Listen

---
name: wicked-garden-product-listen
description: |
  Aggregate customer feedback from discovered sources across support, surveys,
  social, and direct channels. This skill should be used when the user needs to
  gather customer voice data to inform product decisions or understand sentiment.

  Use when: aggregating customer feedback from discovered sources, gathering
  voice-of-customer data, or surveying sentiment across channels.
metadata:
  role: module
  phases: "clarify,design,review"
  archetypes: "*"
---

# Listen Skill

Aggregate customer feedback from multiple channels with automatic source discovery.

> Tier-3 knowledge module behind the **`listen`** action of the
> `wicked-garden-product` domain skill (`skills/product/SKILL.md`). Canonical
> invocation: `/wicked-garden-product listen [args]` or plain natural language —
> the examples below use that form.

## Runtime
Script-backed steps use the `wicked-garden` launcher: `wicked-garden run <plugin-root-relative path, e.g. scripts/…> [args]`. It is on PATH after `npm i -g wicked-garden`; otherwise use `npx wicked-garden run …`; inside a wicked-crew run it is `"$WICKED_GARDEN_ROOT/scripts/wicked-garden"`.
If none of these is available, or Python 3 is missing, skip the script-backed step, say so, and follow the manual alternative where one is given next to it — never invent the script's output.
Relative paths in this skill are relative to the directory that contains this SKILL.md.

## 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 and routes to whichever are present:

| Capability | Discovers | Examples |
|------------|-----------|----------|
| `support-tickets` | CLI tools, APIs, exports providing ticket data | Ticket system CLIs, support platform exports, help desk APIs |
| `customer-feedback` | Feedback platforms, voting systems, feature request tools | Feedback exports, product board files, customer labels in issue trackers |
| `surveys` | Survey response exports (CSV, JSON) | Survey platform exports, NPS data files, form responses |
| `conversations` | Chat and messaging data sources | Chat exports, messaging platform data |
| `issue-tracking` | Bug/issue trackers with customer-reported items | Issue tracker CLIs with customer labels or tags |

## Usage

```bash
# 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: wicked-garden run scripts/resolve_path.py wicked-garden:product
   {local_root}/wicked-garden:product/voice/feedback/{source}/{date}/{id}.md
   ```

## Unified Feedback Format

```yaml
---
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:

```markdown
## 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](refs/channels.md) for detailed capability integration patterns.

## Integration

### With the memory layer (wicked-garden-mem)

**Hand-off** — open the `wicked-garden-mem` skill and run its `recall` action with `customer feedback about {topic}` as the query to recall past customer insights for historical context; on Claude Code this is the Skill tool, on any other seat open the named skill from your catalog and carry it out inline, then continue here.

### With wicked-crew
```python
# 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)