s}")
#> Found 1 file

nfile <- 3
cli_text("Found {nfile} file{?s}")
#> Found 3 files

ndir <- 1
cli_text("Found {ndir} director{?y/ies}")
#> Found 1 directory

ndir <- 5
cli_text("Found {ndir} director{?y/ies}")
#> Found 5 directories

nfile <- 0
cli_text("Found {nfile} file{?s}: {?no/the/the} file{?s}")
#> Found 0 files: no files

nfile <- 1
cli_text("Found {nfile} file{?s}: {?no/the/the} file{?s}")
#> Found 1 file: the file

nfile <- 3
cli_text("Found {nfile} file{?s}: {?no/the/the} file{?s}")
#> Found 3 files: the files

nfile <- 0
cli_text("Found {no(nfile)} file{?s}")
#> Found no files

nupd <- 3
ntotal <- 10
cli_text("{nupd}/{ntotal} {qty(nupd)} file{?s} {?needs/need} updates")
#> 3/10 files need updates

# Before (base R)
stop("File not found: ", path)

# After (cli)
cli_abort("File {.file {path}} not found")

# With bullets for context
check_file <- function(path) {
  if (!file.exists(path)) {
    cli_abort(c(
      "File not found",
      "x" = "Cannot read {.file {path}}",
      "i" = "Check that the file exists"
    ))
  }
}

# Before (base R)
warning("Column ", col, " has missing values")

# After (cli)
cli_warn("Column {.field {col}} has missing values")

# With context
cli_warn(c(
  "Data quality issues detected",
  "!" = "Column {.field {col}} has {n_missing} missing value{?s}",
  "i" = "Consider using {.fn tidyr::drop_na}"
))

# Before (base R)
message("Processing ", n, " files")

# After (cli)
cli_inform("Processing {n} file{?s}")

# With structure
cli_inform(c(
  "v" = "Successfully loaded {.pkg dplyr}",
  "i" = "Version {packageVersion('dplyr')}"
))

process_data <- function() {
  cli_progress_step("Loading data")
  data <- load_data()

  cli_progress_step("Cleaning data")
  clean <- clean_data(data)

  cli_progress_step("Analyzing data")
  analyze(clean)
}

process_files <- function(files) {
  cli_progress_bar("Processing files", total = length(files))

  for (file in files) {
    process_file(file)
    cli_progress_update()
  }
}

process <- function() {
  cli_progress_bar("Working", total = 100)
  for (i in 1:100) {
    Sys.sleep(0.01)
    cli_progress_update()
  }
  # No need to call cli_progress_done() - auto-closes
}

cli_h1("Main Section")
cli_h2("Subsection")
cli_h3("Detail")

cli_alert_success("Operation completed successfully")
cli_alert_danger("Critical error occurred")
cli_alert_warning("Potential issue detected")
cli_alert_info("Additional information available")

# Regular text with markup
cli_text("This is formatted text with {.emph emphasis}")

# Code blocks
cli_code(c(
  "library(dplyr)",
  "mtcars %>% filter(mpg > 20)"
))

# Verbatim text (no formatting)
cli_verbatim("This is displayed exactly as-is: {not interpolated}")

# Unordered list
cli_ul()
cli_li("First item")
cli_li("Second item")
cli_end()

# Ordered list
cli_ol()
cli_li("First step")
cli_li("Second step")
cli_end()

# Definition list
cli_dl()
cli_li(c(name = "The name field"))
cli_li(c(email = "The email address"))
cli_end()

# Before: Base R error handling
validate_input <- function(x, y) {
  if (!is.numeric(x)) {
    stop("x must be numeric")
  }
  if (length(y) == 0) {
    stop("y cannot be empty")
  }
  if (length(x) != length(y)) {
    stop("x and y must have the same length")
  }
}

# After: CLI error handling
validate_input <- function(x, y) {
  if (!is.numeric(x)) {
    cli_abort(c(
      "{.arg x} must be numeric",
      "x" = "You supplied a {.cls {class(x)}} vector",
      "i" = "Use {.fn as.numeric} to convert"
    ))
  }

  if (length(y) == 0) {
    cli_abort(c(
      "{.arg y} cannot be empty",
      "i" = "Provide at least one element"
    ))
  }

  if (length(x) != length(y)) {
    cli_abort(c(
      "{.arg x} and {.arg y} must have the same length",
      "x" = "{.arg x} has length {length(x)}",
      "x" = "{.arg y} has length {length(y)}"
    ))
  }
}

check_required_columns <- function(data, required_cols) {
  actual_cols <- names(data)
  missing_cols <- setdiff(required_cols, actual_cols)

  if (length(missing_cols) > 0) {
    cli_abort(c(
      "Required column{?s} missing from data",
      "x" = "Missing {length(missing_cols)} column{?s}: {.field {missing_cols}}",
      "i" = "Data has {length(actual_cols)} column{?s}: {.field {actual_cols}}",
      "i" = "Add the missing column{?s} or check for typos"
    ))
  }

  invisible(data)
}

process_files <- function(files, verbose = TRUE) {
  n <- length(files)

  if (verbose) {
    cli_progress_bar(
      format = "Processing {cli::pb_bar} {cli::pb_current}/{cli::pb_total} [{cli::pb_eta}]",
      total = n
    )
  }

  results <- vector("list", n)

  for (i in seq_along(files)) {
    results[[i]] <- process_file(files[[i]])

    if (verbose) {
      cli_progress_update()
    }
  }

  results
}

© quarto-dev, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 5 other files (references) in .claude/skills/cli of quarto-dev/quarto-r.

• SKILL.md
• references/ansi-operations.md
• references/conditions.md
• references/inline-markup.md
• references/progress.md
• references/themes.md

Open the folder on GitHubat commit bd2329a

Used in 1 other repository

We found 1 copy of this SKILL.md (exact, near-identical or edited) in other folders, from 1 other GitHub owner. This page covers the copy in quarto-dev/quarto-r, which our catalogue first saw on October 7, 2026.

• posit-dev/skillsr-lib/r-cli