菜单
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.
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。
基于 SOC 职业分类
| name | notebooklm-artifact-bundle |
| description | 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 the repo-local NotebookLM workflow in .venv/bin/notebooklm. This skill is for repeated artifact generation and transcript recovery, not for generic NotebookLM brainstorming.
.venv/bin/notebooklm..venv/bin/notebooklm auth check --test.git diff --name-status for deleted assets and git diff -- <draft> | rg '^-!\[' for removed image embeds.source fulltext, save with -o <path> instead of shell redirection. The terminal view can be a preview and may not contain the full transcript.deep-dive, longdetailedmore, hardmore, hardexplainer../../../workflows/notebooklm-artifacts/README.md: tracked canonical artifact-generation and transcript-recovery workflow.references/workflows.md: notebook resolution, standard bundle generation, polling, and transcript round-trip.references/prompts.md: canonical prompt files and the voice constraints they encode.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 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.