Web Article Curator Skill

When this skill is invoked via /urlArticle <url>, execute the following 2-step streamlined workflow:

1. Fetch & Stage Article Content (Single-Turn FastMCP):
   • Execute the native FastMCP tool fetch_article_data(url="<url>", download_all_images=True) on the okc server.
   • Features (all returned in a single JSON payload):
     • Pre-flight duplicate check (already_exists and existing_note).
     • Full DOM extraction, concurrent downloads of valid images ($\ge 100\text{px}$) to <VAULT_ROOT>/assets/images/, avatar filtering, CDN sanitization, and automated technical quality scoring (0-100).
     • Inline full article text (when is_truncated == False, up to 50,000 chars) and SQLite graphify_context (suggested_category, author_existing_notes, and matched_wiki_notes with current content).
   • 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.
   • If technical_quality.is_passing is false, output a brief scorecard and confirm with the user before proceeding.
2. Synthesize & Atomically Commit (Hot-Path + Async Background Sync):
   • Format the curated note into the raw/ zone adhering to vault conventions (no YAML, H1 title, blockquote with Processed: DD-MM-YYYY and Tags: #no-read-yet, Key Takeaways, numbered sections, flashcards, glossary, and related wikilinks).
   • Update or create 1-3 high-value wiki/ concept pages using matched_wiki_notes.
   • Commit all notes in a single call using FastMCP commit_curated_note:

     commit_curated_note(
         raw_note_path="dataScienceKnowledgeBase/AI Engineer/raw/<Category>/<Filename>.md",
         raw_content="...",
         wiki_notes={"ConceptName.md": "..."},
         target_kb="dataScienceKnowledgeBase/AI Engineer",
         fast_sync=True,
         async_sync=True
     )

   • Report progress and show the Obsidian URIs to the user.