Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Interpret YouTube Analytics, TikTok Analytics, and video performance data. Identifies trends, explains metrics, and provides actionable recommendations for growth. Use when analyzing video performance, understanding metrics, or optimizing channel strategy.
.claude/skills/nicepkg-video-analytics-interpreter/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-09 | ✗→✓ | ▲ Improved | 76% | 0% |
| case-01 | ✓→✓ | ＝ Same ✓ | 32% | 0% |
| case-18 | ✓→✓ | ＝ Same ✓ | 103% | 0% |
| case-08 | ✓→✓ | ＝ Same ✓ | 171% | 0% |
| case-02 | ✓→✓ | ＝ Same ✓ | 59% | 0% |
Transform raw video metrics into actionable growth strategies.
📊 CORE METRICS:
VIEWS
- What: Total video plays (30+ seconds or full if shorter)
- Good: Trending upward week-over-week
- Warning: Sudden drops may indicate algorithm changes
WATCH TIME
- What: Total minutes watched
- Why it matters: #1 factor for YouTube algorithm
- Good: Higher than channel average
AVERAGE VIEW DURATION (AVD)
- What: Average time viewers watch
- Benchmark: 50%+ of video length is good
- Tip: Longer videos = lower % is acceptable
CLICK-THROUGH RATE (CTR)
- What: Impressions → Clicks percentage
- Good: 4-10% (varies by content type)
- Excellent: 10%+
- Warning: <2% needs thumbnail/title work
IMPRESSIONS
- What: Times thumbnail shown to users
- Note: Higher impressions = YouTube promoting you
- Tip: CTR × Impressions = Views potential
AUDIENCE RETENTION
- What: Graph showing when viewers leave
- Key: Look for drop-off points
- Goal: Flat line is ideal, gradual decline acceptable
ENGAGEMENT RATE
- What: (Likes + Comments) / Views
- Good: 4-8%
- Excellent: 8%+📊 TIKTOK METRICS:
VIDEO VIEWS
- Includes replays and loops
- Higher than YouTube due to autoplay
AVERAGE WATCH TIME
- Critical for algorithm
- Goal: Above 100% (indicates replays)
WATCH FULL VIDEO RATE
- % who watched entire video
- Good: 30%+ for 15-30 sec videos
- Excellent: 50%+
ENGAGEMENT RATE
- (Likes + Comments + Shares) / Views
- Good: 5-10%
- Viral potential: 15%+
SHARES
- Most important engagement type
- Strong shares = algorithm boost
- Indicates "save for later" or "send to friend"
PROFILE VIEWS
- Viewers who clicked your profile
- Indicates content sparked curiosity
- Goal: 1-3% of views
FOLLOWER CONVERSION
- New followers / Profile views
- Good: 10-20%
- Tip: Pin best content, optimize bioPERFORMANCE CATEGORIES:
🚀 BREAKOUT SUCCESS (Top 10% of your content)
- Views: 3x+ your average
- CTR: Above your channel average
- Retention: Higher than similar videos
- Action: Double down, create more like this
✅ SOLID PERFORMER (Above average)
- Views: 1.5-3x your average
- CTR: At or above average
- Retention: Consistent with similar content
- Action: Note what worked, iterate
😐 AVERAGE
- Views: Near your typical numbers
- CTR: Around channel average
- Retention: Normal patterns
- Action: Test new elements
⚠️ UNDERPERFORMER (Below average)
- Views: Below your average
- CTR: Lower than normal
- Retention: Early drop-offs
- Action: Analyze what went wrong
❌ FLOP (Bottom 10%)
- Views: Significantly below average
- CTR: Much lower than normal
- Retention: Severe early drop-off
- Action: Don't delete - learn from itLOW VIEWS DIAGNOSIS:
Q1: Is CTR low?
YES → Thumbnail/title problem
NO → Algorithm not promoting (impressions issue)
Q2: Is retention low?
YES → Content/hook problem
NO → Distribution/timing issue
Q3: Low impressions but good CTR/retention?
YES → Algorithm testing phase, be patient
→ Or topic has limited search volume
DIAGNOSIS FLOWCHART:
┌─────────────────────────────────────────────────────────┐
│ Low Views? │
│ ↓ │
│ Check CTR → Low? → Fix thumbnail/title │
│ ↓ │
│ CTR OK? → Check Retention → Low? → Fix hook/content │
│ ↓ │
│ Both OK? → Check Impressions → Low? → Topic/timing issue│
│ ↓ │
│ All OK but low views? → Give it time, algorithm testing │
└─────────────────────────────────────────────────────────┘RETENTION PATTERNS:
📉 EARLY DROP (0-30 seconds)
Problem: Weak hook, misleading thumbnail/title
Fix: Stronger hook, match expectations
📉 GRADUAL DECLINE (Steady downward slope)
Normal: Expected for most videos
Optimize: Add pattern breaks every 30-60 sec
📉 CLIFF DROP (Sudden sharp decline)
Problem: Boring section, promise unfulfilled
Fix: Cut/improve that section, better pacing
📈 SPIKE (Retention increases)
Meaning: Replay/rewind point
Opportunity: Create clip from this moment
─── FLAT LINE (Stable)
Ideal: Viewers engaged throughout
Indicates: Strong content-hook match═══════════════════════════════════════════════════════════════
VIDEO ANALYTICS REPORT
Video: [Title]
Published: [Date]
Analysis Period: [X days since publish]
═══════════════════════════════════════════════════════════════
📊 PERFORMANCE SUMMARY:
─────────────────────────────────────────────────────────────
Views: [X] ([+/-X%] vs channel avg)
Watch Time: [X hours] ([+/-X%] vs channel avg)
CTR: [X%] ([+/-X%] vs channel avg)
Avg View Duration: [X:XX] ([X%] of video)
Engagement: [X%] (Likes: X, Comments: X)
Performance Tier: [🚀 Breakout / ✅ Solid / 😐 Average / ⚠️ Under / ❌ Flop]
📈 RETENTION ANALYSIS:
─────────────────────────────────────────────────────────────
Hook Effectiveness (0-30s): [Strong/Moderate/Weak]
- [X%] still watching at 30 seconds
Key Drop-off Points:
- [Timestamp]: [X%] dropped - Likely cause: [reason]
- [Timestamp]: [X%] dropped - Likely cause: [reason]
Rewatch Spikes:
- [Timestamp]: Viewers replayed - Content: [what happened]
Overall Shape: [Early drop / Gradual decline / Cliff / Flat]
🎯 TRAFFIC SOURCES:
─────────────────────────────────────────────────────────────
1. [Source]: [X%] - [Insight]
2. [Source]: [X%] - [Insight]
3. [Source]: [X%] - [Insight]
Best Performing Source: [Source] - Why: [explanation]
Underperforming Source: [Source] - Recommendation: [action]
👥 AUDIENCE INSIGHTS:
─────────────────────────────────────────────────────────────
New vs Returning: [X% new / X% returning]
Geographic: Top countries [list]
Demographics: Primary age/gender [if available]
Device: [X% mobile / X% desktop / X% TV]
Subscriber Impact: [+X subscribers] ([X%] conversion)
🔍 DIAGNOSIS:
─────────────────────────────────────────────────────────────
Primary Issue: [Identify main problem if any]
Root Cause: [Why this happened]
Secondary Issues: [Other concerns]
💡 RECOMMENDATIONS:
─────────────────────────────────────────────────────────────
IMMEDIATE (This Video):
1. [Action] - Expected impact: [result]
2. [Action] - Expected impact: [result]
FUTURE VIDEOS:
1. [Lesson learned] - Apply to: [future content]
2. [Lesson learned] - Apply to: [future content]
A/B TEST SUGGESTION:
- Test: [Element to test]
- Hypothesis: [What you expect]
- Measure: [Metric to track]
🎬 CLIP OPPORTUNITY:
─────────────────────────────────────────────────────────────
High-engagement moment at [Timestamp]: "[Description]"
Recommended for: [TikTok/Shorts/Reels]
Hook angle: "[Suggested hook]"
📅 NEXT STEPS:
─────────────────────────────────────────────────────────────
[ ] [Action item 1]
[ ] [Action item 2]
[ ] [Action item 3]
═══════════════════════════════════════════════════════════════Analyze this video's performance:
[Paste analytics data or describe metrics]
Comparisons:
- Channel average CTR: [X%]
- Channel average retention: [X%]
- Similar video performance: [description]My video has [X views] but my CTR is [X%].
Why is it underperforming and how do I fix it?Analyze these videos' performance trends:
Video 1: [Title] - [Views, CTR, Retention]
Video 2: [Title] - [Views, CTR, Retention]
Video 3: [Title] - [Views, CTR, Retention]
What patterns do you see?Here are my last 10 videos' metrics:
[List videos with key metrics]
How is my channel performing overall?
What should I focus on? CTR Retention Engagement
Educational 3-6% 40-60% 3-6%
Entertainment 5-10% 30-50% 5-10%
Gaming 4-8% 25-45% 4-8%
Vlog 3-7% 35-55% 4-8%
Product Review 4-8% 40-60% 3-6%
Tutorial 3-6% 45-65% 3-5%
Short-form 8-15% 70-100%+ 8-15%⚠️ IMMEDIATE ATTENTION:
- CTR dropped 50%+ from average
- Retention cliff in first 30 seconds
- Impressions declining week-over-week
- Subscriber loss instead of gain
📉 CONCERNING TRENDS:
- AVD decreasing over time
- Engagement rate declining
- More dislikes than usual
- Comments increasingly negative| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | pass→pass | 22,710 | 14,279 | -37% | 1 | 1 | 0% | 3,733 | 4,941 | +32% | 0 | 0 | — |
case-18 | pass→pass | 10,214 | 16,258 | +59% | 1 | 1 | 0% | 1,733 | 3,513 | +103% | 0 | 0 | — |
case-08 | pass→pass | 8,007 | 5,719 | -29% | 1 | 1 | 0% | 1,221 | 3,306 | +171% | 0 | 0 | — |
case-02 | pass→pass | 18,627 | 12,363 | -34% | 1 | 1 | 0% | 2,761 | 4,395 | +59% | 0 | 0 | — |
case-03 | pass→pass | 17,322 | 12,845 | -26% | 1 | 1 | 0% | 2,758 | 4,541 | +65% | 0 | 0 | — |
case-04 | pass→pass | 14,870 | 13,986 | -6% | 1 | 1 | 0% | 2,361 | 4,610 | +95% | 0 | 0 | — |
case-05 | pass→pass | 18,970 | 17,311 | -9% | 1 | 1 | 0% | 3,138 | 5,184 | +65% | 0 | 0 | — |
case-06 | pass→pass | 18,044 | 18,584 | +3% | 1 | 1 | 0% | 2,779 | 4,968 | +79% | 0 | 0 | — |
case-07 | pass→pass | 11,530 | 11,624 | +1% | 1 | 1 | 0% | 1,818 | 4,139 | +128% | 0 | 0 | — |
case-09 | fail→pass | 11,701 | 5,907 | -50% | 1 | 1 | 0% | 1,880 | 3,317 | +76% | 0 | 0 | — |
case-10 | pass→pass | 9,243 | 5,616 | -39% | 1 | 1 | 0% | 1,516 | 3,298 | +118% | 0 | 0 | — |
case-11 | pass→pass | 13,378 | 11,081 | -17% | 1 | 1 | 0% | 2,197 | 4,068 | +85% | 0 | 0 | — |
case-12 | pass→pass | 9,760 | 9,899 | +1% | 1 | 1 | 0% | 1,655 | 3,914 | +136% | 0 | 0 | — |
case-13 | pass→pass | 9,744 | 7,423 | -24% | 1 | 1 | 0% | 1,609 | 3,534 | +120% | 0 | 0 | — |
case-14 | pass→pass | 7,536 | 5,112 | -32% | 1 | 1 | 0% | 1,269 | 3,178 | +150% | 0 | 0 | — |
case-15 | pass→pass | 11,681 | 10,785 | -8% | 1 | 1 | 0% | 1,684 | 3,877 | +130% | 0 | 0 | — |
case-16 | pass→pass | 11,748 | 11,227 | -4% | 1 | 1 | 0% | 1,723 | 3,938 | +129% | 0 | 0 | — |
case-17 | pass→pass | 9,530 | 8,079 | -15% | 1 | 1 | 0% | 1,525 | 3,602 | +136% | 0 | 0 | — |
case-19 | pass→pass | 9,150 | 6,160 | -33% | 1 | 1 | 0% | 1,815 | 3,435 | +89% | 0 | 0 | — |
case-20 | pass→pass | 13,388 | 11,200 | -16% | 1 | 1 | 0% | 2,170 | 4,088 | +88% | 0 | 0 | — |
case-21 | pass→pass | 10,819 | 5,589 | -48% | 1 | 1 | 0% | 1,531 | 3,224 | +111% | 0 | 0 | — |
case-22 | pass→pass | 13,143 | 13,944 | +6% | 1 | 1 | 0% | 1,936 | 4,379 | +126% | 0 | 0 | — |
case-23 | pass→pass | 8,831 | 4,978 | -44% | 1 | 1 | 0% | 1,486 | 3,178 | +114% | 0 | 0 | — |
case-24 | pass→pass | 12,471 | 7,491 | -40% | 1 | 1 | 0% | 1,930 | 3,521 | +82% | 0 | 0 | — |
case-25 | pass→pass | 11,792 | 10,732 | -9% | 1 | 1 | 0% | 1,969 | 3,808 | +93% | 0 | 0 | — |
DecimalAI ran this skill against gemini-3.6-flash twice over the same eval suite — once with the skill loaded and once without — and compared the two runs case by case. 25 cases were attempted. The headline lift of +4 percentage points is the difference between those two pass rates over the 25 comparable cases.
Without the skill loaded, the model failed this case. With it loaded, the same prompt on the same model passed. This is one improved case from the latest verified run; every case, including any that regressed, is in the table above.
Other measured skills in the registry, with their headline benchmark lift.