Create Cli

This walks you through designing a CLI from scratch, covering the whole surface area: arguments, flags, subcommands, output formats, error handling, configuration precedence, and dry-run semantics. It front-loads the clig.dev guidelines as a default rubric, asks only the minimum clarifying questions, then outputs a complete spec with usage synopsis, exit codes, stdin/stdout contracts, and example invocations. Use it when you need to nail down the interface before writing any code. The structured deliverables list is thorough without being prescriptive about implementation. It defaults to sensible conventions like respecting NO_COLOR and requiring confirmations for destructive operations, but stays language-agnostic unless you need parsing library recommendations.

skills.sh installs: 437
GitHub stars: 7.5K
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add steipete/agent-scripts --skill create-cli --agent claude-code

Installs into .claude/skills of the current project.

Files

Create CLI

Design CLI surface area (syntax + behavior), human-first, script-friendly.

Do This First

Read agent-scripts/skills/create-cli/references/cli-guidelines.md and apply it as the default rubric.
Upstream/full guidelines: https://clig.dev/ (propose changes: https://github.com/cli-guidelines/cli-guidelines)
Ask only the minimum clarifying questions needed to lock the interface.

Clarify (fast)

Ask, then proceed with best-guess defaults if user is unsure:

Command name + one-sentence purpose.
Primary user: humans, scripts, or both.
Input sources: args vs stdin; files vs URLs; secrets (never via flags).
Output contract: human text, --json, --plain, exit codes.
Interactivity: prompts allowed? need --no-input? confirmations for destructive ops?
Config model: flags/env/config-file; precedence; XDG vs repo-local.
Platform/runtime constraints: macOS/Linux/Windows; single binary vs runtime.