Use when analyzing user feedback data - generates analytics and insights from collected ratings to identify agent performance, improvement areas, and trends. Do NOT use for collecting feedback (that happens automatically via hooks).
/plugin marketplace add jrc1883/popkit-claude/plugin install popkit@popkit-marketplaceThis skill inherits all available tools. When active, it can use any tool Claude has access to.
Generate analytics and insights from collected user feedback.
Part of Issue #91 (User Feedback Collection System) Parent: Epic #88 (Self-Improvement & Learning System)
Invoke this skill when:
Analyzes collected feedback to provide:
from feedback_store import get_feedback_store
store = get_feedback_store()
stats = store.get_stats()
agent_stats = store.get_agent_stats()
low_rated = store.get_low_rated_items()
Present findings in a structured format:
## Feedback Report
### Overview
| Metric | Value |
|--------|-------|
| Total Feedback | {total} |
| Average Rating | {avg:.2f}/3 |
| Recent (7 days) | {recent} |
| Low-Rated Items | {low_count} |
### Rating Distribution
0 (Harmful) : ████░░░░░░ 15% 1 (Unhelpful) : ██░░░░░░░░ 8% 2 (Helpful) : ████████░░ 42% 3 (Very) : ███████░░░ 35%
### Agent Performance
| Agent | Avg Rating | Count | Trend |
|-------|------------|-------|-------|
| code-reviewer | 2.8 | 45 | ↑ |
| bug-whisperer | 2.6 | 23 | → |
| security-auditor | 2.4 | 12 | ↓ |
### Items Needing Attention
These items have average ratings ≤ 1.5:
1. **command:/popkit:debug** (avg: 1.2, count: 5)
- Last feedback: "Didn't find the actual issue"
- Suggested action: Review debugging workflow
2. **agent:api-designer** (avg: 1.4, count: 8)
- Last feedback: "Generated outdated patterns"
- Suggested action: Update API design templates
Use AskUserQuestion to offer follow-up actions:
[AskUserQuestion: What would you like to do?]
- View details for low-rated items
- Export feedback data
- Clear old feedback
- Adjust feedback settings
## Feedback Summary
📊 **45 total ratings** | Avg: 2.5/3 | 12 this week
Top performers: code-reviewer (2.8), test-writer-fixer (2.7)
Needs attention: api-designer (1.4), debug (1.2)
Run `pop-feedback-report --full` for detailed breakdown.
Include all sections above plus:
| Argument | Description |
|---|---|
| (none) | Quick summary |
--full | Full detailed report |
--agent NAME | Focus on specific agent |
--command NAME | Focus on specific command |
--low-rated | Only show items needing attention |
--export FILE | Export data to JSON file |
User: Show feedback summary
Claude: [Invokes pop-feedback-report skill]
## Feedback Summary
📊 **45 total ratings** | Avg: 2.5/3 | 12 this week
Top performers:
- code-reviewer (2.8, 15 ratings)
- test-writer-fixer (2.7, 8 ratings)
Needs attention:
- api-designer (1.4, 8 ratings) ⚠️
User: How is the code-reviewer performing?
Claude: [Invokes pop-feedback-report --agent code-reviewer]
## code-reviewer Feedback Analysis
| Metric | Value |
|--------|-------|
| Total Ratings | 45 |
| Average | 2.8/3 |
| This Week | 8 |
**Rating Distribution:**
- 3 (Very helpful): 55%
- 2 (Helpful): 35%
- 1 (Unhelpful): 8%
- 0 (Harmful): 2%
**Recent Comments:**
- "Great catch on the security issue" (rating: 3)
- "Missed some edge cases" (rating: 2)
**Trend:** ↑ Improving (was 2.5 last month)
feedback_store.py - SQLite storage for feedbackfeedback_triggers.py - Feedback timing logicfeedback_hook.py - PostToolUse hook for collection/popkit:dev - May trigger feedback after workflowsFor rating distributions, use simple ASCII bar charts:
def rating_bar(count: int, total: int, width: int = 10) -> str:
"""Generate an ASCII progress bar."""
if total == 0:
return "░" * width
filled = int((count / total) * width)
return "█" * filled + "░" * (width - filled)
Compare current period average to previous period:
def calculate_trend(current_avg: float, previous_avg: float) -> str:
"""Determine trend arrow."""
diff = current_avg - previous_avg
if diff > 0.2:
return "↑"
elif diff < -0.2:
return "↓"
return "→"
When showing feedback comments:
This skill should be used when the user asks to "create an agent", "add an agent", "write a subagent", "agent frontmatter", "when to use description", "agent examples", "agent tools", "agent colors", "autonomous agent", or needs guidance on agent structure, system prompts, triggering conditions, or agent development best practices for Claude Code plugins.
This skill should be used when the user asks to "create a slash command", "add a command", "write a custom command", "define command arguments", "use command frontmatter", "organize commands", "create command with file references", "interactive command", "use AskUserQuestion in command", or needs guidance on slash command structure, YAML frontmatter fields, dynamic arguments, bash execution in commands, user interaction patterns, or command development best practices for Claude Code.
This skill should be used when the user asks to "create a hook", "add a PreToolUse/PostToolUse/Stop hook", "validate tool use", "implement prompt-based hooks", "use ${CLAUDE_PLUGIN_ROOT}", "set up event-driven automation", "block dangerous commands", or mentions hook events (PreToolUse, PostToolUse, Stop, SubagentStop, SessionStart, SessionEnd, UserPromptSubmit, PreCompact, Notification). Provides comprehensive guidance for creating and implementing Claude Code plugin hooks with focus on advanced prompt-based hooks API.