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 ErickRamirezAU/claude-skills --skill youtube-idea-findergit clone --depth 1 https://github.com/ErickRamirezAU/claude-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/erickramirezau/claude-skills/youtube-idea-finder)<a href="https://agentmods.dev/skills/erickramirezau/claude-skills/youtube-idea-finder"><img src="https://agentmods.dev/badge/skills/erickramirezau/claude-skills/youtube-idea-finder/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/erickramirezau/claude-skills/youtube-idea-finder"><img src="https://agentmods.dev/badge/skills/erickramirezau/claude-skills/youtube-idea-finder.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 | $0.00179 | $0.02023 |
| Opus 5 | $0.00089 | $0.01012 |
| Sonnet 5 | $0.00036 | $0.00405 |
| Haiku 4.5 | $0.00018 | $0.00202 |
Grade A, and why
youtube-idea-finder 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 11d 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 — 180 lines — stays where its author put it; the contents beside it link to each section on GitHub.
YouTube Idea Finder
Idea and name credit: inspired by Shane Hummus's YouTube videos on channel strategy and finding proven video ideas — this skill automates that "find videos overperforming their channel size" research.
Find videos on a given topic where the view count is large relative to the
channel's subscriber count — a signal that a small or unknown creator produced
something that broke out beyond their usual audience. This uses the YouTube
Data API v3 (search.list, videos.list, channels.list) via a bundled
script, so results are exact numbers straight from the API rather than
scraped or estimated.
Inputs
The only thing the user is required to give you is the search term (the topic/niche). Everything else has a sensible default, and you should state the defaults you're using up front so the user can redirect you if they actually wanted something different:
| Parameter | Default | Notes |
|---|---|---|
| Minimum views | 100,000 | The "overperformance" floor |
| Maximum subscribers | 100,000 | Keeps results to small/mid channels |
| Minimum views : subscribers ratio | 5 : 1 | The core "punching above their weight" signal |
| Number of candidates to find | 5 | Stop once you hit this many |
| Max search pages | 5 | Quota safety cap — see Quota below |
If the user gives you different numbers, use theirs instead. If the script exhausts search results or hits the search-page cap before reaching the requested count, report however many qualifying videos it actually found — don't re-run with ever-looser queries trying to force a full set.
Getting an API key
If the user doesn't already have YOUTUBE_API_KEY set (see Tooling below),
walk them through this rather than assuming they know it:
- Go to the Google Cloud Console and create a project (or pick an existing one).
- Enable the YouTube Data API v3 for that project.
- Go to APIs & Services → Credentials → Create Credentials → API key.
- Optionally restrict the key to the YouTube Data API v3 (recommended, but not required for this to work).
What ships with it
2 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.
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.
- 11d ago First seen · 180 lines · 179 tokens per session scan A 07dba16ceac9
youtube-idea-finder is a skill published in the GitHub repository ErickRamirezAU/claude-skills (2 stars, last pushed 1mo ago), licensed MIT. It adds 179 tokens to every session and 2,023 once invoked, about $0.0009 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
skill-builder
Automatically detect source types and build AI skills using Skill Seekers. Use when the user wants to create skills from documentation, repos, PDFs, videos, or other knowledge sources.
skill-builder
Automatically detect source types and build AI skills using Skill Seekers. Use when the user wants to create skills from documentation, repos, PDFs, videos, or other knowledge sources.
rmm-powershell-scripts
Create and review PowerShell 5.1 scripts specifically for NinjaOne or Action1 RMM deployment. ONLY use when the user explicitly mentions RMM, NinjaOne, Action1, or background agent deployment. Do NOT use for general PowerShell scripting.
rmm-linux-scripts
Create and review bash scripts specifically for NinjaOne or Action1 RMM deployment to Linux servers. ONLY use when the user explicitly mentions RMM, NinjaOne, Action1, or background agent deployment targeting Linux. Do NOT use for general shell scripting.
rmm-macos-scripts
Create and review zsh scripts specifically for NinjaOne or Action1 RMM deployment to macOS endpoints. ONLY use when the user explicitly mentions RMM, NinjaOne, Action1, or background agent deployment targeting Macs. Do NOT use for general shell scripting.
hook-factory
Generate production-ready Claude Code hooks with interactive Q&A, automated installation, and enhanced validation. Supports 10 templates across 7 event types for comprehensive workflow automation.