Cli

CLI for R Packages

When to Use What

task: Display error with context and formatting use: cli_abort() with inline markup and bullet lists

task: Show warning with formatting use: cli_warn() with inline markup

task: Display informative message use: cli_inform() with inline markup

task: Show progress for counted operations use: cli_progress_bar() with total count

task: Show simple progress steps use: cli_progress_step() with status messages

task: Format code or function names use: {.code ...} or {.fn package::function}

task: Format file paths use: {.file path/to/file}

task: Format package names use: {.pkg packagename}

task: Format variable names use: {.var variable_name}

task: Format values use: {.val value}

task: Handle singular/plural text use: {?s} or {?y/ies} with pluralization

task: Create headers use: cli_h1(), cli_h2(), cli_h3()

task: Create alerts use: cli_alert_success(), cli_alert_danger(), cli_alert_warning(), cli_alert_info()

task: Create lists use: cli_ul(), cli_ol(), cli_dl() with cli_li()

Inline Markup Essentials

Use inline markup with {.class content} syntax to format text:

# 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")

Vector Collapsing

Vectors are automatically collapsed with commas and "and":

pkgs  Installing packages: dplyr, tidyr, and ggplot2

files  Found 2 files: data.csv and script.R

Escaping Braces

Use double braces {{ and }} to escape literal braces:

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

For complete markup reference: See [references/inline-markup.md](references/inline-markup.md) for all 50+ inline classes, edge cases, nesting rules, and advanced patterns.

Pluralization Basics

Use {?} for pluralization with three patterns:

Single Alternative

nfile  Found 1 file

nfile  Found 3 files

Two Alternatives

ndir  Found 1 directory

ndir  Found 5 directories

Three Alternatives (zero/one/many)

nfile  Found 0 files: no files

nfile  Found 1 file: the file

nfile  Found 3 files: the files

Helpers: qty() and no()

Use no() to display "no" instead of zero:

nfile  Found no files

Use qty() to set quantity explicitly:

nupd  3/10 files need updates

For advanced pluralization: See [references/inline-markup.md](references/inline-markup.md) for edge cases and complex patterns.

CLI Conditions: Core Patterns

Use cli conditions instead of base R for better formatting:

cli_abort() - Formatted Errors

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

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

# With bullets for context
check_file "` - Arrow/pointer

**For advanced error design**: See [references/conditions.md](references/conditions.md) for error design principles, rlang integration, testing strategies, and real-world patterns.

## Basic Progress Indicators

### Simple Progress Steps

```r
process_data % filter(mpg > 20)"
))

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

Lists

# 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()

Common Workflows

Base R to CLI Migration

# Before: Base R error handling
validate_input  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)
}

Function with Progress Bar

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
}

Resources & Advanced Topics

Reference Files

• [references/inline-markup.md](references/inline-markup.md) - Complete catalog of inline classes organized by category, advanced patterns, nesting rules, and real-world examples

• [references/conditions.md](references/conditions.md) - Advanced error design patterns, rlang integration, testing with testthat snapshots, migration guide, and anti-patterns

• [references/progress.md](references/progress.md) - Nested progress bars, custom formats, all progress variables, parallel processing, Shiny integration, and debugging

• [references/themes.md](references/themes.md) - Complete theming system with CSS-like selectors, container functions, color palettes, custom themes, and accessibility

• [references/ansi-operations.md](references/ansi-operations.md) - ANSI string operations (align, columns, nchar, etc.), hyperlinks, color detection, testing CLI output, and troubleshooting

External Resources

• cli package documentation
• cli GitHub repository
• Building a semantic CLI (article)

Related Packages

• rlang - Condition handling and error objects integrate with cli
• glue - String interpolation powers cli's {} syntax
• testthat - Snapshot testing for cli output

Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

• Author: posit-dev
• Source: posit-dev/skills
• License: MIT

Install and usage instructions live in the source repository linked above.