polymath-void/ai-agents-skills-workspace/generative-tui
Claude Code and agent skill by polymath-void/ai-agents-skills-workspace
- community
Checking that the SKILL.md file is still in the repository.
Guidelines and reasoning procedures for designing native interactive Python Terminal User Interfaces (TUIs) using the Textual framework, strictly avoiding HTML/Web widgets.
Install
npx vskill@latest install polymath-void/ai-agents-skills-workspace/generative-tuiSKILL.md
The same SKILL.md was published earlier as polymath-void/ai-agents-skills-workspace/generative-tui.
Generative Native TUI Dashboard Design
When the user asks you to build a "TUI", "Terminal Dashboard", or explicitly invokes the /generative_tui or generative-tui skill, you MUST build a native Python terminal interface using the textual framework.
CRITICAL RULE: DO NOT build HTML, CSS, or JS web widgets. DO NOT use the /generative_ui Web constraints. You are building a native terminal application that runs via python3 app.py inside the user's Termux shell.
1. Architectural Reasoning
Before writing the code, structure your reasoning into the following components:
- State Management: How will data be loaded and saved? (e.g., reading/writing local JSON files, querying SQLite).
- Layout Topology:
- Top: Headers (Titles, Breadcrumbs)
- Body: Scrollable Containers (Lists, Tables, Grids)
- Bottom: Footers (Hotkeys and Action binds)
- Reactive UI: Define which variables should trigger UI updates when they change by using Textual's
@reactivedecorators or.set_interval()polling.
2. Textual Framework Constraints
- Library: Always import from
textual.app,textual.widgets, andtextual.containers. - CSS: Define styling inside the
CSSclass variable. Avoid using undefined raw variables like$surfacedirectly unless you know the theme injects them; instead, rely on the default Textual terminal theme or standard color names (e.g.,green,red,blue). - Interactive Lists: DO NOT clutter the screen with giant buttons for list items. Always use
DataTablefor displaying rows of data. It is lightweight, professional, and users can navigate via arrow keys and pressEnter(triggeringon_data_table_row_selected) to perform actions on a row. - Subprocesses & Auth: If you need to run an interactive terminal script or an OAuth login flow (which prints a URL or requires standard input), use the
with self.suspend():context manager to temporarily drop out of the TUI, runsubprocess.run(), and then seamlessly resume the TUI. - Hotkeys: Always define
BINDINGS = [("q", "quit", "Quit")]in the App class so the user can gracefully exit.
3. Implementation Example Boilerplate
4. Execution
Always write the TUI code directly to a .py file in the user's project directory (e.g., ~/Projects/my-project/app_tui.py) and instruct the user to run it via python3 app_tui.py.
Security
- Security scanPassed, 90 of 100Pattern checks on the skill's files.
- Model reviewPassed
Quality evaluation
- Task evaluationNot runNo evaluation yet. Run one in Skill Studio.
Source
- SKILL.md in the repositoryCheckinguser-skills/generative-tui/SKILL.md
Popularity
- 7-day trend score
- 0
Not refreshed yet.
Works with
Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.
- Claude Code
- Cursor
- GitHub Copilot
- Windsurf
- Codex
- Gemini CLI
- Cline
- Amp
- Roo Code
- Goose
- Continue
- Kilo Code
- Junie
- Trae
- OpenHands
- Qwen Code
- AI Agent
- Tabnine Chat
- Sourcegraph Cody
- Amazon Q
- Firebase Genkit
- Sweep
- Devin
- Phind
- Mentat
- Claude Desktop
- Aider
- GPT Pilot
- Plandex
- bolt.new
- v0
- Replit Agent
- Anse
- TypingMind
- BetterChatGPT
- LibreChat
- Warp AI
- Pieces
- Fig AI
Embed badge
[](https://verified-skill.com/skills/polymath-void/ai-agents-skills-workspace/generative-tui)