skills.rest
rameshkumarchouhanr
rameshkumarchouhanrCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

agent-tui

Automate and test terminal UI applications through screenshot-driven interaction loops.

Updated Aug 26, 2026
Search Tags:#cli#regression testing#screenshot#terminal automation#keystroke automation#tui testing#agent-tui
One-click install
npx skills add https://github.com/rameshkumarchouhanr/gemni-cli --skill agent-tui-rameshkumarchouhanr
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: agent-tui
Source: https://github.com/rameshkumarchouhanr/gemni-cli/tree/main/.gemini/skills/agent-tui
Command: npx skills add https://github.com/rameshkumarchouhanr/gemni-cli --skill agent-tui-rameshkumarchouhanr

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Testing and automating interactive terminal UI applications is difficult because terminal screens are stateless character grids without a persistent DOM, making traditional automation approaches unreliable and flaky. ## Core Features & Use Cases - Programmatic TUI Control: Launch terminal applications in managed sessions and interact via screenshots, keystrokes, and text input. - State Verification: Wait for specific text to appear or disappear, or for the UI to stabilize, with assertion-based verification of outcomes. - Regression Testing: Automate CLI/TUI interaction testing, including Gemini CLI testing with isolated environments and trust-modal bypassing. - Use Case: Verify that a CLI application's interactive prompts behave correctly by launching it in a session, typing responses, pressing keys, and asserting expected output appears on screen. ## Quick Start Use agent-tui to launch my CLI application, take a screenshot of its interface, and verify the welcome message appears.

Frequently Asked Questions about agent-tui

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I automate a terminal UI application for testing?▼

Launch the app with agent-tui run, take a screenshot to observe the current state, then act with type or press commands. Always wait for expected text or UI stability and verify outcomes with assertions before proceeding to the next action.

How to test interactive CLI apps with agent-tui?▼

Start the CLI in a session using agent-tui run, then follow the observe-decide-act-wait-verify loop. For Gemini CLI specifically, build the project first and set GEMINI_CLI_TRUST_WORKSPACE=true to bypass trust modals that intercept keystrokes.

Does agent-tui work on Windows?▼

No, agent-tui currently supports only macOS and Linux. Windows is not supported yet according to the documented prerequisites.

Why does agent-tui fail with connection refused on macOS?▼

The default background daemonization crashes on macOS, causing connection refused errors. Start the daemon manually inside a tmux session with agent-tui daemon start --foreground to shield it from TTY hangups.

What should I do when an agent-tui wait command times out?▼

Take a screenshot to visually diagnose what intercepted the flow, such as a modal, error dialog, or lost focus. Do not blindly restart the session; if failures repeat after 3-5 attempts, stop and reassess.

Related Skills

Explore More Software Engineering Skills→
Coverage-CreativesCoverage-Creatives

Test Environment Setup

Configure isolated test environments with Supabase and environment variables.

Official
Intermediate
i-standard1i-standard1
6

gen-test-report

Consolidate unit, integration, and end-to-end test results into a standardized report.

Official
Intermediate
BradliebsBradliebs

canary

Monitor live web apps for console errors, performance regressions, and visual anomalies.

Community
Advanced
adoptaiadoptai
25

noui-autopilot

Record browser workflows and compile them into MCP servers.

Official
Advanced