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 sergebulaev/youtube-skills --skill youtube-skillsgit clone --depth 1 https://github.com/sergebulaev/youtube-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/sergebulaev/youtube-skills/youtube-skills)<a href="https://agentmods.dev/skills/sergebulaev/youtube-skills/youtube-skills"><img src="https://agentmods.dev/badge/skills/sergebulaev/youtube-skills/youtube-skills/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/sergebulaev/youtube-skills/youtube-skills"><img src="https://agentmods.dev/badge/skills/sergebulaev/youtube-skills/youtube-skills.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00105 | $0.02359 |
| Opus 5.5 | $0.00042 | $0.00944 |
| Sonnet 5.5 | $0.00021 | $0.00472 |
| Haiku 4.5 | $0.00011 | $0.00236 |
Grade A, and why
youtube-marketing 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 12d 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 — 174 lines — stays where its author put it; the contents beside it link to each section on GitHub.
YouTube Marketing Skills
A bundle of 9 focused skills for YouTube content ops in 2026, covering both long-form and YouTube Shorts. Each skill is single-purpose, follows the draft then approval then publish pattern, and uses the Publora API for uploading and scheduling the video you supply.
When to use this bundle
- Writing high-CTR titles (curiosity, number, how-I, comparison) with A/B variants -> use
yt-title-optimizer - Writing the description (first-150-char hook, chapters, keywords, links) -> use
yt-description-writer - Scripting the first 30 seconds for retention (or the first 3 seconds of a Short) -> use
yt-hook-scripter - Briefing a thumbnail (text overlay, face/emotion, contrast) plus the upload flow -> use
yt-thumbnail-brief - Writing a community-tab post or poll -> use
yt-community-post-writer - Planning a week of uploads (long-form vs Shorts mix, title/thumbnail pairing) -> use
yt-content-planner - Repurposing off-platform content (a blog post, thread, or LinkedIn post) into a YouTube community post or a video brief -> use
yt-repurposer - Auditing and rewriting the channel page (banner, trailer, About, playlists, section order) to convert viewers into subscribers -> use
yt-channel-optimizer - Reading your audience from the comments (who commented, themes, superfans, trending) -> use
yt-audience-insights
Core pattern
Every action-taking skill follows three steps:
- Parse the input. If the user gives a YouTube URL, the skill uses
lib/url_parser.pyto extract the video id, Short id, channel, or handle. - Draft the content. The skill applies 2026 research (title and hook formulas, CTR x retention heuristics, thumbnail principles, voice rules) and shows the draft to the user.
- Wait for approval. The user replies "publish", "yes", or suggests edits. Only after explicit approval does the skill upload and schedule via Publora.
Why YouTube is video-first (read this once)
What ships with it
45 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- .codex-plugin/plugin.json 2.0 KB
- .env.example 2.7 KB
- assets/hero.png 3934 KB
- assets/icon.svg 768 B
- assets/social-preview.jpg 58 KB
- lib/__init__.py 1.1 KB runs code
- lib/_env.py 2.2 KB runs code
- lib/approval.py 2.0 KB runs code
- lib/backend_selector.py 17 KB runs code
- lib/pixfaro_client.py 9.1 KB runs code
- lib/publora_client.py 17 KB runs code
- lib/url_parser.py 5.4 KB runs code
- lib/youtube_client.py 10 KB runs code
- LICENSE 1.0 KB
- README.md 21 KB
- references/algorithm-heuristics.md 8.5 KB
- references/hook-formulas.md 16 KB
- references/thumbnail-principles.md 6.5 KB
- references/untrusted-content.md 2.8 KB
- references/voice-profile.md 1.7 KB
- references/voice-rules.md 6.1 KB
- requirements.txt 38 B
- scripts/check_frontmatter.py 3.8 KB runs code
- scripts/check_no_secrets.py 4.7 KB runs code
- scripts/check_security_boundaries.py 3.8 KB runs code
- scripts/check_text_encoding.py 3.4 KB runs code
- scripts/check_untrusted_rule.py 3.1 KB runs code
- skills/yt-audience-insights/SKILL.md 5.5 KB
- skills/yt-channel-optimizer/SKILL.md 7.2 KB
- skills/yt-community-post-writer/references/post-types.md 2.0 KB
- skills/yt-community-post-writer/SKILL.md 6.3 KB
- skills/yt-community-post-writer/sub-skills/illustration.md 3.8 KB
- skills/yt-community-post-writer/sub-skills/voice-profile.md 2.1 KB
- skills/yt-content-planner/references/example-week.md 3.0 KB
- skills/yt-content-planner/references/pillars-framework.md 3.0 KB
- skills/yt-content-planner/SKILL.md 5.0 KB
- skills/yt-description-writer/references/description-template.md 2.6 KB
- skills/yt-description-writer/SKILL.md 5.8 KB
- skills/yt-hook-scripter/references/retention-beats.md 3.3 KB
- skills/yt-hook-scripter/SKILL.md 6.4 KB
- skills/yt-repurposer/SKILL.md 8.5 KB
- skills/yt-thumbnail-brief/references/brief-template.md 2.7 KB
- skills/yt-thumbnail-brief/SKILL.md 5.6 KB
- skills/yt-title-optimizer/references/title-checklist.md 2.2 KB
- skills/yt-title-optimizer/SKILL.md 5.2 KB
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.
- 12d ago Changed · +9 lines ebf05bb931d0
- 1mo ago Changed 066d6e7393e9
- 1mo ago Changed 5541c4c5605c
- 1mo ago First seen · 165 lines · 105 tokens per session scan A dbc0d21c1b53
youtube-marketing is a skill published in the GitHub repository sergebulaev/youtube-skills (74 stars, last pushed 6d ago), licensed MIT. It adds 105 tokens to every session and 2,359 once invoked, about $0.0004 per session on Opus 5.5. 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
x-humanizer
Remove the AI tells human readers react to in a tweet or thread: 2026 vocabulary by density, reveal bridges, staccato stacks, stacked triads, performed sincerity. Also --mode audit (280-char fit and format), --mode profile (learns how you write) and --mode interview (fills your Story Bank: the numbers, turning points…
x-marketing
Plan, draft, audit, and publish posts and threads for X (Twitter). Use when the user wants to write a single tweet or an auto-numbered thread, build a long-form tweetstorm, remove AI tells from a draft, reverse-engineer the hook from a viral tweet, draft a reply or quote tweet, or plan a week of X content. Tweets and…
tt-humanizer
Remove the AI-script tells viewers hear in a TikTok spoken script and caption: 2026 vocabulary by density, reveal bridges, staccato stacks, stacked triads, performed sincerity, written-not-spoken phrasing, "hey guys" filler; caps em dashes. Includes --mode audit pre-film check (hook, completion design, caption fit)…
tiktok-marketing
Plan, script, caption, and publish short-form video for TikTok. Use when the user wants to write the first 1-3 second hook (spoken line plus on-screen text), draft a caption under 2,200 chars with TikTok settings and hashtags, ride a trending sound without being cringe, strip AI tells from a spoken script to sound…
fb-humanizer
Remove the AI tells readers react to in a Facebook Page post: 2026 vocabulary by density, reveal bridges, staccato stacks, stacked triads, announcement auto-pilot. Also --mode audit (under-80 sweet spot, hook, engagement bait), --mode profile (learns how you write) and --mode interview (fills your Story Bank: the…
facebook-marketing
Plan, draft, audit, and publish posts for a Facebook Page. Use when the user wants to write a short punchy Page post or a longer story post, remove AI tells from a draft, reverse-engineer the hook from a high-share Page post, draft replies to comments on their Page, or plan a week of Facebook Page content. Page posts…