Agent skill

Tui Use

Operate interactive terminal programs (REPLs, installers, TUI apps) using PTY automation.

MITAuto-check passed

Install Tui Use

skills CLI

$ npx skills add onesuper/tui-use --skill tui-use -a claude-code

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

GitHub CLI

$ gh skill install onesuper/tui-use tui-use --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/onesuper/tui-use.git skills-src && mkdir -p .claude/skills && cp -r skills-src/plugins/tui-use/skills/tui-use .claude/skills/tui-use && 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 "tui-use" agent skill from https://github.com/onesuper/tui-use/tree/main/plugins/tui-use/skills/tui-use into .claude/skills/tui-use/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "tui-use", 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/onesuper/tui-use/tree/main/plugins/tui-use/skills/tui-use

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 onesuper/tui-use --skill tui-use -a codex

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

GitHub CLI

$ gh skill install onesuper/tui-use tui-use --agent codex

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

Manual copy

$ git clone --depth 1 https://github.com/onesuper/tui-use.git skills-src && mkdir -p .agents/skills && cp -r skills-src/plugins/tui-use/skills/tui-use .agents/skills/tui-use && 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 "tui-use" agent skill from https://github.com/onesuper/tui-use/tree/main/plugins/tui-use/skills/tui-use into .agents/skills/tui-use/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "tui-use", 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 onesuper/tui-use --skill tui-use -a cursor

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

GitHub CLI

$ gh skill install onesuper/tui-use tui-use --agent cursor

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

Manual copy

$ git clone --depth 1 https://github.com/onesuper/tui-use.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/plugins/tui-use/skills/tui-use .cursor/skills/tui-use && 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 "tui-use" agent skill from https://github.com/onesuper/tui-use/tree/main/plugins/tui-use/skills/tui-use into .cursor/skills/tui-use/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "tui-use", 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/onesuper/tui-use.git --path plugins/tui-use/skills/tui-use

--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 onesuper/tui-use --skill tui-use -a gemini-cli

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

GitHub CLI

$ gh skill install onesuper/tui-use tui-use --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/onesuper/tui-use.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/plugins/tui-use/skills/tui-use .gemini/skills/tui-use && 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 "tui-use" agent skill from https://github.com/onesuper/tui-use/tree/main/plugins/tui-use/skills/tui-use into .gemini/skills/tui-use/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "tui-use", 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 onesuper/tui-use tui-use

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 onesuper/tui-use --skill tui-use -a github-copilot

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

Manual copy

$ git clone --depth 1 https://github.com/onesuper/tui-use.git skills-src && mkdir -p .github/skills && cp -r skills-src/plugins/tui-use/skills/tui-use .github/skills/tui-use && 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 "tui-use" agent skill from https://github.com/onesuper/tui-use/tree/main/plugins/tui-use/skills/tui-use into .github/skills/tui-use/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "tui-use", 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 onesuper/tui-use --skill tui-use -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 onesuper/tui-use tui-use --agent opencode

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

Manual copy

$ git clone --depth 1 https://github.com/onesuper/tui-use.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/plugins/tui-use/skills/tui-use .opencode/skills/tui-use && 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 "tui-use" agent skill from https://github.com/onesuper/tui-use/tree/main/plugins/tui-use/skills/tui-use into .opencode/skills/tui-use/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "tui-use", 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: tui-use
GitHub stars: 266
Token cost: ~1k tokens
SKILL.md length: 114 words
Files: 1
Skills in repo: 5
Repo updated: Apr 11, 2026
First seen: Oct 7, 2026
Licence: MIT

At a glance

Operate interactive terminal programs (REPLs, installers, TUI apps) using PTY automation.

Works in 4 steps: use first — always set current session… → wait before type/press — confirms… → check status — if "exited", don't send… → …
You need to interact with programs that require keyboard input
SKILL.md covers Core Workflow, Commands, Rules and Example, plus 1 more section
Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Tui Use is an agent skill from onesuper/tui-use. Operate interactive terminal programs (REPLs, installers, TUI apps) using PTY automation. Use when you need to interact with programs that require keyboard input.

Its SKILL.md is about 1k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

The repository describes itself as: tui-use lets agents interact with programs that expect a human at the keyboard — REPLs, debuggers, TUI apps, and anything else bash can't reach. The licence is MIT.

When your agent uses it

You need to interact with programs that require keyboard input

Example prompts

“/tui-use”

Requirements

Python 3

Workflow steps

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

use first — always set current session before other commands
wait before type/press — confirms program is ready
check status — if "exited", don't send more input
kill when done — clean up sessions

What it can do on your machine

Read from SKILL.md and the folder at commit 0170481. 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
No scripts in the folder and no shell commands in SKILL.md (its code samples are bash and json).
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
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

Tui Use loads about 1k tokens when it runs. Until then it costs about 43 tokens; SKILL.md has 114 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it: ~43
When it runs · the whole SKILL.md, loaded when a task matches: ~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 onesuper/tui-use at commit 0170481, republished under its MIT licence (© onesuper). 114 words, ~1,049 tokens.

Download SKILL.mdSave it as .claude/skills/tui-use/SKILL.md (or your agent's skills folder).

name: tui-use
description: Operate interactive terminal programs (REPLs, installers, TUI apps) using PTY automation. Use when you need to interact with programs that require keyboard input.

tui-use — TUI Automation for AI Agents

Use tui-use to operate interactive terminal programs that require keyboard input. Works with prompt-based CLIs, REPLs, interactive installers, and TUI apps (htop, vim, fzf, etc.).

Core Workflow

start → use → wait → type/press → wait → ... → kill

Commands

Core Commands

tui-use start <cmd>                            # Start a program
tui-use start --cwd <dir> <cmd>                # Start in specific directory
tui-use start --cwd <dir> "<cmd> -flags"       # Quote full command to pass flags (e.g. git rebase -i)
tui-use start --label <name> <cmd>             # Start with label
tui-use start --cols <n> --rows <n> <cmd>      # Custom terminal size (default: 120x30)
tui-use use <session_id>                       # Switch to a session
tui-use type <text>                            # Type text
tui-use type "<text>\n"                        # Type with Enter
tui-use type "<text>\t"                        # Type with Tab
tui-use paste "<text>\n<text>\n"               # Multi-line paste (each line + Enter)
tui-use press <key>                            # Press a key
tui-use snapshot                               # Get current screen
tui-use snapshot --format json                 # JSON output
tui-use scrollup <n>                           # Scroll up to older content
tui-use scrolldown <n>                         # Scroll down to newer content
tui-use find <pattern>                         # Search in screen (regex)
tui-use wait                                   # Wait for screen change
tui-use wait <ms>                              # Custom timeout (default: 3000ms)
tui-use wait --text <pattern>                  # Wait until screen contains pattern
tui-use wait --format json                     # JSON output
tui-use list                                   # List all sessions
tui-use info                                   # Show session details
tui-use rename <label>                         # Rename session
tui-use kill                                   # Kill current session

Daemon Commands

tui-use daemon status                          # Check if daemon is running
tui-use daemon stop                            # Stop the daemon
tui-use daemon restart                         # Restart the daemon

Waiting

wait is the primary way to observe the terminal state. It blocks until the screen changes or a timeout occurs.

Always call wait before type/press — ensures program is ready.

Default output (pretty format):

─── session-id ────────────────────────────────────────────
What is your name?
> Alice
─── running | cursor(2,8) | fullscreen:false | title:"" ────
highlights(0):

JSON output (--format json):

json

{
  "session_id": "abc12345",
  "screen": "What is your name?\n> Alice",
  "cursor": { "x": 2, "y": 1 },
  "changed": true,
  "status": "running",
  "exit_code": null,
  "title": "",
  "is_fullscreen": false,
  "cols": 120,
  "rows": 30,
  "highlights": []
}

Rules

use first — always set current session before other commands
wait before type/press — confirms program is ready
check status — if "exited", don't send more input
kill when done — clean up sessions

Example

bash

# Start (automatically becomes current session)
tui-use start python3 examples/ask.py

# Interact
tui-use wait                    # wait for prompt
tui-use type "Alice"
tui-use press enter
tui-use wait                    # wait for output
tui-use kill                    # cleanup

Multiple Sessions

bash

# Start two sessions
SID1=$(tui-use start htop --label monitor)
SID2=$(tui-use start python3)

# Work with first
tui-use use $SID1
tui-use wait --text "PID"
tui-use press q
tui-use kill

# Work with second
tui-use use $SID2
tui-use wait --text ">>>"
tui-use type "print(1+1)"
tui-use press enter
tui-use wait --text ">>>"
tui-use type "exit()"
tui-use press enter
tui-use kill

Files

Just SKILL.md in plugins/tui-use/skills/tui-use of onesuper/tui-use.

Open the folder on GitHubat commit 0170481

Compare with similar skills

Tui Use 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.

Tui Use compared with similar skills
Skill	Stars	Used in	Tokens	Auto-check	Licence	Repo updated
Tui Use this skillonesuper/tui-use	266	—	~1k	Automated safety check: Pass	MIT	6 mo ago
Interactive CLI Testing With tui-testslopus/happy	24k	—	~603	Automated safety check: Pass	MIT	yesterday
Remember Interactive Programminggithub/awesome-copilot	40k	1 repos	~221	Automated safety check: Pass	MIT	today
Nanoclaw Replaffaan-m/ECC	275k	4 repos	~286	Automated safety check: Pass	MIT	3 days ago
Prototype Openclaw Tuiopenclaw/openclaw	392k	—	~1.3k	Automated safety check: Pass	MIT	today
Golem Interactive Repl Rustgolemcloud/golem	1.5k	—	~638	Automated safety check: Pass	Custom licence	today

Similar skills

Interactive CLI Testing With tui-test
slopus/happy
Tests interactive CLI and TUI programs with Microsoft's tui-test, driving prompts, arrow keys and screen output in a real pseudo-terminal.
24k GitHub stars~603 tokensUpdated yesterday
Testing & QAAuto-check passed
Remember Interactive Programming
github/awesome-copilot
Official
A micro-prompt that reminds the agent that it is an interactive programmer.
40k GitHub starsUsed in 1 repo~221 tokens
Auto-check passed
Nanoclaw Repl
affaan-m/ECC
Operate and extend NanoClaw, ECC's zero-dependency session-aware REPL, with persistent markdown-backed sessions and slash commands for model switching, skill loading, session branching…
275k GitHub starsUsed in 4 repos~286 tokens
Agent WorkflowsAuto-check passed
Prototype Openclaw Tui
openclaw/openclaw
Build throwaway, fixture-driven OpenClaw Clack or Pi TUI prototypes and compare multiple interactive variants side by side in tmux without running the full application or touching live state.
392k GitHub stars~1.3k tokensUpdated today
DevelopmentAuto-check passed
Golem Interactive Repl Rust
golemcloud/golem
Using the Golem REPL for interactive testing and scripting of agents.
1.5k GitHub stars~638 tokensUpdated today
Auto-check passed
Golem Interactive Repl TS
golemcloud/golem
Using the Golem REPL for interactive testing and scripting of agents.
1.5k GitHub stars~667 tokensUpdated today
Auto-check passed

Questions about Tui Use

What does Tui Use do?

Operate interactive terminal programs (REPLs, installers, TUI apps) using PTY automation. Tui Use is an agent skill from onesuper/tui-use. Operate interactive terminal programs (REPLs, installers, TUI apps) using PTY automation.

When should I use Tui Use?

Tui Use fits situations like: you need to interact with programs that require keyboard input.

How do I install Tui Use in Claude Code?

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

How do I install Tui Use in Codex?

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

Can I use Tui Use 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 onesuper/tui-use --skill tui-use -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/tui-use, .gemini/skills/tui-use, .github/skills/tui-use and .opencode/skills/tui-use in your project.

What does Tui Use need to run?

SKILL.md names no scripts, command-line tools or credentials: Tui Use is instructions for the agent only. Our summary lists: Python 3.

Does Tui Use access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Tui Use 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 Tui Use use?

Tui Use 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 Tui Use use?

About 1k tokens (SKILL.md is roughly 4.2k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Tui Use?

Skills that share tags, products or a category with Tui Use: Interactive CLI Testing With tui-test (slopus/happy, 24k stars), Remember Interactive Programming (github/awesome-copilot, 40k stars), Nanoclaw Repl (affaan-m/ECC, 275k stars) and Prototype Openclaw Tui (openclaw/openclaw, 392k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Tui Use?

onesuper (a GitHub user) maintains it in onesuper/tui-use, which has 266 GitHub stars. The repository holds 5 skills in this directory. The repository was last updated on April 11, 2026.

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

Install Tui Use

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

tui-use — TUI Automation for AI Agents

Core Workflow

Commands

Core Commands

Daemon Commands

Waiting

Rules

Example

Multiple Sessions

Files

Compare with similar skills

Similar skills

More from onesuper/tui-use

Questions about Tui Use