agentleFS
UXMagicaiUXMagicai/seosorted-skills/skills/youtube-creator-outreach/SKILL.md

youtube-creator-outreach

Skill0 starsChanged 41 days agoMITView on GitHub

Build and manage a list of YouTube creators to partner with or pitch in the user's niche — channels AI engines cite, found and vetted with live channel stats and SEOsorted's YouTube targets. Use when the user asks for YouTube influencer outreach, creator partnerships, sponsored video targets, or which YouTubers to work with.

The file

Files
SKILL.md

YouTube creator outreach

Steps

  1. Find creators that matter for AI search: find_youtube_videos_cited_by_ai with the business's key intents (free). Channels cited across several intents carry the most weight.
  2. Widen the pool: research_youtube operation: "channel_search" with query (free, 20 per hour) and operation: "search_videos" with query (1 keyword lookup credit) for channels ranking on YouTube itself.
  3. Vet each candidate: research_youtube operation: "channel_stats" with channel (URL, @handle or UC… id; free) — subscribers, median views, engagement rate, uploads in the last 30/90 days. For a deeper read, analyze_any_youtube_channel with channel (metadata audit free; profile: true adds content mix and tone for 1 keyword lookup).
  4. Read the existing list: plan_youtube_videos operation: "targets".
  5. Shortlist up to 10 (the target list holds 10): topical fit, cited for buyer intents (not just entertainment), active recently, engagement over raw subscribers. Note the video that made each one relevant.
  6. Save: plan_youtube_videos operation: "set_targets" with targets (channel URLs or @handles; EDITOR). This replaces the list — include the ones you keep. Confirm with the user first.
  7. Draft a pitch per creator referencing their cited video and offering something specific: data, a product to review, an expert interview.

Guardrails

Numbers come from the tools — never invent subscriber counts or contact details. Draft messages for the user to send; never claim anything was sent.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.