video-analytics-interpreter

video-analytics-interpreter is a skill for Claude Code, Codex from nicepkg/ai-workflow. It costs 48 tokens per session (2,323 once invoked), scanned A, original, MIT.

A guide for understanding performance data from YouTube, TikTok, and other video platforms. It explains measures such as views, watch time, click-through rate, and audience retention.

In plain words
What is it for?
Reviewing video or channel performance, finding where viewers leave, and planning changes to content, titles, or thumbnails.
Why use it?
Raw platform numbers can be difficult to interpret or connect to specific improvements. This helps turn those numbers into trends and suggested actions.

Skill for Claude CodeCodex

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add skills/nicepkg/ai-workflow/video-analytics-interpreter
Any agent
npx skills add nicepkg/ai-workflow --skill video-analytics-interpreter
Clone the repo
git clone --depth 1 https://github.com/nicepkg/ai-workflow

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for video-analytics-interpreter

README.md
[![agentmods](https://agentmods.dev/badge/skills/nicepkg/ai-workflow/video-analytics-interpreter.svg)](https://agentmods.dev/skills/nicepkg/ai-workflow/video-analytics-interpreter)
Your own site
<a href="https://agentmods.dev/skills/nicepkg/ai-workflow/video-analytics-interpreter"><img src="https://agentmods.dev/badge/skills/nicepkg/ai-workflow/video-analytics-interpreter.svg" alt="Measured on agentmods" height="20"></a>
Per session 48 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,323 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00048 $0.02323
Opus 5 $0.00024 $0.01162
Sonnet 5 $0.00010 $0.00465
Haiku 4.5 $0.00005 $0.00232

Measured yesterday against content hash b84b6e554994, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

video-analytics-interpreter scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

workflows/video-creator-workflow/.claude/skills/video-analytics-interpreter/SKILL.md · 341 lines

How it starts

The opening of the file, as written. The whole thing — 341 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Video Analytics Interpreter

Transform raw video metrics into actionable growth strategies.

Key Metrics Explained

YouTube Analytics

📊 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 Analytics

📊 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 bio

Analytics Interpretation Framework

Step 1: Identify the Pattern

PERFORMANCE 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 it

Read the full file on GitHub · 341 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. yesterday First seen · 341 lines · 48 tokens per session scan A b84b6e554994

Subscribe to this mod's changes

video-analytics-interpreter is a skill published in the GitHub repository nicepkg/ai-workflow (282 stars, last pushed 7mo ago), licensed MIT. It adds 48 tokens to every session and 2,323 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.