youtube-seo-video

youtube-seo-video is a skill for Claude Code from deeployCO/youtube-seo-skills. It costs 82 tokens per session (2,585 once invoked), scanned A, original, MIT.

A detailed review of one YouTube video covering viewer retention, the opening hook, search metadata, captions, thumbnail, audio, and engagement features. Retention means how much of the video viewers continue watching.

In plain words
What is it for?
Use it to diagnose a video's performance and create fixes for its title, description, tags, chapters, thumbnail, captions, audio, and end screen.
Why use it?
It helps identify why a video may lose viewers or attract few clicks, using available video data instead of changing titles or thumbnails blindly.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Good fit Use it to diagnose a video's performance and create fixes for its title, description, tags, chapters, thumbnail, captions, audio, and end screen.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/deeployco/youtube-seo-skills/youtube-seo-video
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.

Any agent
npx skills add deeployCO/youtube-seo-skills --skill youtube-seo-video
Clone the repo
git clone --depth 1 https://github.com/deeployCO/youtube-seo-skills

Made for: Claude Code.

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 youtube-seo-video

README.md
[![agentmods](https://agentmods.dev/badge/skills/deeployco/youtube-seo-skills/youtube-seo-video/github.svg)](https://agentmods.dev/skills/deeployco/youtube-seo-skills/youtube-seo-video)
Your own site
<a href="https://agentmods.dev/skills/deeployco/youtube-seo-skills/youtube-seo-video"><img src="https://agentmods.dev/badge/skills/deeployco/youtube-seo-skills/youtube-seo-video/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for youtube-seo-video

Your own site · 80×15
<a href="https://agentmods.dev/skills/deeployco/youtube-seo-skills/youtube-seo-video"><img src="https://agentmods.dev/badge/skills/deeployco/youtube-seo-skills/youtube-seo-video.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 82 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,585 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00082 $0.02585
Opus 5 $0.00041 $0.01293
Sonnet 5 $0.00016 $0.00517
Haiku 4.5 $0.00008 $0.00259

Measured 13d ago against content hash 0ef45f6b999a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

youtube-seo-video 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 13d ago.

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.

youtube-seo-video/SKILL.md · 248 lines

How it starts

The opening of the file, as written. The whole thing — 248 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Single Video Deep Analysis (Advanced)

Diagnose why a video underperforms and produce a paste-ready fix kit. Retention and CTR are the primary levers; metadata is secondary. Always ask for the Studio CSV export if the user wants retention diagnosis — never guess Tier 1 numbers.

Data Collection (in order)

  1. WebFetch the watch URL → title, description (partial), view/like, duration, upload date, channel, visible chapters
  2. yt-dlp (scripts/fetch_video.py or direct call) → full JSON metadata, tags, full description, chapters, thumbnails, captions
  3. YouTube Data API (if key) → videos.list?part=snippet,statistics, contentDetails,topicDetails,status,player,liveStreamingDetails and captions.list + captions.download (if OAuth)
  4. Transcript: prefer manual captions > auto-captions > Whisper transcription from audio stream
  5. Studio CSV (user-provided): retention curve, traffic sources, CTR by source, impressions, audience tab, real-time first-24h curve
  6. Audio loudness: ffmpeg -i audio.m4a -af loudnorm=print_format=json -f null - → integrated LUFS, true peak
  7. Thumbnail file: download for analysis via scripts/analyze_thumbnail.py
  8. SERP grid: fetch top-10 for primary keyword, save competitor thumbnails and titles for differentiation scoring

Analysis Dimensions

1. Retention Curve (highest weight when Studio data provided)

Diagnose from the Studio retention curve:

  • 0-15s intro: target ≥70% still watching. Below → hook problem. Diagnose: weak first sentence, no payoff preview, long logo animation, re-introducing yourself ("Hey guys welcome back..."), asking to subscribe before value delivery.
  • 15-60s premise: target ≥60%. Below → premise unclear or mismatch with title/thumbnail.
  • Retention cliffs: any drop >10% in <5s is a structural issue. Map cliffs to transcript timestamps and identify:
    • Tangent / digression
    • Ad or sponsor break placed badly
    • Pacing death (long, slow exposition)
    • Promise broken (title said X, video now does Y)
    • Visual monotony (static shot >20s without B-roll)
  • Mid-video sustain: target curve slope ≥-0.3%/sec. Steeper = boring middle.
  • Ending: the last 30s often rises (re-watchers, end-screen hover). If it drops hard, end-screen is poorly placed or content feels done before the promise delivered.
  • Spike detection: peaks = rewatched moments = high-value moments. Reuse as chapter titles, thumbnails, Shorts clips.
  • APV vs niche median: score video as ×median. Flag anything <0.8×.

Read the full file on GitHub · 248 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. 13d ago First seen · 248 lines · 82 tokens per session scan A 0ef45f6b999a

Subscribe to this mod's changes

youtube-seo-video is a skill published in the GitHub repository deeployCO/youtube-seo-skills (9 stars, last pushed 5mo ago), licensed MIT. It adds 82 tokens to every session and 2,585 once invoked, about $0.0004 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 2026-08-31.

Related

Other skills, from other repositories

cms-metadata-writer

Writes structured metadata fields — title tag, meta description, tags, category, slug, and Open Graph text — for a CMS entry, optimized for search discoverability and social sharing.

ur-grue/autopunk-media-skills · 42 tokens

show-notes-generator

Generates complete, SEO-friendly podcast show notes from a transcript or episode summary — including episode description, key takeaways, timestamps, guest bio, and links section — ready to paste into a podcast host platform.

ur-grue/autopunk-media-skills · 47 tokens

headline-ab-variants-writer

Takes one original headline and produces five distinct tested variants, each using a different proven approach to drive clicks, shares, or engagement — ready to load directly into a CMS or A/B testing tool.

ur-grue/autopunk-media-skills · 47 tokens

content-amplifier

Use when the user asks to "amplify influencer content with paid media", "set up whitelisting or Spark Ads", "decide which posts to boost", "repurpose influencer content", "turn one video into multiple ads", or "build a UGC asset library"; produces (paid mode) a content-selection scorecard, a paid amplification…

aaron-he-zhu/aaron-marketing-skills · 202 tokens

product-feed-optimizer

Use when the user asks to "optimize my Shopping feed", "fix product disapprovals", "improve product titles/attributes", or "build feed-driven PMax asset groups"; audits and rewrites the Shopping/Performance Max product feed — title/description patterns, required and recommended attributes, GTIN/availability/price…

aaron-he-zhu/aaron-marketing-skills · 144 tokens

cold-outbound-sequencer

Use when the user asks to "build a B2B cold-outbound sequence", "design reply-triage branching", "plan a domain warmup / sending throttle", or "make my outbound CAN-SPAM / opt-in compliant"; produces a multi-step outbound sequence with reply-triage branches (positive / objection / referral / not-now / opt-out), a…

aaron-he-zhu/aaron-marketing-skills · 172 tokens