{
  "schemaVersion": "1.0",
  "item": {
    "slug": "explainer-video-guide",
    "name": "Explainer Video Guide",
    "source": "tencent",
    "type": "skill",
    "category": "内容创作",
    "sourceUrl": "https://clawhub.ai/okaris/explainer-video-guide",
    "canonicalUrl": "https://clawhub.ai/okaris/explainer-video-guide",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadMode": "redirect",
    "downloadUrl": "/downloads/explainer-video-guide",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=explainer-video-guide",
    "sourcePlatform": "tencent",
    "targetPlatform": "OpenClaw",
    "installMethod": "Manual import",
    "extraction": "Extract archive",
    "prerequisites": [
      "OpenClaw"
    ],
    "packageFormat": "ZIP package",
    "includedAssets": [
      "SKILL.md"
    ],
    "primaryDoc": "SKILL.md",
    "quickSetup": [
      "Download the package from Yavira.",
      "Extract the archive and review SKILL.md first.",
      "Import or place the package into your OpenClaw setup."
    ],
    "agentAssist": {
      "summary": "Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually.",
      "steps": [
        "Download the package from Yavira.",
        "Extract it into a folder your agent can access.",
        "Paste one of the prompts below and point your agent at the extracted folder."
      ],
      "prompts": [
        {
          "label": "New install",
          "body": "I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Tell me what you changed and call out any manual steps you could not complete."
        },
        {
          "label": "Upgrade existing",
          "body": "I downloaded an updated skill package from Yavira. Read SKILL.md from the extracted folder, compare it with my current installation, and upgrade it while preserving any custom configuration unless the package docs explicitly say otherwise. Summarize what changed and any follow-up checks I should run."
        }
      ]
    },
    "sourceHealth": {
      "source": "tencent",
      "slug": "explainer-video-guide",
      "status": "healthy",
      "reason": "direct_download_ok",
      "recommendedAction": "download",
      "checkedAt": "2026-04-29T15:24:57.655Z",
      "expiresAt": "2026-05-06T15:24:57.655Z",
      "httpStatus": 200,
      "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=explainer-video-guide",
      "contentType": "application/zip",
      "probeMethod": "head",
      "details": {
        "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=explainer-video-guide",
        "contentDisposition": "attachment; filename=\"explainer-video-guide-0.1.5.zip\"",
        "redirectLocation": null,
        "bodySnippet": null,
        "slug": "explainer-video-guide"
      },
      "scope": "item",
      "summary": "Item download looks usable.",
      "detail": "Yavira can redirect you to the upstream package for this item.",
      "primaryActionLabel": "Download for OpenClaw",
      "primaryActionHref": "/downloads/explainer-video-guide"
    },
    "validation": {
      "installChecklist": [
        "Use the Yavira download entry.",
        "Review SKILL.md after the package is downloaded.",
        "Confirm the extracted package contains the expected setup assets."
      ],
      "postInstallChecks": [
        "Confirm the extracted package includes the expected docs or setup files.",
        "Validate the skill or prompts are available in your target agent workspace.",
        "Capture any manual follow-up steps the agent could not complete."
      ]
    },
    "downloadPageUrl": "https://openagent3.xyz/downloads/explainer-video-guide",
    "agentPageUrl": "https://openagent3.xyz/skills/explainer-video-guide/agent",
    "manifestUrl": "https://openagent3.xyz/skills/explainer-video-guide/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/explainer-video-guide/agent.md"
  },
  "agentAssist": {
    "summary": "Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually.",
    "steps": [
      "Download the package from Yavira.",
      "Extract it into a folder your agent can access.",
      "Paste one of the prompts below and point your agent at the extracted folder."
    ],
    "prompts": [
      {
        "label": "New install",
        "body": "I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Tell me what you changed and call out any manual steps you could not complete."
      },
      {
        "label": "Upgrade existing",
        "body": "I downloaded an updated skill package from Yavira. Read SKILL.md from the extracted folder, compare it with my current installation, and upgrade it while preserving any custom configuration unless the package docs explicitly say otherwise. Summarize what changed and any follow-up checks I should run."
      }
    ]
  },
  "documentation": {
    "source": "clawhub",
    "primaryDoc": "SKILL.md",
    "sections": [
      {
        "title": "Explainer Video Guide",
        "body": "Create explainer videos from script to final cut via inference.sh CLI."
      },
      {
        "title": "Quick Start",
        "body": "curl -fsSL https://cli.inference.sh | sh && infsh login\n\n# Generate a scene for an explainer\ninfsh app run google/veo-3-1-fast --input '{\n  \"prompt\": \"Clean motion graphics style animation, abstract data flowing between connected nodes, blue and white color scheme, professional corporate aesthetic, smooth transitions\"\n}'\n\nInstall note: The install script only detects your OS/architecture, downloads the matching binary from dist.inference.sh, and verifies its SHA-256 checksum. No elevated permissions or background processes. Manual install & verification available."
      },
      {
        "title": "Problem-Agitate-Solve (PAS) — 60 seconds",
        "body": "SectionDurationContentWord CountProblem10sState the pain point the viewer has~25 wordsAgitate10sShow why it's worse than they think~25 wordsSolution15sIntroduce your product/idea~35 wordsHow It Works20sShow 3 key steps or features~50 wordsCTA5sOne clear next action~12 words"
      },
      {
        "title": "Before-After-Bridge (BAB) — 90 seconds",
        "body": "SectionDurationContentBefore15sShow the current frustrating stateAfter15sShow the ideal outcomeBridge40sExplain how your product gets them thereSocial Proof10sQuick stat or testimonialCTA10sClear next step"
      },
      {
        "title": "Feature Spotlight — 30 seconds (social)",
        "body": "SectionDurationContentHook3sSurprising fact or questionFeature15sShow one feature solving one problemResult7sThe outcome/benefitCTA5sTry it / Learn more"
      },
      {
        "title": "Pacing Rules",
        "body": "Content TypeWords Per MinuteNotesStandard narration150 wpmConversational paceComplex/technical120 wpmAllow processing timeEnergetic/social170 wpmFaster for short-formChildren's content100 wpmClear and slow\n\nKey rule: 1 scene per key message. Don't pack multiple ideas into one visual."
      },
      {
        "title": "Scene Duration Guidelines",
        "body": "Establishing shot: 3-5 seconds\nFeature demonstration: 5-8 seconds\nText/stat on screen: 3-4 seconds (must be readable)\nTransition: 0.5-1 second\nCTA screen: 3-5 seconds"
      },
      {
        "title": "Scene Types",
        "body": "# Product in context\ninfsh app run google/veo-3-1-fast --input '{\n  \"prompt\": \"Clean product demonstration video, hands typing on a laptop showing a dashboard interface, bright modern office, soft natural lighting, professional\"\n}'\n\n# Abstract concept visualization\ninfsh app run bytedance/seedance-1-5-pro --input '{\n  \"prompt\": \"Abstract motion graphics, colorful data streams connecting floating geometric shapes, smooth fluid animation, dark background with glowing elements, tech aesthetic\"\n}'\n\n# Lifestyle/outcome shot\ninfsh app run google/veo-3-1-fast --input '{\n  \"prompt\": \"Happy person relaxing on couch with laptop, smiling at screen, bright airy living room, warm afternoon light, satisfied customer feeling, lifestyle commercial style\"\n}'\n\n# Before/after comparison\ninfsh app run falai/flux-dev-lora --input '{\n  \"prompt\": \"Split screen comparison, left side cluttered messy desk with papers and stress, right side clean organized minimalist workspace, dramatic difference, clean design\"\n}'"
      },
      {
        "title": "Image-to-Video for Scenes",
        "body": "# Generate a still frame first\ninfsh app run falai/flux-dev-lora --input '{\n  \"prompt\": \"Professional workspace with glowing holographic interface, futuristic but clean, blue accent lighting\"\n}'\n\n# Animate it\ninfsh app run falai/wan-2-5-i2v --input '{\n  \"prompt\": \"Gentle camera push in, holographic elements subtly floating and rotating, soft ambient light shifts\",\n  \"image\": \"path/to/workspace-still.png\"\n}'"
      },
      {
        "title": "Script Writing Tips",
        "body": "Short sentences. Max 15 words per sentence.\nActive voice. \"You can track your data\" not \"Your data can be tracked.\"\nConversational tone. Read it aloud — if it sounds stiff, rewrite.\nOne idea per sentence. One sentence per visual beat."
      },
      {
        "title": "Generating Voiceover",
        "body": "# Professional narration with Dia TTS\ninfsh app run falai/dia-tts --input '{\n  \"prompt\": \"[S1] Tired of spending hours on reports that nobody reads? There is a better way. Meet DataFlow. It turns your raw data into visual stories... in seconds. Just connect your source, pick a template, and share. Try DataFlow free today.\"\n}'"
      },
      {
        "title": "Pacing Control in TTS",
        "body": "TechniqueEffectExamplePeriod .Medium pause\"This changes everything. Here's how.\"Ellipsis ...Long pause (dramatic)\"And the result... was incredible.\"Comma ,Short pause\"Fast, simple, powerful.\"Exclamation !Emphasis/energy\"Start building today!\"Question ?Rising intonation\"What if there was a better way?\""
      },
      {
        "title": "Background Music Guidelines",
        "body": "Volume: 20-30% under narration (duck 6-12dB when voice plays)\nStyle: match the brand tone (corporate = ambient electronic, startup = upbeat indie)\nStructure: intro swell (first 3s) -> subtle loop under narration -> swell at CTA\nNo vocals: instrumental only under narration\n\n# Generate background music\ninfsh app run <music-gen-app> --input '{\n  \"prompt\": \"upbeat corporate background music, modern electronic, 90 BPM, positive and professional, no vocals, suitable for product explainer video\"\n}'"
      },
      {
        "title": "Full Production Workflow",
        "body": "# 1. Generate voiceover\ninfsh app run falai/dia-tts --input '{\n  \"prompt\": \"[S1] Your script here...\"\n}'\n\n# 2. Generate scene visuals (in parallel)\ninfsh app run google/veo-3-1-fast --input '{\"prompt\": \"scene 1 description\"}' --no-wait\ninfsh app run google/veo-3-1-fast --input '{\"prompt\": \"scene 2 description\"}' --no-wait\ninfsh app run google/veo-3-1-fast --input '{\"prompt\": \"scene 3 description\"}' --no-wait\n\n# 3. Merge scenes into sequence\ninfsh app run infsh/media-merger --input '{\n  \"media\": [\"scene1.mp4\", \"scene2.mp4\", \"scene3.mp4\"]\n}'\n\n# 4. Add voiceover to video\ninfsh app run infsh/video-audio-merger --input '{\n  \"video\": \"merged-scenes.mp4\",\n  \"audio\": \"voiceover.mp3\"\n}'\n\n# 5. Add captions\ninfsh app run infsh/caption-videos --input '{\n  \"video\": \"final-with-audio.mp4\",\n  \"caption_file\": \"captions.srt\"\n}'"
      },
      {
        "title": "Video Length by Format",
        "body": "FormatLengthPlatformSocial teaser15-30sTikTok, Instagram Reels, YouTube ShortsProduct demo60-90sWebsite, landing pageFeature explainer90-120sYouTube, emailTutorial/walkthrough2-5minYouTube, help centerInvestor pitch video2-3minPitch deck supplement"
      },
      {
        "title": "Transition Types",
        "body": "TransitionWhen to UseEffectCutDefault between related scenesClean, professionalDissolve/CrossfadeTime passing, mood shiftSoft, contemplativeWipeNew topic or sectionClear separationZoom/PushDrilling into detailFocus attentionMatch cutVisual similarity between scenesClever, memorable"
      },
      {
        "title": "Common Mistakes",
        "body": "MistakeProblemFixScript too wordyVoiceover rushed, viewer overwhelmedCut to 150 wpm maxNo hook in first 3sViewers leave immediatelyStart with the problem or surprising statVisuals lag narrationConfusing disconnectVisuals should match or slightly precede wordsBackground music too loudCan't hear narrationDuck music 6-12dB under voiceNo captions85% of social video watched silentAlways add captionsToo many ideasViewer retains nothingOne core message per video"
      },
      {
        "title": "Related Skills",
        "body": "npx skills add inference-sh/skills@ai-video-generation\nnpx skills add inference-sh/skills@video-prompting-guide\nnpx skills add inference-sh/skills@text-to-speech\nnpx skills add inference-sh/skills@prompt-engineering\n\nBrowse all apps: infsh app list"
      }
    ],
    "body": "Explainer Video Guide\n\nCreate explainer videos from script to final cut via inference.sh CLI.\n\nQuick Start\ncurl -fsSL https://cli.inference.sh | sh && infsh login\n\n# Generate a scene for an explainer\ninfsh app run google/veo-3-1-fast --input '{\n  \"prompt\": \"Clean motion graphics style animation, abstract data flowing between connected nodes, blue and white color scheme, professional corporate aesthetic, smooth transitions\"\n}'\n\n\nInstall note: The install script only detects your OS/architecture, downloads the matching binary from dist.inference.sh, and verifies its SHA-256 checksum. No elevated permissions or background processes. Manual install & verification available.\n\nScript Formulas\nProblem-Agitate-Solve (PAS) — 60 seconds\nSection\tDuration\tContent\tWord Count\nProblem\t10s\tState the pain point the viewer has\t~25 words\nAgitate\t10s\tShow why it's worse than they think\t~25 words\nSolution\t15s\tIntroduce your product/idea\t~35 words\nHow It Works\t20s\tShow 3 key steps or features\t~50 words\nCTA\t5s\tOne clear next action\t~12 words\nBefore-After-Bridge (BAB) — 90 seconds\nSection\tDuration\tContent\nBefore\t15s\tShow the current frustrating state\nAfter\t15s\tShow the ideal outcome\nBridge\t40s\tExplain how your product gets them there\nSocial Proof\t10s\tQuick stat or testimonial\nCTA\t10s\tClear next step\nFeature Spotlight — 30 seconds (social)\nSection\tDuration\tContent\nHook\t3s\tSurprising fact or question\nFeature\t15s\tShow one feature solving one problem\nResult\t7s\tThe outcome/benefit\nCTA\t5s\tTry it / Learn more\nPacing Rules\nContent Type\tWords Per Minute\tNotes\nStandard narration\t150 wpm\tConversational pace\nComplex/technical\t120 wpm\tAllow processing time\nEnergetic/social\t170 wpm\tFaster for short-form\nChildren's content\t100 wpm\tClear and slow\n\nKey rule: 1 scene per key message. Don't pack multiple ideas into one visual.\n\nScene Duration Guidelines\nEstablishing shot: 3-5 seconds\nFeature demonstration: 5-8 seconds\nText/stat on screen: 3-4 seconds (must be readable)\nTransition: 0.5-1 second\nCTA screen: 3-5 seconds\nVisual Production\nScene Types\n# Product in context\ninfsh app run google/veo-3-1-fast --input '{\n  \"prompt\": \"Clean product demonstration video, hands typing on a laptop showing a dashboard interface, bright modern office, soft natural lighting, professional\"\n}'\n\n# Abstract concept visualization\ninfsh app run bytedance/seedance-1-5-pro --input '{\n  \"prompt\": \"Abstract motion graphics, colorful data streams connecting floating geometric shapes, smooth fluid animation, dark background with glowing elements, tech aesthetic\"\n}'\n\n# Lifestyle/outcome shot\ninfsh app run google/veo-3-1-fast --input '{\n  \"prompt\": \"Happy person relaxing on couch with laptop, smiling at screen, bright airy living room, warm afternoon light, satisfied customer feeling, lifestyle commercial style\"\n}'\n\n# Before/after comparison\ninfsh app run falai/flux-dev-lora --input '{\n  \"prompt\": \"Split screen comparison, left side cluttered messy desk with papers and stress, right side clean organized minimalist workspace, dramatic difference, clean design\"\n}'\n\nImage-to-Video for Scenes\n# Generate a still frame first\ninfsh app run falai/flux-dev-lora --input '{\n  \"prompt\": \"Professional workspace with glowing holographic interface, futuristic but clean, blue accent lighting\"\n}'\n\n# Animate it\ninfsh app run falai/wan-2-5-i2v --input '{\n  \"prompt\": \"Gentle camera push in, holographic elements subtly floating and rotating, soft ambient light shifts\",\n  \"image\": \"path/to/workspace-still.png\"\n}'\n\nVoiceover Production\nScript Writing Tips\nShort sentences. Max 15 words per sentence.\nActive voice. \"You can track your data\" not \"Your data can be tracked.\"\nConversational tone. Read it aloud — if it sounds stiff, rewrite.\nOne idea per sentence. One sentence per visual beat.\nGenerating Voiceover\n# Professional narration with Dia TTS\ninfsh app run falai/dia-tts --input '{\n  \"prompt\": \"[S1] Tired of spending hours on reports that nobody reads? There is a better way. Meet DataFlow. It turns your raw data into visual stories... in seconds. Just connect your source, pick a template, and share. Try DataFlow free today.\"\n}'\n\nPacing Control in TTS\nTechnique\tEffect\tExample\nPeriod .\tMedium pause\t\"This changes everything. Here's how.\"\nEllipsis ...\tLong pause (dramatic)\t\"And the result... was incredible.\"\nComma ,\tShort pause\t\"Fast, simple, powerful.\"\nExclamation !\tEmphasis/energy\t\"Start building today!\"\nQuestion ?\tRising intonation\t\"What if there was a better way?\"\nMusic & Audio\nBackground Music Guidelines\nVolume: 20-30% under narration (duck 6-12dB when voice plays)\nStyle: match the brand tone (corporate = ambient electronic, startup = upbeat indie)\nStructure: intro swell (first 3s) -> subtle loop under narration -> swell at CTA\nNo vocals: instrumental only under narration\n# Generate background music\ninfsh app run <music-gen-app> --input '{\n  \"prompt\": \"upbeat corporate background music, modern electronic, 90 BPM, positive and professional, no vocals, suitable for product explainer video\"\n}'\n\nAssembly Pipeline\nFull Production Workflow\n# 1. Generate voiceover\ninfsh app run falai/dia-tts --input '{\n  \"prompt\": \"[S1] Your script here...\"\n}'\n\n# 2. Generate scene visuals (in parallel)\ninfsh app run google/veo-3-1-fast --input '{\"prompt\": \"scene 1 description\"}' --no-wait\ninfsh app run google/veo-3-1-fast --input '{\"prompt\": \"scene 2 description\"}' --no-wait\ninfsh app run google/veo-3-1-fast --input '{\"prompt\": \"scene 3 description\"}' --no-wait\n\n# 3. Merge scenes into sequence\ninfsh app run infsh/media-merger --input '{\n  \"media\": [\"scene1.mp4\", \"scene2.mp4\", \"scene3.mp4\"]\n}'\n\n# 4. Add voiceover to video\ninfsh app run infsh/video-audio-merger --input '{\n  \"video\": \"merged-scenes.mp4\",\n  \"audio\": \"voiceover.mp3\"\n}'\n\n# 5. Add captions\ninfsh app run infsh/caption-videos --input '{\n  \"video\": \"final-with-audio.mp4\",\n  \"caption_file\": \"captions.srt\"\n}'\n\nVideo Length by Format\nFormat\tLength\tPlatform\nSocial teaser\t15-30s\tTikTok, Instagram Reels, YouTube Shorts\nProduct demo\t60-90s\tWebsite, landing page\nFeature explainer\t90-120s\tYouTube, email\nTutorial/walkthrough\t2-5min\tYouTube, help center\nInvestor pitch video\t2-3min\tPitch deck supplement\nTransition Types\nTransition\tWhen to Use\tEffect\nCut\tDefault between related scenes\tClean, professional\nDissolve/Crossfade\tTime passing, mood shift\tSoft, contemplative\nWipe\tNew topic or section\tClear separation\nZoom/Push\tDrilling into detail\tFocus attention\nMatch cut\tVisual similarity between scenes\tClever, memorable\nCommon Mistakes\nMistake\tProblem\tFix\nScript too wordy\tVoiceover rushed, viewer overwhelmed\tCut to 150 wpm max\nNo hook in first 3s\tViewers leave immediately\tStart with the problem or surprising stat\nVisuals lag narration\tConfusing disconnect\tVisuals should match or slightly precede words\nBackground music too loud\tCan't hear narration\tDuck music 6-12dB under voice\nNo captions\t85% of social video watched silent\tAlways add captions\nToo many ideas\tViewer retains nothing\tOne core message per video\nRelated Skills\nnpx skills add inference-sh/skills@ai-video-generation\nnpx skills add inference-sh/skills@video-prompting-guide\nnpx skills add inference-sh/skills@text-to-speech\nnpx skills add inference-sh/skills@prompt-engineering\n\n\nBrowse all apps: infsh app list"
  },
  "trust": {
    "sourceLabel": "tencent",
    "provenanceUrl": "https://clawhub.ai/okaris/explainer-video-guide",
    "publisherUrl": "https://clawhub.ai/okaris/explainer-video-guide",
    "owner": "okaris",
    "version": "0.1.5",
    "license": null,
    "verificationStatus": "Indexed source record"
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/explainer-video-guide",
    "downloadUrl": "https://openagent3.xyz/downloads/explainer-video-guide",
    "agentUrl": "https://openagent3.xyz/skills/explainer-video-guide/agent",
    "manifestUrl": "https://openagent3.xyz/skills/explainer-video-guide/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/explainer-video-guide/agent.md"
  }
}