agentleFS
c-ibarrac-ibarra/ObsidianKnowledgeCurator/.agents/skills/okc-urlYoutube/SKILL.md

okc-urlYoutube

Skill0 starsChanged 44 days agoMITView on GitHub

Downloads transcript, curates source note, compiles concepts, and syncs vault.

The file

We split this skill into the rules it gives an agent

4 rules. About 0 are common, 0 are distinctive, and 4 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈0

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 4

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    When this skill is invoked via /urlYoutube <url> or /okc-urlYoutube <url>, execute the following strict 2-call Turbo Workflow:

    line 9
  2. Very specific:

    Zero Extra Read Turns: If is_truncated is False, do not call read_file on temp/fetched_data.txt or temp/fetched_data.json, and do not run …

    line 18
  3. Very specific:

    Update or create 1-3 high-value wiki/ concept pages using the inline matched_wiki_notes context.

    line 22
  4. Very specific:

    Commit all notes in a single call using FastMCP commit_curated_note:

    line 23

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

YouTube Video Curator Skill

When this skill is invoked via /urlYoutube <url> or /okc-urlYoutube <url>, execute the following strict 2-call Turbo Workflow:

  1. Fetch & Stage YouTube Content (Single-Turn FastMCP):
    • Execute the native FastMCP tool fetch_youtube_data(url_or_id="<url>") on the okc server.
    • Features (all returned in a single JSON payload):
      • Pre-flight duplicate check (already_exists and existing_note).
      • Concurrent fast metadata (oembed/HTML + yt-dlp fallback) & transcript extraction.
      • Inline full transcript (when is_truncated == False, up to 50,000 chars).
      • SQLite context (graphify_context): suggested_category, author_existing_notes ([[wikilinks]]), and matched_wiki_notes (including current markdown content of the top matched wiki/ concept pages).
    • Zero Extra Read Turns: If is_truncated is False, do not call read_file on temp/fetched_data.txt or temp/fetched_data.json, and do not run extra find_notes queries unless a specific concept is missing from matched_wiki_notes.
  2. Synthesize & Atomically Commit (Hot-Path + Async Background Sync):
    • Format the curated note in the raw/ zone following vault conventions (no YAML, H1 title, blockquote with Processed: DD-MM-YYYY and Tags: #no-read-yet, Key Takeaways, numbered sections, flashcards, glossary, related wikilinks).
    • Update or create 1-3 high-value wiki/ concept pages using the inline matched_wiki_notes context.
    • Commit all notes in a single call using FastMCP commit_curated_note:
      commit_curated_note(
          raw_note_path="dataScienceKnowledgeBase/AI Engineer/raw/<Category>/<Channel> — <Title>.md",
          raw_content="...",
          wiki_notes={"ConceptName.md": "..."},
          target_kb="dataScienceKnowledgeBase/AI Engineer",
          fast_sync=True,
          async_sync=True
      )
    • commit_curated_note performs a <25ms surgical SQLite upsert and link check synchronously, while spawning scripts/async_post_commit.py in a detached background process to rebuild the Master Plan and update Graphify without blocking your response.
    • Report progress and show the clickable file link and Obsidian URI to the user.

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.