Control Cli

When you need to reproduce a CLI bug or check how your TUI handles a resize, this gives Claude a structured way to drive interactive commands without manual poking. It prefers existing test harnesses but can spin up tmux sessions or PTY scripts to send keystrokes, wait for prompts, and capture transcripts. Handy for startup profiling, memory leak hunting, or recording terminal demos. The tmux and Python examples are bare bones enough to adapt quickly, and the deterministic wait advice will save you from flaky sleeps. Treats the harness as temporary unless your repo already has demo tooling.

skills.sh installs: 2.6K
GitHub stars: 15.9K
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add cursor/plugins --skill control-cli --agent claude-code

Installs into .claude/skills of the current project.

Files

Control CLI

Use a repeatable local harness to exercise an interactive CLI instead of poking at it manually. First reuse the repo's own test/demo harness if it exists; otherwise assemble a temporary harness from standard local tools.

What It Is Used For

Reproducing CLI/TUI bugs with deterministic input.
Verifying keyboard flows, prompts, interrupts, resize behavior, and terminal layout.
Capturing before/after transcripts for bug fixes.
Profiling startup time, slow operations, hangs, or memory growth.
Recording a short terminal demo when output is easier to show than explain.

Harness Loop

Identify the command under test and the smallest reproducible workspace.
Discover existing local harnesses: package scripts, e2e tests, demo recorders, expect scripts, or PTY helpers.
If no harness exists, launch the CLI in an isolated terminal session with deterministic env vars.
Capture the current screen before interacting.
Send one action at a time: text, Enter, arrows, Escape, Ctrl-C, resize.
Wait for a concrete screen pattern or prompt before the next action.
Save the transcript and any profile artifacts.
Kill the session cleanly.

SKILL.md on GitHub