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.
npx agentmods add skills/nicepkg/ai-workflow/video-analytics-interpreternpx skills add nicepkg/ai-workflow --skill video-analytics-interpretergit clone --depth 1 https://github.com/nicepkg/ai-workflowWrote 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.
[](https://agentmods.dev/skills/nicepkg/ai-workflow/video-analytics-interpreter)<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>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.
| Model | Per session | Once 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 |
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.
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
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.
- yesterday First seen · 341 lines · 48 tokens per session scan A b84b6e554994
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.
Other skills, from other repositories
aatmf-t10-confidentiality-breach
AATMF T10 — Integrity & Confidentiality Breach. System prompt extraction, training-data extraction, model-weight leakage, private-key recovery.
ensembl-database
Query Ensembl genome database REST API for 250+ species. Gene lookups, sequence retrieval, variant analysis, comparative genomics, orthologs, VEP predictions, for genomic research.
mochi-remind
Handle due reminders — notify the user with natural language and mark them done.
wukongim-cloud-analysis
Diagnose one exact live WuKongIM cloud Simulation Run or chat-lifecycle Cloud Lease through the repository Analysis MCP. Use when the user or a local Analysis Session asks Codex to inspect a run's cluster state, Prometheus signals, application logs, diagnostics, Controller task audits, profiles, or redacted config…
memory
Use when the user asks to remember, recall, forget, update, search, or inspect durable OpenSquilla memory, including profile facts in USER.md and long-term notes in MEMORY.md or memory//.md.
sidewinder-rattlesnake
Adversary-emulation profile for SideWinder (G0121 / Rattlesnake / T-APT-04 / Razor Tiger), India's suspected state-sponsored cyber-espionage actor.