菜单
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.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
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.
基于 SOC 职业分类
| name | youtube-operating-agents |
| description | 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 this skill for the series-specific Operating Agents workflow. Prefer it over the broader $youtube-data-api skill when the task is clearly about the Operating Agents course or TL;DR playlists.
workflows/skills/youtube-data-api/references/operating_agents_tldr_metadata.json as the source of truth.workflows/skills/youtube-data-api/scripts/sync_operating_agents_crosslinks.py to plan or apply navigation blocks.workflows/skills/youtube-data-api/scripts/sync_operating_agents_playlist_order.py to compare metadata order with live playlist order.youtube-slide-video-pipeline to produce or verify the rendered MP4s, cue sheets, and caption timing before any replacement upload.workflows/skills/youtube-data-api/scripts/replace_course_video.py or replace_remaining_course_videos.py only after the rendered MP4s and metadata inputs are confirmed.--apply only when the user explicitly wants the write.../../../workflows/youtube-series-operating-agents/README.md: tracked canonical series workflow for metadata, cross-links, order sync, and replacements.../../../workflows/youtube-production/README.md: tracked local production workflow that should be completed before uploads or replacements.../youtube-data-api/references/operating-agents-workflows.md: end-to-end workflow, quota fallback, and replacement sequencing.../youtube-slide-video-pipeline/references/workflow.md: local slide, transcript, cue, and render workflow before upload.../youtube-data-api/references/rollout-lessons.md: constraints recovered from prior Operating Agents YouTube runs.