Skip to content
SkillModel-led977 tokens in use

CLI Developer

Builds command-line tools in Node, Python or Go with consistent flags, early input checks, TTY-aware color, graceful Ctrl+C and shell completions.

12,471 stars on the repository MIT LicenseJeffallan/claude-skills · skills/cli-developer
/plugin marketplace add jeffallan/claude-skills /plugin install fullstack-dev-skills@fullstack-dev-skills
View source

Install command as written in the repository's README

Skill label

measured from its files

What installing CLI Developer costs

67tokens idle
977tokens in use
12,433tokens, up to

Idle is what sits in context while the skill is installed. In use is its instructions, loaded when it runs. Up to adds the files its instructions link. Counts are approximate, made offline with cl100k_base.

Model dependence Model-led

Script-ledMixedModel-led

Mostly instructions, so how well it works depends on the model that follows them.

This describes the skill's structure, how much of it is scripts. It does not say how well it works.

Touches

networkdetected

Declared tags come from the skill's frontmatter; detected ones from its scripts, its code blocks and the commands it names in inline code. This is detected, not audited.

How it scores

Quality

How well the skill is written, counted from its own files: its frontmatter, its steps, examples, stated output and constraints, its size and whether every file it ships is one it names.How we score it →
Excellent
  • Frontmatter15/15
  • Structure22/25
  • Examples12/15
  • Output15/15
  • Size15/15
  • Resources15/15

Security

Starts at 100 and loses points for each thing in the skill's files that a reader should look at first.How we score it →
Excellent

No findings.

Repository health

Pre-computed score based on development activity, maintenance, community, maturity, and trend momentum.How we score it →
Excellent
  • Development activity100
  • Maintenance100
  • Community60
  • Maturity36
  • Momentum40

CLI Developer guides Claude through building a command-line tool: map the user workflows, design the command tree, implement with the right framework, polish and test.

It covers commander, yargs and inquirer for Node, click, typer and rich for Python, and cobra, viper and bubbletea for Go, and sets firm rules for output, interactivity and startup time.

What You Get

  • A command structure with an entry point and subcommands
  • Configuration handling across files, environment variables and flags
  • Implementation with clear, actionable error messages
  • Shell completion scripts for bash, zsh and fish where the framework supports them
  • A short explanation of the user experience decisions

Common Use Cases

  • Starting a new Node.js CLI with commander
  • Building a Python tool with click or typer
  • Writing a Go CLI with cobra and viper
  • Adding progress bars, spinners and prompts
  • Generating shell completions for an existing tool

What Makes It Unique

The rules cover real terminal behavior: send diagnostics to stderr when output is piped, skip color when output is not a TTY, give non-interactive fallbacks for CI and resolve paths with home directory helpers. Reference files are split by language and by UX patterns.

Under The Hood

The skill is a SKILL.md with five reference files for design patterns, Node, Python, Go and UX patterns. It has no scripts of its own. During a run the agent builds the tool in your project and runs it, calling the new command with —help and —version and running cross-platform smoke tests and startup benchmarks, so it executes shell commands and writes source files there. It does not fetch web pages or call outside APIs.

Join founders building with open source

Opinionated takes, migration guides, cost-saving tips, and insights from the open source ecosystem.

Subscribe on SubstackJoin 750+ subscribers