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 skills add deeployCO/youtube-seo-skills --skill youtube-seo-videogit clone --depth 1 https://github.com/deeployCO/youtube-seo-skillsWrote 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/deeployco/youtube-seo-skills/youtube-seo-video)<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.
<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>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 5.1 | $0.00082 | $0.02585 |
| Opus 5 | $0.00041 | $0.01293 |
| Sonnet 5 | $0.00016 | $0.00517 |
| Haiku 4.5 | $0.00008 | $0.00259 |
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.
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)
- WebFetch the watch URL → title, description (partial), view/like, duration, upload date, channel, visible chapters
- yt-dlp (
scripts/fetch_video.pyor direct call) → full JSON metadata, tags, full description, chapters, thumbnails, captions - YouTube Data API (if key) →
videos.list?part=snippet,statistics, contentDetails,topicDetails,status,player,liveStreamingDetailsandcaptions.list+captions.download(if OAuth) - Transcript: prefer manual captions > auto-captions > Whisper transcription from audio stream
- Studio CSV (user-provided): retention curve, traffic sources, CTR by source, impressions, audience tab, real-time first-24h curve
- Audio loudness:
ffmpeg -i audio.m4a -af loudnorm=print_format=json -f null -→ integrated LUFS, true peak - Thumbnail file: download for analysis via
scripts/analyze_thumbnail.py - 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×.
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.
- 13d ago First seen · 248 lines · 82 tokens per session scan A 0ef45f6b999a
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.
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.
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.
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.
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…
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…
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…