listen

Listen Skill

Aggregate customer feedback from multiple channels with automatic source discovery.

When to Use

• Starting product requirements (gather customer needs)
• Investigating customer pain points
• Reviewing recent feedback
• User asks to "listen to customers" or "what are customers saying"

Capability Discovery

The skill automatically discovers available feedback capabilities:

support-tickets capability

# Discovers CLI tools, APIs, and exports that provide ticket data
# Examples: ticket system CLIs, support platform exports, help desk APIs

customer-feedback capability

# Discovers feedback platforms, voting systems, feature request tools
# Examples: feedback exports, product board files, customer labels in issue trackers

surveys capability

# Discovers survey response exports (CSV, JSON)
# Examples: survey platform exports, NPS data files, form responses

conversations capability

# Discovers chat and messaging data sources
# Examples: chat exports, messaging platform data

issue-tracking capability

# Discovers bug/issue tracking systems with customer-reported items
# Examples: issue tracker CLIs with customer labels or tags

Usage

# Listen to all available capabilities (auto-discovers sources)
/wicked-garden:product:listen

# Specific capability type
/wicked-garden:product:listen --capability support-tickets

# Time window
/wicked-garden:product:listen --days 30
/wicked-garden:product:listen --since "2026-01-01"

# Filter by tags
/wicked-garden:product:listen --tags bug,feature-request

# Limit results
/wicked-garden:product:listen --limit 50

Aggregation Strategy

1. Discover Available Capabilities

   • Check for support-tickets capability (CLI tools, APIs)
   • Check for customer-feedback capability (exports, voting systems)
   • Check for surveys capability (CSV/JSON exports)
   • Check for conversations capability (chat/messaging data)
   • Check for issue-tracking capability (customer-labeled issues)
   • Look for saved feedback in voice store

2. Fetch Recent Feedback

   • Default: Last 30 days
   • Configurable timeframe
   • Filter by source, tag, or keyword

3. Normalize Format

   • Extract: ID, source, date, author, content, sentiment
   • Tag with categories (bug, feature, praise, complaint)
   • Store in unified format

4. Store for Analysis

   # Resolved via: sh "${CLAUDE_PLUGIN_ROOT}/scripts/_python.sh" "${CLAUDE_PLUGIN_ROOT}/scripts/resolve_path.py" wicked-garden:product
   {local_root}/wicked-garden:product/voice/feedback/{source}/{date}/{id}.md
   

Unified Feedback Format

---
id: fb_abc123
capability: support-tickets
source_tool: detected-cli-tool
source_id: ticket_456
date: 2026-01-20T10:30:00Z
author: customer@example.com
segment: enterprise
tags: [bug, mobile, performance]
sentiment: negative
priority: high
---

# {Title/Subject}

## Original Feedback
{Raw customer quote}

## Context
- Platform: iOS 16
- Plan: Enterprise
- User since: 2025-06-01

Output

Concise summary of aggregated feedback:

## Listening Report: {Timeframe}

### Capabilities Discovered
- support-tickets: {X} items from {N} source(s)
- customer-feedback: {Y} items from {N} source(s)
- surveys: {Z} responses from {N} source(s)
- Total: {N} feedback items across {M} capabilities

### Quick Stats
- Sentiment: {%pos} positive, {%neg} negative, {%neu} neutral
- Top tags: {tag1} ({count}), {tag2} ({count})
- Critical items: {count}

### Recent Highlights
1. **{Title}** - {source} - {date}
   - Sentiment: {sentiment}
   - Quote: "{excerpt}"

{Top 5-10 items}

### Next Steps
Run /wicked-garden:product:analyze to extract themes and trends.

See channels.md for detailed capability integration patterns.

Integration

With wicked-garden:mem

# Recall past customer insights via /wicked-garden:mem:recall
memories = recall(f"customer feedback about {topic}")
# Provide historical context

With wicked-crew

# Auto-trigger during product:requirements phase
if event == "product:requirements:started":
    feedback = listen(days=30, tags=["feature-request"])
    inject_context(feedback)

Storage

Feedback stored at: {local_root}/wicked-garden:product/voice/feedback/{source}/{YYYY-MM}/{id}.md (resolve via resolve_path.py wicked-garden:product)

Error Handling

• Source unavailable: Skip gracefully, report in summary
• No recent feedback: Report "No feedback found in timeframe"
• API rate limits: Cache and resume
• Invalid format: Log warning, continue with valid items

Rules

• Never expose customer PII beyond what's already in feedback
• Respect source rate limits
• Cache API responses when possible
• Report source availability in output
• Keep summaries concise (top 10 items max)