agentleFS
UXMagicaiUXMagicai/seosorted-skills/skills/youtube-citation-strategy/SKILL.md

youtube-citation-strategy

Skill0 starsChanged 41 days agoMITView on GitHub

Find which YouTube videos AI engines and Google AI Overviews cite for the user's topics, read their transcripts, size the YouTube competition, and plan and script videos the brand can make to be cited instead, with SEOsorted. Use when the user asks about YouTube SEO for AI search, which videos ChatGPT or AI Overviews cite, video content strategy, YouTube topics, or writing YouTube scripts.

The file

Files
SKILL.md

YouTube citation strategy

1. What gets cited

  1. Pick 3–10 search intents the business should own (from keyword-research or the AI visibility gap list).
  2. find_youtube_videos_cited_by_ai with intents, max_videos_per_intent: 3, transcript_mode: "summary" ("full" only for a few videos in depth), country: "auto". Free.
  3. Per intent note: whether an AI Overview appeared and cited videos, which channels win, length and format, what the transcripts cover that a written article does not.
  4. Size each intent: research_youtube operation: "keyword_research" with query (the intent) — Google volume plus a low/medium/high competition reading of the YouTube results (1 keyword lookup credit). For a winning video, research_youtube operation: "video_details" with video, transcript: true (free).

2. Plan

One row per video to make: intent, angle that beats the cited video, format, target keyword, competition level. Prefer intents where AI cites video and competition is low or medium.

3. Topics and scripts (needs a connected YouTube channel)

plan_youtube_videos:

  • operation: "strategy" and "topics" for the existing plan; "starter_topics" works without a channel.
  • operation: "add_topic" with title, target_keyword, format and brief per planned video (EDITOR); "suggest_titles" with target_keyword for title options.
  • operation: "write_script" with topic_id — background job (poll check_job_status), one YouTube-script credit. Say so before starting.
  • operation: "read_script" with script_id to review: citation-readiness checks, YouTube title, description, tags.
  • operation: "edit_script" with script_id and instruction for AI edits (at least 1 AI credit, more if it researches); "update_script" with body, seo_title, seo_description, seo_tags and base_version for your own edits (free).
  • operation: "export_script" with export_format: "md" (or "txt" for a teleprompter).
  • delete_script / delete_topics only when the user asks.

Guardrails

Distinguish the four AI Overview outcomes the tool reports (cited, no AI Overview, uncited, lookup failed). A failed lookup is not a finding — retry. Never claim a video is cited without the tool showing it. YouTube volumes are Google web search volumes; say so.

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.