{
  "title": "Tools for skills and deck-to-video",
  "summary": "Current original documentation for NotebookLM-first video production, two alternatives and the existing Praxis access boundary.",
  "researched_on": "2026-09-13",
  "assistant_guidance": "Read these findings as supporting research. Distinguish documented methods and capabilities from proposed adaptations and untested outcomes. Reading this page does not start the repeat-research task.",
  "research_prompt": "### Verify the tool route for this task\n\nEstablish the actual task and account environment: improving an existing skill or turning a presentation into a playable video. Inspect available capabilities and current official documentation. For a skill, look for the user’s genuine Feedforward Praxis resource and supported skill format; never invent a missing link or substitute an unrelated product. For video, inspect Google NotebookLM source imports and Video Overview first, then suitable direct presentation-to-video alternatives if needed. Verify import types, notes, editing, account restrictions and export; distinguish documented capability from live access and quality actually tested. Cite original links and the date checked, explain the supported route and unresolved access, and stop with a concise research note unless the user also authorizes execution.",
  "examples": [],
  "sources": [
    {
      "id": "source-1",
      "title": "Google: supported sources and imports",
      "url": "https://support.google.com/gemininotebook/answer/16215270?hl=en"
    },
    {
      "id": "source-2",
      "title": "Google: Video Overviews",
      "url": "https://support.google.com/gemininotebook/answer/16454555?hl=en"
    },
    {
      "id": "source-3",
      "title": "Synthesia: Import PowerPoint",
      "url": "https://docs.synthesia.io/docs/import-powerpoint"
    },
    {
      "id": "source-4",
      "title": "HeyGen: PPT/PDF to Video",
      "url": "https://help.heygen.com/en/articles/13007313-ppt-pdf-to-video"
    }
  ],
  "methodology": [
    {
      "title": "Orientation",
      "text": "Checked September 13, 2026. This is targeted product-documentation research for move 018 and move 024, not a live account test or a comparative quality benchmark. Original links are also embedded in the video prompt so it works independently of this file."
    },
    {
      "title": "NotebookLM first",
      "text": "Google’s current source list explicitly includes PowerPoint .pptx, alongside PDF and Google Slides. The activity can accurately start with importing the PowerPoint directly. The prompt checks actual account support and prepares an alternate supported export if necessary. It separately checks important speaker notes rather than assuming everything imported. Google: supported sources and imports (https://support.google.com/gemininotebook/answer/16215270?hl=en).\n\nGoogle documents Studio → Video Overview, customization before generation, playback and downloading the result. The current help pages use the name Gemini Notebook. The instructions retain the familiar NotebookLM name and tell the executing AI to inspect the interface available to the user. Google: Video Overviews (https://support.google.com/gemininotebook/answer/16454555?hl=en).\n\nThe activity treats the output as a generated explanation and verifies its fidelity. Preserving every original slide or a word-perfect script is not established by these sources. Captions require a separate capability check and output review; the draft does not attribute guaranteed caption controls to NotebookLM."
    },
    {
      "title": "Two direct alternatives",
      "text": "Synthesia’s standalone Import PowerPoint flow accepts .pptx, imports editable material and can populate narration from speaker notes. It generates a script from slide text where notes are absent. Original PowerPoint animations do not import. The documented file limits are 1 GB and 150 slides; the prompt checks current limits before use. This standalone route differs from Synthesia Assistant’s file-import workflow. Synthesia: Import PowerPoint (https://docs.synthesia.io/docs/import-powerpoint).\n\nHeyGen documents PPT/PPTX/PDF upload through PPT/PDF to Video, editing and MP4 export. Its speaker-note script and editable-element import options apply to PPT/PPTX, not PDF. Current documented limits are 50 MB and 50 slides; the prompt requires a live limit check. These documents establish available workflows, not superior output quality. HeyGen: PPT/PDF to Video (https://help.heygen.com/en/articles/13007313-ppt-pdf-to-video)."
    },
    {
      "title": "Praxis and capability boundaries",
      "text": "The approved move 017 entry names Feedforward’s Praxis skill-writing skill and deliberately retains a missing-link placeholder. Narrow public searches for Feedforward Praxis and Feedforward skill-writing did not establish a verified resource URL. No unrelated Praxis product is substituted. move 018 starts with the requested suggestion, has the executing AI inspect actual available Praxis and other skill-writing tools, and continues through the LLM route when unavailable. It invents neither a URL nor a Praxis interface.\n\nThe capability-probing, reviewed-copy comparison, custom LLM rendering trial and guided user handoffs are authored workflow recommendations. They require inspecting real access and outputs when the activity runs; this research did not execute them. move 110 similarly makes actual learning-medium production and scheduling contingent on supported tools and authorized delivery, without claiming any product automatically provides the whole experience."
    },
    {
      "title": "How this research was done",
      "text": "One author performed bounded public searches, opened Google, Synthesia and HeyGen official documentation, and inspected the existing approved Praxis entry. No independent tool comparison, subscription trial, media generation, account inspection or Praxis functionality test occurred. The source list and video page were read together to check the exact PowerPoint-to-Video Overview sequence; alternatives were retained only when official documentation explicitly described presentation import and video production."
    }
  ],
  "schema_version": 5,
  "id": "024",
  "shared_ai_guidance": "These are general instructions, not a description of this user's particular AI system, tools, access, or circumstances. Adapt the method to the user's goal and the capabilities you can actually use, while preserving the activity's essential sequence, review points, and intended result.\n\n### Start with the activity and the user's context\n\nRead the complete activity and guide the user through it. Use the activity prompt yourself; the user does not need to paste it again. Keep the responsibilities of the user, the AI, and any colleague clear.\n\nBegin with what the user has already supplied. Establish the intended result and resolve missing context through focused questions when needed. Work within the activity's stated scope, permissions, required confirmations, and stopping points, including any deliberate order for introducing information. Make progress with the available information and reasonable, clearly identified assumptions where the activity allows them.\n\n### Check the capabilities needed for this work\n\nInspect relevant available tools, connectors, and data. Use small, relevant, non-destructive checks to establish whether necessary access or a capability actually works. Naming a product does not establish access to it. Let this activity determine what needs checking; do not impose a universal preliminary questionnaire or a full system audit.\n\nWhen useful access is missing:\n\n- Explain what you cannot reach and how that material would help.\n- Investigate practical setup, connection, export, or other access alternatives before asking the user to gather material or troubleshoot.\n- If progress depends on access, request only the specific user action or permission needed to enable it or provide the material another way. Continue useful independent work while awaiting the response.\n- Offer to walk the user through an export or upload. Welcome files, links, copied text, rough notes, or an interview as supported by your system and the activity, and use the best available route. If the missing access is optional, continue with what is available.\n\n### Ask focused questions and respect the answers\n\nAsk questions only when necessary to complete the work well or satisfy the activity's required review points. Build on answers already supplied. Ask one question at a time, or a small group of closely related questions. Wait on work that depends on the answer, and continue useful work that does not. Explain unfamiliar language with examples where helpful.\n\nConfirm answers or decisions you supply on the user's behalf before treating them as the user's final answers or decisions. This does not require separate approval of every sourced finding; follow the activity's specific review requirements.\n\n### Keep evidence and independent contributions distinct\n\nDistinguish evidence, inference, and missing information. Check your work against the source material.\n\nUse independent agents when your system actually supports delegation and independent investigation or review would improve the work:\n\n- Give each agent a bounded brief and the context appropriate to its role.\n- Keep discovery independent until synthesis where the activity requires it. Preserve any requirement for the user or colleagues to contribute before seeing other explanations.\n- Follow the activity's stated fallback and any required confirmation when independent agents or fresh contexts are unavailable. Preserve reviewer isolation where required; describe shared-context or sequential passes accurately.\n\n### Produce, check, and revise the result\n\nDo the substantive investigation and production. Carry the activity through to the most complete, usable result within its scope, rather than ending with a plan or handing the main work back to the user. When missing information does not prevent useful work, proceed with clearly identified assumptions where the activity permits them.\n\nCheck the result against the activity's completion criteria. At each substantive delivery, state what is complete and any material unfinished work, assumptions, helpful missing information, and remaining uncertainty. Explain how these affect what the user can use, and help the user revise the result.\n\nPreserve the activity's stopping point. Do not turn a rehearsal, investigation, or test-design activity into execution that the user has not authorized.",
  "effective_research_prompt": "These are general instructions, not a description of this user's particular AI system, tools, access, or circumstances. Adapt the method to the user's goal and the capabilities you can actually use, while preserving the activity's essential sequence, review points, and intended result.\n\n### Start with the activity and the user's context\n\nRead the complete activity and guide the user through it. Use the activity prompt yourself; the user does not need to paste it again. Keep the responsibilities of the user, the AI, and any colleague clear.\n\nBegin with what the user has already supplied. Establish the intended result and resolve missing context through focused questions when needed. Work within the activity's stated scope, permissions, required confirmations, and stopping points, including any deliberate order for introducing information. Make progress with the available information and reasonable, clearly identified assumptions where the activity allows them.\n\n### Check the capabilities needed for this work\n\nInspect relevant available tools, connectors, and data. Use small, relevant, non-destructive checks to establish whether necessary access or a capability actually works. Naming a product does not establish access to it. Let this activity determine what needs checking; do not impose a universal preliminary questionnaire or a full system audit.\n\nWhen useful access is missing:\n\n- Explain what you cannot reach and how that material would help.\n- Investigate practical setup, connection, export, or other access alternatives before asking the user to gather material or troubleshoot.\n- If progress depends on access, request only the specific user action or permission needed to enable it or provide the material another way. Continue useful independent work while awaiting the response.\n- Offer to walk the user through an export or upload. Welcome files, links, copied text, rough notes, or an interview as supported by your system and the activity, and use the best available route. If the missing access is optional, continue with what is available.\n\n### Ask focused questions and respect the answers\n\nAsk questions only when necessary to complete the work well or satisfy the activity's required review points. Build on answers already supplied. Ask one question at a time, or a small group of closely related questions. Wait on work that depends on the answer, and continue useful work that does not. Explain unfamiliar language with examples where helpful.\n\nConfirm answers or decisions you supply on the user's behalf before treating them as the user's final answers or decisions. This does not require separate approval of every sourced finding; follow the activity's specific review requirements.\n\n### Keep evidence and independent contributions distinct\n\nDistinguish evidence, inference, and missing information. Check your work against the source material.\n\nUse independent agents when your system actually supports delegation and independent investigation or review would improve the work:\n\n- Give each agent a bounded brief and the context appropriate to its role.\n- Keep discovery independent until synthesis where the activity requires it. Preserve any requirement for the user or colleagues to contribute before seeing other explanations.\n- Follow the activity's stated fallback and any required confirmation when independent agents or fresh contexts are unavailable. Preserve reviewer isolation where required; describe shared-context or sequential passes accurately.\n\n### Produce, check, and revise the result\n\nDo the substantive investigation and production. Carry the activity through to the most complete, usable result within its scope, rather than ending with a plan or handing the main work back to the user. When missing information does not prevent useful work, proceed with clearly identified assumptions where the activity permits them.\n\nCheck the result against the activity's completion criteria. At each substantive delivery, state what is complete and any material unfinished work, assumptions, helpful missing information, and remaining uncertainty. Explain how these affect what the user can use, and help the user revise the result.\n\nPreserve the activity's stopping point. Do not turn a rehearsal, investigation, or test-design activity into execution that the user has not authorized.\n\n### Verify the tool route for this task\n\nEstablish the actual task and account environment: improving an existing skill or turning a presentation into a playable video. Inspect available capabilities and current official documentation. For a skill, look for the user’s genuine Feedforward Praxis resource and supported skill format; never invent a missing link or substitute an unrelated product. For video, inspect Google NotebookLM source imports and Video Overview first, then suitable direct presentation-to-video alternatives if needed. Verify import types, notes, editing, account restrictions and export; distinguish documented capability from live access and quality actually tested. Cite original links and the date checked, explain the supported route and unresolved access, and stop with a concise research note unless the user also authorizes execution.",
  "status": "companion",
  "urls": {
    "page": "https://bingo.feedforward-collective.com/moves/024",
    "markdown": "https://bingo.feedforward-collective.com/moves/024/instructions.md",
    "json": "https://bingo.feedforward-collective.com/moves/024/instructions.json",
    "record": "https://bingo.feedforward-collective.com/moves/024/record.json",
    "qrPng": "https://bingo.feedforward-collective.com/moves/024/qr.png",
    "qrSvg": "https://bingo.feedforward-collective.com/moves/024/qr.svg",
    "research": "https://bingo.feedforward-collective.com/moves/024/research",
    "researchMarkdown": "https://bingo.feedforward-collective.com/moves/024/research/resources.md",
    "researchJson": "https://bingo.feedforward-collective.com/moves/024/research/resources.json",
    "researchText": "https://bingo.feedforward-collective.com/moves/024/research/resources.txt",
    "researchPrompt": "https://bingo.feedforward-collective.com/moves/024/research/research-prompt.txt"
  }
}