feedback-analyzer（反馈分析仪）

Feedback Analyzer

Overview

feedback-analyzer evaluates skill effectiveness through analysis of usage data, feedback, metrics, and outcomes.

Purpose: Data-driven understanding of what works and what doesn't

The 4 Analysis Operations:

1. Collect Usage Data - Gather metrics on skill usage and effectiveness
2. Measure Effectiveness - Quantify impact and ROI of skills
3. Analyze Trends - Identify patterns in usage and effectiveness
4. Extract Insights - Generate actionable insights from data

When to Use

• After skills have been used (have usage data)
• Measuring toolkit ROI and impact
• Understanding which skills provide most value
• Identifying underutilized skills
• Data-driven improvement decisions

Operations

Operation 1: Collect Usage Data

Purpose: Gather data on how skills are used

Data Sources:

• Build times (how long to build skills?)
• Usage frequency (which skills used most?)
• Effectiveness metrics (do skills achieve purposes?)
• Quality scores (from reviews)
• User feedback (satisfaction, issues)

Process:

1. Identify data sources
2. Collect available metrics
3. Document usage patterns
4. Organize data for analysis

Output: Usage data collection

Time: 30-60 minutes

Operation 2: Measure Effectiveness

Purpose: Quantify skill impact and ROI

Metrics:

• Time savings (vs without tool)
• Quality improvements (before/after)
• Efficiency gains (percentage faster)
• Usage rate (frequency of use)
• Satisfaction (user ratings)

Process:

1. Define effectiveness criteria
2. Calculate metrics
3. Compare to baseline or targets
4. Assess ROI

Output: Effectiveness measurements with evidence

Time: 45-90 minutes

Operation 3: Analyze Trends

Purpose: Identify patterns in effectiveness over time

Process:

1. Plot metrics over time
2. Identify trends (improving/degrading/stable)
3. Find correlations
4. Detect anomalies

Output: Trend analysis with insights

Time: 45-90 minutes

Operation 4: Extract Insights

Purpose: Generate actionable insights from data

Process:

1. Synthesize findings
2. Identify high-impact insights
3. Make recommendations
4. Prioritize actions

Output: Data-driven insights and recommendations

Time: 30-60 minutes

Example Analysis

Effectiveness Analysis: Development Toolkit
===========================================

Usage Data (Skills 1-23):
- Build times: 2h - 20h (mean: 6.8h)
- Efficiency: 35% - 97% faster than baseline (mean: 85%)
- Quality: 100% pass rate (5/5 structure)

Effectiveness Metrics:
- Time Saved: 392 hours total (85% reduction)
- Quality: Maintained (100% Grade A)
- Completion: 100% (all 23 finished)
- ROI: 392h saved / 68h invested = 576% ROI

Trends:
✅ Improving: Efficiency compounds (72% → 97%)
✅ Stable: Quality consistent (all 5/5)
⚠️ Plateau: Efficiency plateaus ~85-90% for simple skills

Insights:
1. Toolkit highly effective (576% ROI, 85% efficiency)
2. Quality maintained despite speed (100% pass rate)
3. Efficiency plateaus at 85-90% (cannot exceed certain minimum times)
4. Complex skills still benefit (35-50% faster)

Recommendations:
1. Continue using toolkit (proven effective)
2. Expect 85-90% efficiency for simple/medium skills
3. Adjust estimates for complex skills (30-50% faster, not 85%)
4. Focus on quality maintenance (already excellent)

Quick Reference

Integration: Uses data from skill-evolution-tracker, analysis skill

feedback-analyzer provides data-driven understanding of toolkit effectiveness for evidence-based improvement decisions.