content

Legacy fallback for repo-local paper intake when OpenDataLoader PDF cannot convert a source. Prefer opendataloader-paper-intake for PDF-to-Markdown conversion, and use markitdown only as the fallback or for non-PDF sources.

Use when Codex needs to place papers into a package's canonical source tree, convert PDFs to single-file markdown with OpenDataLoader PDF as the primary converter, omit images, fall back to markitdown on failure, and update the package paper index using the tracked paper-intake workflow.

Use when Codex needs to work with the repository's YouTube Data API automation for OAuth setup, authenticated channel inspection, caption download, playlist maintenance, Shorts draft review, or Operating Agents upload and replacement workflows under workflows/skills/youtube-data-api/.

Use when the user wants to work with the alphaXiv CLI to search for papers, inspect paper metadata or full text, manage saved paper or assistant context, or use the authenticated assistant, folders, or comments in terminal-based research workflows.

Use when Codex needs to republish the Operating Agents preface or essay markdown to live Substack, preserve embedded video blocks, keep published links Substack-first, and refresh the local archive after publication.

Use when Codex needs to generate the repository's standard NotebookLM artifact bundle for a notebook, inspect artifact/task status, reuse the established audio/slide/video prompt texts, or upload generated audio back into NotebookLM to recover a transcript.

Use when Codex needs to turn repo slide decks plus narrated audio, transcripts, or captions into long-form YouTube-ready MP4s, draft or verify cue sheets, recover transcript timing, or prepare replacement-course assets before using the YouTube upload skills.

Convert slide PDFs into high-DPI, zero-padded PNG folders for Substack or article publishing. Use when Codex needs to turn a single deck PDF or a directory of PDFs into per-slide images, verify page counts and sample dimensions, and report the output folders. Prefer this skill for macOS workflows that rely on pdfinfo, pdftocairo, and sips.

Use when Codex needs to refresh the tracked public Substack archive, validate the Eleventy mirror, troubleshoot sync or deploy failures, or follow the repo's documented manual-import fallback for publication_strategy_and_archive/.

Use when Codex needs to manage the Operating Agents YouTube pipeline specifically: TL;DR uploads, description cross-links, playlist ordering, caption recovery, or full-course replacement uploads tied to the local Operating Agents metadata.

Use when Codex needs to inspect or maintain the repo's Shorts drafts workflow on YouTube, including listing draft uploads by date, diagnosing playlist contents, checking duplicates, cleaning duplicate playlist entries, or updating draft/private descriptions from a shared template.