wicked-garden 12.27.0

package/skills/product/accessibility/refs/wcag-checklist.md

@@ -0,0 +1,262 @@
+---
+phase_relevance: ["clarify", "design", "review"]
+archetype_relevance: ["*"]
+---
+# WCAG 2.1 Level AA Complete Checklist
+
+Comprehensive checklist for WCAG 2.1 Level AA compliance.
+
+## Perceivable
+
+### 1.1 Text Alternatives
+
+**1.1.1 Non-text Content (Level A)**
+- [ ] All images have appropriate `alt` attributes
+- [ ] Decorative images use `alt=""`
+- [ ] Complex images have detailed descriptions
+- [ ] Form controls have associated labels
+- [ ] CAPTCHA has text alternative
+
+### 1.2 Time-based Media
+
+**1.2.1 Audio-only and Video-only (Level A)**
+- [ ] Audio-only has transcript
+- [ ] Video-only has audio track or text description
+
+**1.2.2 Captions (Level A)**
+- [ ] Pre-recorded video has captions
+
+**1.2.3 Audio Description or Media Alternative (Level A)**
+- [ ] Pre-recorded video has audio description or transcript
+
+**1.2.4 Captions (Live) (Level AA)**
+- [ ] Live video has captions
+
+**1.2.5 Audio Description (Level AA)**
+- [ ] Pre-recorded video has audio description
+
+### 1.3 Adaptable
+
+**1.3.1 Info and Relationships (Level A)**
+- [ ] Semantic HTML used (`<header>`, `<nav>`, `<main>`, etc.)
+- [ ] Heading hierarchy correct (h1 → h2 → h3, no skips)
+- [ ] Lists use `<ul>`, `<ol>`, `<dl>`
+- [ ] Tables use `<th>` for headers
+- [ ] Form labels associated with inputs
+
+**1.3.2 Meaningful Sequence (Level A)**
+- [ ] Reading order matches visual order
+- [ ] Tab order is logical
+
+**1.3.3 Sensory Characteristics (Level A)**
+- [ ] Instructions don't rely solely on shape, size, location, or sound
+- [ ] "Click the round button" → "Click the Submit button"
+
+**1.3.4 Orientation (Level AA)**
+- [ ] Content not restricted to single orientation (portrait/landscape)
+- [ ] Unless specific orientation essential
+
+**1.3.5 Identify Input Purpose (Level AA)**
+- [ ] Autocomplete attributes used where appropriate
+- [ ] `autocomplete="email"`, `autocomplete="name"`, etc.
+
+### 1.4 Distinguishable
+
+**1.4.1 Use of Color (Level A)**
+- [ ] Color not only means of conveying information
+- [ ] Links distinguishable from text (underline, bold, etc.)
+- [ ] Error states have icon + color
+
+**1.4.2 Audio Control (Level A)**
+- [ ] Auto-playing audio can be paused/stopped/controlled
+
+**1.4.3 Contrast (Minimum) (Level AA)**
+- [ ] Normal text: 4.5:1 contrast ratio
+- [ ] Large text (18pt+ or 14pt+ bold): 3:1 contrast ratio
+- [ ] UI components: 3:1 contrast ratio
+
+**1.4.4 Resize Text (Level AA)**
+- [ ] Text can be resized to 200% without loss of functionality
+- [ ] No horizontal scrolling at 200% zoom
+
+**1.4.5 Images of Text (Level AA)**
+- [ ] Actual text used instead of images of text
+- [ ] Exceptions: logos, essential presentation
+
+**1.4.10 Reflow (Level AA)**
+- [ ] Content reflows at 320px width
+- [ ] No two-dimensional scrolling
+- [ ] Exceptions: complex data tables, maps
+
+**1.4.11 Non-text Contrast (Level AA)**
+- [ ] UI components: 3:1 contrast against adjacent colors
+- [ ] Focus indicators: 3:1 contrast
+- [ ] Graphical objects: 3:1 contrast
+
+**1.4.12 Text Spacing (Level AA)**
+- [ ] No loss of content when:
+  - Line height 1.5x font size
+  - Paragraph spacing 2x font size
+  - Letter spacing 0.12x font size
+  - Word spacing 0.16x font size
+
+**1.4.13 Content on Hover or Focus (Level AA)**
+- [ ] Hover/focus content dismissible (Escape)
+- [ ] Hover/focus content hoverable (can move pointer to it)
+- [ ] Hover/focus content persistent (doesn't disappear)
+
+## Operable
+
+### 2.1 Keyboard Accessible
+
+**2.1.1 Keyboard (Level A)**
+- [ ] All functionality available via keyboard
+- [ ] No keyboard-only exceptions
+
+**2.1.2 No Keyboard Trap (Level A)**
+- [ ] Focus can move away from all components
+- [ ] Standard navigation (Tab, arrow keys, Escape)
+
+**2.1.4 Character Key Shortcuts (Level A)**
+- [ ] Single key shortcuts can be turned off, remapped, or only active on focus
+
+### 2.2 Enough Time
+
+**2.2.1 Timing Adjustable (Level A)**
+- [ ] Time limits can be turned off, adjusted, or extended
+- [ ] Warning before timeout with option to extend
+
+**2.2.2 Pause, Stop, Hide (Level A)**
+- [ ] Moving, blinking, scrolling content can be paused
+- [ ] Auto-updating content can be paused/hidden
+
+### 2.3 Seizures and Physical Reactions
+
+**2.3.1 Three Flashes or Below Threshold (Level A)**
+- [ ] No content flashes more than 3 times per second
+- [ ] Or below flash threshold
+
+### 2.4 Navigable
+
+**2.4.1 Bypass Blocks (Level A)**
+- [ ] Skip to main content link
+- [ ] Landmark regions defined
+- [ ] Headings structure content
+
+**2.4.2 Page Titled (Level A)**
+- [ ] Every page has descriptive `<title>`
+
+**2.4.3 Focus Order (Level A)**
+- [ ] Focus order matches visual order
+- [ ] Logical tab sequence
+
+**2.4.4 Link Purpose (Level A)**
+- [ ] Link text describes destination
+- [ ] Avoid "click here", "read more" without context
+
+**2.4.5 Multiple Ways (Level AA)**
+- [ ] Multiple ways to find pages (search, sitemap, nav, etc.)
+- [ ] Exception: process steps
+
+**2.4.6 Headings and Labels (Level AA)**
+- [ ] Headings describe topic/purpose
+- [ ] Labels describe purpose
+
+**2.4.7 Focus Visible (Level AA)**
+- [ ] Focus indicator always visible
+- [ ] Clear visual indication of focused element
+
+### 2.5 Input Modalities
+
+**2.5.1 Pointer Gestures (Level A)**
+- [ ] Multi-point or path-based gestures have single-pointer alternative
+- [ ] Exception: essential gestures (e.g., drawing)
+
+**2.5.2 Pointer Cancellation (Level A)**
+- [ ] Click actions on up event (not down)
+- [ ] Or can be aborted/undone
+
+**2.5.3 Label in Name (Level A)**
+- [ ] Accessible name contains visible label text
+- [ ] `aria-label` should include visible text
+
+**2.5.4 Motion Actuation (Level A)**
+- [ ] Motion-triggered actions have UI alternative
+- [ ] Can disable motion triggering
+
+## Understandable
+
+### 3.1 Readable
+
+**3.1.1 Language of Page (Level A)**
+- [ ] `<html lang="en">` attribute set
+
+**3.1.2 Language of Parts (Level AA)**
+- [ ] Language changes marked with `lang` attribute
+- [ ] `<span lang="es">Hola</span>`
+
+### 3.2 Predictable
+
+**3.2.1 On Focus (Level A)**
+- [ ] Focus doesn't trigger unexpected context changes
+- [ ] No automatic form submission on focus
+
+**3.2.2 On Input (Level A)**
+- [ ] Input doesn't trigger unexpected context changes
+- [ ] Changes happen on button click, not automatic
+
+**3.2.3 Consistent Navigation (Level AA)**
+- [ ] Navigation menus in consistent order across pages
+
+**3.2.4 Consistent Identification (Level AA)**
+- [ ] Same functionality labeled consistently
+- [ ] Search icon always means search
+
+### 3.3 Input Assistance
+
+**3.3.1 Error Identification (Level A)**
+- [ ] Errors identified in text
+- [ ] Location of error indicated
+- [ ] Error description provided
+
+**3.3.2 Labels or Instructions (Level A)**
+- [ ] Form fields have labels
+- [ ] Instructions provided where needed
+- [ ] Required fields indicated
+
+**3.3.3 Error Suggestion (Level AA)**
+- [ ] Error messages suggest corrections
+- [ ] "Invalid email" → "Email must include @"
+
+**3.3.4 Error Prevention (Legal, Financial, Data) (Level AA)**
+- [ ] Reversible or reviewable
+- [ ] Data checked and user can correct
+- [ ] Confirmation page for important actions
+
+## Robust
+
+### 4.1 Compatible
+
+**4.1.1 Parsing (Level A)**
+- [ ] No duplicate IDs
+- [ ] Proper nesting of elements
+- [ ] Complete start/end tags
+
+**4.1.2 Name, Role, Value (Level A)**
+- [ ] All UI components have accessible name
+- [ ] Role communicated to assistive tech
+- [ ] State/properties/values available
+- [ ] Proper ARIA implementation
+
+**4.1.3 Status Messages (Level AA)**
+- [ ] Status messages announced without focus change
+- [ ] Use `role="status"`, `role="alert"`, `aria-live`
+
+## Testing Tools
+
+- **axe DevTools**: Browser extension
+- **WAVE**: WebAIM's browser extension
+- **Lighthouse**: Chrome DevTools
+- **NVDA**: Free screen reader (Windows)
+- **VoiceOver**: Built-in screen reader (Mac)
+- **Contrast checker**: WebAIM or browser tools

package/skills/product/analyze/SKILL.md

@@ -0,0 +1,164 @@
+---
+name: analyze
+description: |
+  Sentiment analysis, theme extraction, and trend detection from customer feedback.
+
+  Use when: analyzing customer feedback for sentiment, extracting themes from
+  support or survey data, or detecting trends in voice-of-customer signal.
+phase_relevance: ["clarify", "design", "review"]
+archetype_relevance: ["*"]
+---
+
+# Analyze Skill
+
+Extract themes, sentiment, and trends from aggregated customer feedback.
+
+## When to Use
+
+- After running `/wicked-garden:product:listen`
+- User asks "what are customers saying about X"
+- Need to understand sentiment trends
+- Preparing customer insights for product decisions
+
+## Usage
+
+```bash
+# Analyze all recent feedback
+/wicked-garden:product:analyze
+
+# Analyze specific theme
+/wicked-garden:product:analyze --theme "mobile experience"
+
+# Analyze sentiment only
+/wicked-garden:product:analyze --sentiment negative
+
+# Trend analysis
+/wicked-garden:product:analyze --trend "last-quarter"
+
+# Segment analysis
+/wicked-garden:product:analyze --segment enterprise
+```
+
+## Analysis Types
+
+### 1. Sentiment Analysis
+- Classify: positive/negative/neutral/mixed
+- Score intensity: strong/moderate/mild
+- Indicators: See [refs/sentiment-patterns.md](refs/sentiment-patterns.md)
+
+### 2. Theme Extraction
+- Cluster by keywords and co-occurrence
+- Categories: Product, Experience, Business
+- See [refs/algorithms.md](refs/algorithms.md) for clustering logic
+
+### 3. Trend Detection
+- Compare time periods (week, month, quarter)
+- Categories: Emerging, Growing, Stable, Declining, Resolved
+- Threshold: >50% = Growing, >30% decline = Declining
+
+### 4. Priority Scoring
+```
+Priority = (Frequency × Severity × Urgency) / Total_Feedback
+```
+See [refs/algorithms.md](refs/algorithms.md) for detailed scoring.
+
+## Analysis Process
+
+1. **Load Feedback Data**:
+   ```bash
+   LOCAL_ROOT=$(sh "${CLAUDE_PLUGIN_ROOT}/scripts/_python.sh" "${CLAUDE_PLUGIN_ROOT}/scripts/resolve_path.py" wicked-garden:product)
+   ```
+   Then use the **Glob** tool to find feedback files:
+   ```
+   Glob(pattern="**/*.md", path="${LOCAL_ROOT}/voice/feedback/")
+   ```
+   Read individual files with the **Read** tool to load recent feedback.
+
+2. **Extract Themes**:
+   - Keyword frequency analysis
+   - Tag co-occurrence
+   - Natural language clustering
+
+3. **Score Sentiment**:
+   - Classify each item (positive/negative/neutral/mixed)
+   - Score intensity (strong/moderate/mild)
+   - Calculate net sentiment
+
+4. **Detect Trends**:
+   - Group by time period (week, month, quarter)
+   - Compare frequencies
+   - Identify direction (up, down, stable)
+
+5. **Segment Analysis**:
+   - Group by customer segment (if available)
+   - Compare sentiment across segments
+   - Identify segment-specific themes
+
+## Output Format
+
+```markdown
+## Analysis: {Topic or Timeframe}
+
+### Sentiment Overview
+- Net Sentiment: {+/-N} ({X}% positive, {Y}% negative)
+- Strong Emotions: {count} highly positive, {count} highly negative
+- Trend: {IMPROVING/DECLINING/STABLE} compared to previous period
+
+### Top Themes (by priority)
+1. **{Theme}** - Priority: {score}
+   - Frequency: {count} mentions ({%} of total)
+   - Sentiment: {positive/negative/mixed} ({intensity})
+   - Trend: {GROWING/STABLE/DECLINING} ({+/-X}% vs. baseline)
+   - Severity: {CRITICAL/HIGH/MEDIUM/LOW}
+   - Key quote: "{representative example}"
+
+{Top 5 themes}
+
+### Emerging Patterns
+- **{New Theme}**: Recently appeared, {count} mentions
+- **{Growing Theme}**: {X}% increase from last period
+
+### Segment Insights
+- **{Segment}**: {sentiment + top theme}
+
+### Recommendations
+{1-3 actionable recommendations based on analysis}
+```
+
+## Technical Implementation
+
+See [refs/algorithms.md](refs/algorithms.md) for detailed analysis algorithms.
+
+## Integration
+
+### With wicked-crew (Auto Context)
+
+```python
+# Triggered by product:requirements:started event
+if event.type == "product:requirements:started":
+    # Analyze recent feedback for feature context
+    analysis = analyze(days=30, tags=["feature-request"])
+    emit_signal("voice:analysis:ready", analysis)
+```
+
+### With native tasks (Link to Tasks)
+
+```python
+# Tag themes with related task IDs by reading native tasks from
+# ${CLAUDE_CONFIG_DIR}/tasks/{session_id}/ and matching keywords
+tasks = search_native_tasks(theme.keywords)
+theme.related_tasks = tasks
+```
+
+## Storage
+
+Analysis results stored at: `{local_root}/wicked-garden:product/voice/analysis/{theme}/{date}.md` (resolve via `resolve_path.py wicked-garden:product`)
+
+## Rules
+
+- Limit to top 5 themes (context efficiency)
+- Always include sample size (N=X)
+- Provide confidence levels for trends
+- Include representative quotes
+- Keep output under 800 words
+- Distinguish frequency from severity

package/skills/product/analyze/refs/algorithms.md

@@ -0,0 +1,238 @@
+---
+phase_relevance: ["clarify", "design", "review"]
+archetype_relevance: ["*"]
+---
+# Analysis Algorithms
+
+Detailed algorithms for sentiment, theme extraction, and trend detection.
+
+## Sentiment Scoring Algorithm
+
+```python
+def score_sentiment(text: str) -> tuple[str, str]:
+    """
+    Returns (category, intensity)
+    category: positive, negative, neutral, mixed
+    intensity: strong, moderate, mild
+    """
+
+    # Keyword dictionaries
+    positive_strong = ["love", "amazing", "perfect", "brilliant", "excellent"]
+    positive_moderate = ["good", "helpful", "useful", "nice", "better"]
+    positive_mild = ["ok", "fine", "works", "decent"]
+
+    negative_strong = ["hate", "terrible", "broken", "unusable", "awful"]
+    negative_moderate = ["frustrating", "confusing", "slow", "annoying", "difficult"]
+    negative_mild = ["minor", "small issue", "could be better"]
+
+    # Count occurrences (case-insensitive)
+    text_lower = text.lower()
+
+    pos_strong = sum(1 for word in positive_strong if word in text_lower)
+    pos_moderate = sum(1 for word in positive_moderate if word in text_lower)
+    pos_mild = sum(1 for word in positive_mild if word in text_lower)
+
+    neg_strong = sum(1 for word in negative_strong if word in text_lower)
+    neg_moderate = sum(1 for word in negative_moderate if word in text_lower)
+    neg_mild = sum(1 for word in negative_mild if word in text_lower)
+
+    # Score calculation
+    pos_score = (pos_strong * 3) + (pos_moderate * 2) + (pos_mild * 1)
+    neg_score = (neg_strong * 3) + (neg_moderate * 2) + (neg_mild * 1)
+
+    # Intensity modifiers
+    if "!!!" in text or "???" in text:
+        if pos_score > neg_score:
+            pos_score *= 1.5
+        else:
+            neg_score *= 1.5
+
+    # CAPS detection
+    caps_ratio = sum(1 for c in text if c.isupper()) / max(len(text), 1)
+    if caps_ratio > 0.3:
+        neg_score *= 1.3  # CAPS usually indicates frustration
+
+    # Determine category
+    if pos_score > neg_score * 2:
+        category = "positive"
+        intensity = "strong" if pos_strong > 0 else "moderate" if pos_moderate > 0 else "mild"
+    elif neg_score > pos_score * 2:
+        category = "negative"
+        intensity = "strong" if neg_strong > 0 else "moderate" if neg_moderate > 0 else "mild"
+    elif abs(pos_score - neg_score) < 2:
+        category = "mixed"
+        intensity = "moderate"
+    else:
+        category = "neutral"
+        intensity = "mild"
+
+    return category, intensity
+```
+
+## Theme Extraction Algorithm
+
+```python
+def extract_themes(feedback_items: list[dict]) -> list[dict]:
+    """
+    Cluster feedback into themes using keyword frequency and co-occurrence.
+    Returns list of themes sorted by priority.
+    """
+
+    # 1. Keyword extraction
+    keywords = {}
+    for item in feedback_items:
+        words = extract_keywords(item['content'])
+        for word in words:
+            keywords[word] = keywords.get(word, 0) + 1
+
+    # 2. Identify theme clusters
+    # Keywords that frequently appear together form themes
+    themes = cluster_by_cooccurrence(keywords, feedback_items)
+
+    # 3. Score themes by priority
+    for theme in themes:
+        theme['priority'] = calculate_priority(
+            frequency=theme['count'],
+            severity=theme['avg_severity'],
+            urgency=theme['avg_urgency'],
+            total=len(feedback_items)
+        )
+
+    # 4. Sort by priority
+    return sorted(themes, key=lambda t: t['priority'], reverse=True)
+
+def extract_keywords(text: str) -> list[str]:
+    """Extract meaningful keywords, excluding stopwords."""
+    stopwords = {"the", "a", "an", "and", "or", "but", "in", "on", "at", "to"}
+    words = text.lower().split()
+    return [w for w in words if len(w) > 3 and w not in stopwords]
+
+def cluster_by_cooccurrence(keywords: dict, items: list) -> list[dict]:
+    """Find keywords that frequently appear together."""
+    # Use Jaccard similarity for clustering
+    # Keywords with >50% co-occurrence likely form a theme
+    pass  # Implementation details
+
+def calculate_priority(frequency: int, severity: float, urgency: float, total: int) -> float:
+    """
+    Priority = (Frequency_Ratio × Severity × Urgency)
+
+    frequency_ratio = frequency / total
+    severity = 1-5 (derived from sentiment intensity and keywords)
+    urgency = 1-5 (derived from recency and churn signals)
+    """
+    freq_ratio = frequency / max(total, 1)
+    return freq_ratio * severity * urgency
+```
+
+## Trend Detection Algorithm
+
+```python
+def detect_trends(theme: str, timeframes: list[str]) -> dict:
+    """
+    Detect if theme is emerging, growing, stable, or declining.
+
+    Args:
+        theme: Theme keyword(s)
+        timeframes: List of time periods (e.g., ["2025-12", "2026-01"])
+
+    Returns:
+        {
+            "trend": "GROWING" | "STABLE" | "DECLINING" | "EMERGING",
+            "change": "+45%",
+            "baseline": 10,
+            "current": 15
+        }
+    """
+
+    # Count mentions per timeframe
+    counts = []
+    for period in timeframes:
+        count = count_theme_mentions(theme, period)
+        counts.append(count)
+
+    # Detect pattern
+    if len(counts) < 2:
+        return {"trend": "INSUFFICIENT_DATA"}
+
+    baseline = counts[-2]  # Previous period
+    current = counts[-1]   # Current period
+
+    # Calculate change
+    if baseline == 0:
+        if current > 5:
+            return {
+                "trend": "EMERGING",
+                "change": "new",
+                "baseline": 0,
+                "current": current
+            }
+        else:
+            return {"trend": "INSUFFICIENT_DATA"}
+
+    change_pct = ((current - baseline) / baseline) * 100
+
+    if change_pct > 50:
+        trend = "GROWING"
+    elif change_pct < -30:
+        trend = "DECLINING"
+    elif abs(change_pct) <= 20:
+        trend = "STABLE"
+    else:
+        trend = "STABLE"
+
+    return {
+        "trend": trend,
+        "change": f"{change_pct:+.0f}%",
+        "baseline": baseline,
+        "current": current
+    }
+```
+
+## Segment Comparison Algorithm
+
+```python
+def compare_segments(theme: str, segments: list[str]) -> dict:
+    """
+    Compare how different customer segments feel about a theme.
+
+    Returns:
+        {
+            "enterprise": {"sentiment": "negative", "count": 25},
+            "smb": {"sentiment": "positive", "count": 12},
+            "insights": "Enterprise users struggling with feature X"
+        }
+    """
+
+    results = {}
+    for segment in segments:
+        feedback = filter_by_segment(theme, segment)
+
+        sentiment_scores = [score_sentiment(f['content']) for f in feedback]
+        avg_sentiment = aggregate_sentiment(sentiment_scores)
+
+        results[segment] = {
+            "sentiment": avg_sentiment,
+            "count": len(feedback),
+            "top_keywords": extract_top_keywords(feedback, limit=3)
+        }
+
+    # Generate insights from differences
+    insights = generate_segment_insights(results)
+
+    return {**results, "insights": insights}
+```
+
+## Implementation Notes
+
+For actual implementation, prefer:
+- Lightweight text processing (no heavy NLP libraries)
+- Regex-based keyword extraction
+- Simple frequency counting
+- File-based storage (no database required)
+
+## Performance
+
+- Target: <5s for 1000 feedback items
+- Cache theme extractions for 1 hour
+- Incremental updates (don't reprocess all feedback)