tui-validate

# TUI Validate

## Overview

This skill validates Terminal User Interface (TUI) applications by capturing their output and using LLM-as-judge for semantic validation. It leverages [freeze](https://github.com/charmbracelet/freeze) from Charmbracelet for high-fidelity terminal screenshots and provides structured validation criteria.

**Philosophy**: Rather than brittle string matching, this skill uses semantic understanding to validate that TUI output "looks right" - checking layout, content presence, and visual hierarchy without breaking on minor formatting changes.

## When to Use

- Validating TUI rendering after changes
- Checking that UI components display correctly
- Visual regression testing for terminal applications
- Verifying TUI state after specific interactions
- Creating documentation screenshots with validation

## Prerequisites

**Required:**
- `freeze` CLI tool installed (`brew install charmbracelet/tap/freeze`)
- `tmux` for interactive TUI capture (optional, for live applications)

**Verification:**
```bash
# Check freeze is installed
freeze --version

# Check tmux is installed (for interactive capture)
tmux -V
```

## Parameters

- **target** (required): What to validate. One of:
  - `file:<path>` - ANSI output file to validate
  - `command:<cmd>` - Command to execute and capture
  - `tmux:<session>` - Live tmux session to capture
  - `buffer:<text>` - Raw text/ANSI to validate

- **criteria** (required): Validation criteria. Can be:
  - A predefined criteria name (see Built-in Criteria)
  - A custom criteria string describing what to check

- **output_format** (optional, default: "svg"): Screenshot format
  - `svg` - Vector format, best for documentation
  - `png` - Raster format, best for visual diff
  - `text` - Text-only extraction, fastest

- **save_screenshot** (optional, default: false): Whether to save the screenshot
  - If true, saves to `{target_name}.{format}` in current directory

- **judge_mode** (optional, default: "semantic"): Validation approach
  - `semantic` - LLM judges based on meaning and layout
  - `strict` - Also checks exact content presence
  - `visual` - Requires PNG, checks visual appearance

## Built-in Criteria

### `ralph-header`
Validates Ralph TUI header component:
- Iteration counter in `[iter N]` or `[iter N/M]` format
- Elapsed time in `MM:SS` format
- Hat indicator with emoji and name
- Mode indicator (`▶ auto` or `⏸ paused`)
- Optional scroll mode indicator `[SCROLL]`
- Optional idle countdown `idle: Ns`

### `ralph-footer`
Validates Ralph TUI footer component:
- Activity indicator (`◉ active`, `◯ idle`, or `■ done`)
- Last event topic display
- Search mode display when active

### `ralph-full`
Validates complete Ralph TUI layout:
- Header section at top (3 lines)
- Terminal content area (variable height)
- Footer section at bottom (3 lines)
- Proper visual hierarchy and borders

### `tui-basic`
Generic TUI validation:
- Has visible content (not blank)
- No rendering artifacts or broken characters
- Proper terminal dimensions

## Execution Flow

### 1. Capture Phase

Capture TUI output based on target type:

**For file targets:**
```bash
freeze {file_path} -o /tmp/tui-capture.{format}
```

**For command targets:**
```bash
freeze --execute "{command}" -o /tmp/tui-capture.{format}
```

**For tmux targets:**
```bash
tmux capture-pane -pet {session} | freeze -o /tmp/tui-capture.{format}
```

**For buffer targets:**
```bash
echo "{buffer}" | freeze -o /tmp/tui-capture.{format}
```

**Constraints:**
- You MUST verify freeze is installed before attempting capture
- You MUST handle capture failures gracefully and report the error
- You MUST use appropriate freeze flags for the output format
- You SHOULD use `--theme base16` for consistent rendering
- You SHOULD set reasonable dimensions with `--width` and `--height`

### 2. Extraction Phase

Extract content for LLM analysis:

**For text/semantic validation:**
- If format is `text`, use the captured text directly
- If format is `svg` or `png`, also capture text version for content analysis

**For visual validation:**
- Requires PNG format
- Will analyze the image directly using vision capabilities

**Constraints:**
- You MUST extract both visual and text representations when judge_mode is `visual`
- You MUST preserve ANSI escape sequences for color validation when relevant

### 3. Validation Phase

Apply LLM-as-judge with the appropriate criteria:

**Semantic Validation Prompt Template:**
```
Analyze this terminal UI output and determine if it meets the following criteria:

CRITERIA:
{criteria_description}

TERMINAL OUTPUT:
{captured_text}

Evaluate each criterion and provide:
1. PASS or FAIL for each requirement
2. Brief explanation for any failures
3. Overall verdict: PASS or FAIL

Be lenient on exact formatting but strict on:
- Required content presence
- Logical layout and hierarchy
- No rendering errors or artifacts
```

**Visual Validation Prompt Template (with image):**
```
Examine this terminal screenshot and validate:

CRITERIA:
{criteria_description}

Check for:
1. Visual hierarchy and layout
2. Color coding correctness
3. No rendering artifacts or broken characters
4. Proper alignment and spacing

Verdict: PASS or FAIL with explanation
```

**Constraints:**
- You MUST return a clear PASS or FAIL verdict
- You MUST provide specific feedback on failures
- You MUST be lenient on whitespace/formatting differences
- You MUST be strict on content presence and semantic correctness
- You SHOULD note any warnings even on PASS results

### 4. Reporting Phase

Report validation results:

**On PASS:**
```
✅ TUI Validation PASSED

Criteria: {criteria_name}
Target: {target}
Mode: {judge_mode}

All requirements satisfied.
{optional_notes}
```

**On FAIL:**
```
❌ TUI Validation FAILED

Criteria: {criteria_name}
Target: {target}
Mode: {judge_mode}

Issues found:
- {issue_1}
- {issue_2}

Screenshot saved: {path_if_saved}
```

**Constraints:**
- You MUST always provide a clear verdict
- You MUST list