Agent skill

Terminal UI Automation

Drives terminal UI apps from the command line for testing, demos and scripted interactions, using a run, screenshot, act, wait loop.

MITAuto-check passedTesting & QA

Install Terminal UI Automation

skills CLI

$ npx skills add pproenca/agent-tui --skill agent-tui -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI

$ gh skill install pproenca/agent-tui agent-tui --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy

$ git clone --depth 1 https://github.com/pproenca/agent-tui.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/agent-tui .claude/skills/agent-tui && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Paste into Claude Code

Install the "agent-tui" agent skill from https://github.com/pproenca/agent-tui/tree/master/skills/agent-tui into .claude/skills/agent-tui/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "agent-tui", then confirm the skill loads.

Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

$skill-installer

$skill-installer install https://github.com/pproenca/agent-tui/tree/master/skills/agent-tui

Type this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.

skills CLI

$ npx skills add pproenca/agent-tui --skill agent-tui -a codex

Project install goes to .agents/skills/; add -g for ~/.codex/skills/.

GitHub CLI

$ gh skill install pproenca/agent-tui agent-tui --agent codex

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/pproenca/agent-tui.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/agent-tui .agents/skills/agent-tui && rm -rf skills-src

Use ~/.agents/skills/ instead of .agents/skills for a personal install.

Codex skills documentation · loads skills from .agents/skills/

Paste into Codex

Install the "agent-tui" agent skill from https://github.com/pproenca/agent-tui/tree/master/skills/agent-tui into .agents/skills/agent-tui/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "agent-tui", then confirm the skill loads.

Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add pproenca/agent-tui --skill agent-tui -a cursor

Project install goes to .agents/skills/; add -g for ~/.cursor/skills/.

GitHub CLI

$ gh skill install pproenca/agent-tui agent-tui --agent cursor

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/pproenca/agent-tui.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/agent-tui .cursor/skills/agent-tui && rm -rf skills-src

Use ~/.cursor/skills/ instead of .cursor/skills for a personal install.

Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/

Paste into Cursor

Install the "agent-tui" agent skill from https://github.com/pproenca/agent-tui/tree/master/skills/agent-tui into .cursor/skills/agent-tui/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "agent-tui", then confirm the skill loads.

Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

gemini skills install

$ gemini skills install https://github.com/pproenca/agent-tui.git --path skills/agent-tui

--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.

skills CLI

$ npx skills add pproenca/agent-tui --skill agent-tui -a gemini-cli

Project install goes to .agents/skills/; add -g for ~/.gemini/skills/.

GitHub CLI

$ gh skill install pproenca/agent-tui agent-tui --agent gemini-cli

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/pproenca/agent-tui.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/agent-tui .gemini/skills/agent-tui && rm -rf skills-src

Use ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.

Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/

Paste into Gemini CLI

Install the "agent-tui" agent skill from https://github.com/pproenca/agent-tui/tree/master/skills/agent-tui into .gemini/skills/agent-tui/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "agent-tui", then confirm the skill loads.

Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

GitHub CLI

$ gh skill install pproenca/agent-tui agent-tui

Installs for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).

skills CLI

$ npx skills add pproenca/agent-tui --skill agent-tui -a github-copilot

Project install goes to .agents/skills/; add -g for ~/.copilot/skills/.

Manual copy

$ git clone --depth 1 https://github.com/pproenca/agent-tui.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/agent-tui .github/skills/agent-tui && rm -rf skills-src

Use ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.

GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/

Paste into GitHub Copilot

Install the "agent-tui" agent skill from https://github.com/pproenca/agent-tui/tree/master/skills/agent-tui into .github/skills/agent-tui/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "agent-tui", then confirm the skill loads.

GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add pproenca/agent-tui --skill agent-tui -a opencode

OpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.

GitHub CLI

$ gh skill install pproenca/agent-tui agent-tui --agent opencode

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/pproenca/agent-tui.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/agent-tui .opencode/skills/agent-tui && rm -rf skills-src

Use ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.

OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/

Paste into OpenCode

Install the "agent-tui" agent skill from https://github.com/pproenca/agent-tui/tree/master/skills/agent-tui into .opencode/skills/agent-tui/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "agent-tui", then confirm the skill loads.

OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

Facts

Skill name: agent-tui
GitHub stars: 118
Token cost: ~1k tokens
SKILL.md length: 428 words
Files: 15 (incl. references)
Skills in repo: 2
Repo updated: Oct 4, 2026
First seen: Oct 7, 2026
Licence: MIT

At a glance

Drives terminal UI apps from the command line for testing, demos and scripted interactions, using a run, screenshot, act, wait loop.

Works in 7 steps: Run the app with agent-tui run and… → Take a fresh snapshot with agent-tui… → Decide the next action based on the… → …
Automating a CLI or TUI workflow for regression testing
SKILL.md covers Quick start, Core workflow, Reliability rules and Legacy migration, plus 3 more sections
Calls npm, pnpm and bun

What it does

After installing through npm, pnpm, bun, an install script or cargo, a session starts with `agent-tui run`, which returns a session ID. The core loop then takes a fresh screenshot, decides the next move, acts with `press`, `type` or `scroll`, and synchronizes with `wait --assert` or `wait --stable` before repeating, ending with `agent-tui kill --yes` to clean up.

The reliability rules call for re-snapshotting after any action that could change the screen and never acting on a screen that is still changing, verifying outcomes with an assertion instead of assuming success. A legacy migration section lists older command forms, such as `agent-tui input` or `agent-tui action <selector> click`, that still parse but print a deprecation notice to stderr and are slated for removal, in favor of `type` and `press Enter`.

When your agent uses it

Automating a CLI or TUI workflow for regression testing
Extracting structured text from a running terminal application
Scripting an interaction with a terminal app for a demo

Example prompts

“Write an agent-tui script that logs into our TUI app and checks the dashboard.”
“Automate pressing through this terminal wizard and assert the final text.”
“Record a scripted demo of our CLI tool using agent-tui.”

Requirements

agent-tui installed via npm, cargo or the install script

Workflow steps

7 steps, taken from the first numbered list in SKILL.md.

Run the app with agent-tui run and capture session_id from JSON output.
Take a fresh snapshot with agent-tui screenshot or agent-tui screenshot --format json.
Decide the next action based on the latest snapshot.
Act with press, type, or scroll.
Synchronize with wait --assert or wait --stable.
Repeat from step 2 until the task finishes.
Clean up with agent-tui kill --yes.

What it can do on your machine

Read from SKILL.md and the folder at commit 8bf76c4. It shows what the files ask for, not the result of running them.

Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
Shell commands in SKILL.md call:
- npm
- pnpm
- bun
- curl
- sh
- cargo
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md. Its commands use npm, pnpm and curl, which can reach the network depending on how they are called.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Terminal UI Automation loads about 1k tokens when it runs, and up to ~5.1k if it reads all its reference files. Until then it costs about 100 tokens; SKILL.md has 428 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it: ~100
When it runs · the whole SKILL.md, loaded when a task matches: ~1k
With references · SKILL.md plus every file in references/, read only if the agent opens them: ~5.1k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from pproenca/agent-tui at commit 8bf76c4, republished under its MIT licence (© pproenca). 428 words, ~1,027 tokens.

Download SKILL.mdSave it as .claude/skills/agent-tui/SKILL.md (or your agent's skills folder). This skill also uses 14 other files; get the full folder from GitHub.

name: agent-tui
description: Automate terminal UI (TUI) apps with agent-tui for testing, inspection, demos, and scripted interactions. Use when automating CLI/TUI flows, regression testing terminal apps, verifying interactive behavior, or extracting structured text from terminal UIs. Also use when asked what agent-tui is, how it works, or to demo it. Do not use for web browsers, GUI apps, or non-terminal interfaces.

agent-tui

Quick start

Verify install: agent-tui --version
Install with npm i -g agent-tui (or pnpm add -g agent-tui, bun add -g agent-tui).
Alternate install: curl -fsSL https://raw.githubusercontent.com/pproenca/agent-tui/master/install.sh -o /tmp/agent-tui-install.sh && sh /tmp/agent-tui-install.sh or cargo install --git https://github.com/pproenca/agent-tui.git --path cli/crates/agent-tui.
If you used the install script, ensure ~/.local/bin is on your PATH.
Start a session: agent-tui run --format json <command> -- <args...>
Observe: agent-tui screenshot --format json
Act: agent-tui press Enter, agent-tui type "text", or agent-tui scroll down
Wait or verify: agent-tui wait "Expected text" --assert or agent-tui wait --stable
Cleanup: agent-tui kill --yes

Core workflow

Current automation loop: run -> screenshot -> press/type/scroll -> wait -> kill --yes.

Run the app with agent-tui run and capture session_id from JSON output.
Take a fresh snapshot with agent-tui screenshot or agent-tui screenshot --format json.
Decide the next action based on the latest snapshot.
Act with press, type, or scroll.
Synchronize with wait --assert or wait --stable.
Repeat from step 2 until the task finishes.
Clean up with agent-tui kill --yes.

Reliability rules

Re-snapshot after every action that could change the UI.
Never act on a changing screen; wait for stability first.
Verify outcomes with wait --assert instead of assuming success.
Always end automation runs with kill --yes or sessions cleanup --yes.

Legacy migration

Use current commands for new scripts. Legacy compatibility forms still parse for old scripts, but each one writes its deprecation notice to stderr, keeps JSON stdout parseable, and is covered by the next-major removal window.

agent-tui input "text" -> agent-tui type "text".
agent-tui action <selector> click -> agent-tui press Enter.
agent-tui action <selector> fill <text> -> agent-tui type "<text>".
agent-tui screenshot -e -> agent-tui screenshot.
agent-tui screenshot -a -> agent-tui screenshot.
agent-tui wait -e <ref> -> agent-tui wait "<text>".
agent-tui scroll-into-view <selector> -> agent-tui scroll <direction> [amount] or agent-tui press ...; the compatibility command does not send terminal input.

Show full SKILL.md (125 more words)Show less

Session handling

Use --session <id> for every command if more than one session exists.
If you lose the session id, run agent-tui sessions and agent-tui sessions show <id>.

Live preview (optional)

Ask whether a live preview is desired.
Start preview: agent-tui live start --open
Stop standalone preview state with agent-tui live stop; daemon-backed preview remains available until agent-tui daemon stop --yes.

Deep-dive references

Full CLI coverage and options: references/command-atlas.md
JSON output contract: references/output-contract.md
End-to-end command sequences: references/flows.md
Quick command selection: references/decision-tree.md
Session lifecycle and concurrency: references/session-lifecycle.md
Assertions and test oracles: references/assertions.md
Failure recovery playbook: references/recovery.md
Safety and confirmation prompts: references/safety.md
Clarification checklist: references/clarifications.md
Test plan template: references/test-plan.md
Demo script: references/demo.md
User prompt templates: references/prompt-templates.md
Minimal command sets by use case: references/use-cases.md
Explorer/replay automation skill: ../tui-explorer/SKILL.md

Files

SKILL.md and 14 other files (references) in skills/agent-tui of pproenca/agent-tui.

SKILL.md
agents/openai.yaml
references/assertions.md
references/clarifications.md
references/command-atlas.md
references/decision-tree.md
references/demo.md
references/flows.md
references/output-contract.md
references/prompt-templates.md
references/recovery.md
references/safety.md
references/session-lifecycle.md
references/test-plan.md
references/use-cases.md

Open the folder on GitHubat commit 8bf76c4

Compare with similar skills

Terminal UI Automation next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Terminal UI Automation compared with similar skills
Skill	Stars	Used in	Tokens	Auto-check	Licence	Repo updated
Terminal UI Automation this skillpproenca/agent-tui	118	—	~1k	Automated safety check: Pass	MIT	2 days ago
Codex Coding Pluginstyler-ai/ProjectAtlas	438	—	~1.8k	Automated safety check: Pass	MIT	today
Run Shuntpleaseai/shunt	251	—	~2.6k	Automated safety check: Pass	Apache-2.0	today
Warp UI Testing with Computer Usewarpdotdev/warp	65k	1 repos	~1k	Automated safety check: Pass	AGPL-3.0	today
TUI Change Verification for Warpwarpdotdev/warp	65k	1 repos	~5.5k	Automated safety check: Notes	AGPL-3.0	today
Codewhale Dogfood Installcodewhale-hq/Codewhale	41k	—	~1.3k	Automated safety check: Pass	MIT	today

Similar skills

Codex Coding Plugin
styler-ai/ProjectAtlas
Build, review, or fix ProjectAtlas plugin/runtime installer integration for Codex, Claude Code, and OpenCode, especially version convergence, stale ProjectAtlas cache repair, MCP config generation…
438 GitHub stars~1.8k tokensUpdated today
Testing & QAAuto-check passed
Run Shunt
pleaseai/shunt
Build, launch, and drive shunt — the Claude Code LLM gateway (a Rust/axum Anthropic-Messages proxy).
251 GitHub stars~2.6k tokensUpdated today
Testing & QAAuto-check passed
Warp UI Testing with Computer Use
warpdotdev/warp
Guides visual testing of Warp UI changes by launching the app with an API key and driving it through the computer use tool, with optional mocked state.
65k GitHub starsUsed in 1 repo~1k tokens
Testing & QAAuto-check passed
TUI Change Verification for Warp
warpdotdev/warp
Runs Warp's terminal UI for real, drives it with keystrokes and reads the rendered screen back to confirm that a change looks and behaves as intended.
65k GitHub starsUsed in 1 repo~5.5k tokens
Testing & QAAuto-check: notes
Codewhale Dogfood Install
codewhale-hq/Codewhale
Proves a Codewhale change in the real product: a stamped release build, an atomic local install, fresh-shell verification and manual QA that automated gates cannot cover.
41k GitHub stars~1.3k tokensUpdated today
DevelopmentAuto-check passed
Dpis Hyperos Smoke
Kwensiu/DPIS
Run automated DPIS HyperOS device smoke tests for package-specific dp/font emulation or replacement.
107 GitHub stars~715 tokensUpdated yesterday
MobileAuto-check passed

Questions about Terminal UI Automation

What does Terminal UI Automation do?

Drives terminal UI apps from the command line for testing, demos and scripted interactions, using a run, screenshot, act, wait loop. After installing through npm, pnpm, bun, an install script or cargo, a session starts with `agent-tui run`, which returns a session ID. The core loop then takes a fresh screenshot, decides the next move, acts with `press`, `type` or `scroll`, and synchronizes with `wait --assert` or `wait --stable` before repeating, ending with `agent-tui kill --yes` to clean up.

When should I use Terminal UI Automation?

Terminal UI Automation fits situations like: automating a CLI or TUI workflow for regression testing; extracting structured text from a running terminal application; scripting an interaction with a terminal app for a demo.

How do I install Terminal UI Automation in Claude Code?

Run `npx skills add pproenca/agent-tui --skill agent-tui -a claude-code`. Or copy the skill folder (skills/agent-tui in pproenca/agent-tui) into .claude/skills/agent-tui in your project. Claude Code loads it when a task matches its description.

How do I install Terminal UI Automation in Codex?

Run `npx skills add pproenca/agent-tui --skill agent-tui -a codex`. Or copy the skill folder (skills/agent-tui in pproenca/agent-tui) into .agents/skills/agent-tui in your project. Codex loads it when a task matches its description.

Can I use Terminal UI Automation in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add pproenca/agent-tui --skill agent-tui -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/agent-tui, .gemini/skills/agent-tui, .github/skills/agent-tui and .opencode/skills/agent-tui in your project.

What does Terminal UI Automation need to run?

Going by SKILL.md and its folder, Terminal UI Automation needs the command-line tools its instructions call (npm, pnpm, bun, curl, sh and cargo). Our summary lists: agent-tui installed via npm, cargo or the install script.

Does Terminal UI Automation access the network?

SKILL.md contains no URLs. Its commands use npm and curl, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is Terminal UI Automation safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Terminal UI Automation use?

Terminal UI Automation is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Terminal UI Automation use?

About 1k tokens (SKILL.md is roughly 4.1k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 4.1k tokens, read only when the agent opens those files.

What are the alternatives to Terminal UI Automation?

Skills that share tags, products or a category with Terminal UI Automation: Codex Coding Plugin (styler-ai/ProjectAtlas, 438 stars), Run Shunt (pleaseai/shunt, 251 stars), Warp UI Testing with Computer Use (warpdotdev/warp, 65k stars) and TUI Change Verification for Warp (warpdotdev/warp, 65k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Terminal UI Automation?

pproenca (a GitHub user) maintains it in pproenca/agent-tui, which has 118 GitHub stars. The repository holds 2 skills in this directory. The repository was last updated on October 4, 2026.

Source: pproenca/agent-tui on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.

Terminal UI Automation

Install Terminal UI Automation

Facts

At a glance

What it does

When your agent uses it

Example prompts

Requirements

Workflow steps

What it can do on your machine

Tool permissions

Runs code

Network

Credentials

Context cost

Safety

SKILL.md

agent-tui

Quick start

Core workflow

Reliability rules

Legacy migration

Session handling

Live preview (optional)

Deep-dive references

Files

Compare with similar skills

Similar skills

Codex Coding Plugin

Run Shunt

Warp UI Testing with Computer Use

TUI Change Verification for Warp

Codewhale Dogfood Install

Dpis Hyperos Smoke

More from pproenca/agent-tui

TUI Explorer

Questions about Terminal UI Automation

Install Terminal UI Automation

Facts

At a glance

What it does

When your agent uses it

Example prompts

Requirements

Workflow steps

What it can do on your machine

Tool permissions

Runs code

Network

Credentials

Context cost

Safety

SKILL.md

agent-tui

Quick start

Core workflow

Reliability rules

Legacy migration

Session handling

Live preview (optional)

Deep-dive references

Files

Compare with similar skills

Similar skills

Codex Coding Plugin

Run Shunt

Warp UI Testing with Computer Use

TUI Change Verification for Warp

Codewhale Dogfood Install

Dpis Hyperos Smoke

More from pproenca/agent-tui

TUI Explorer

Related

Questions about Terminal UI Automation