{
  "schemaVersion": "1.0",
  "item": {
    "slug": "video-prompting-guide",
    "name": "Video Prompting Guide",
    "source": "tencent",
    "type": "skill",
    "category": "AI 智能",
    "sourceUrl": "https://clawhub.ai/okaris/video-prompting-guide",
    "canonicalUrl": "https://clawhub.ai/okaris/video-prompting-guide",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadMode": "redirect",
    "downloadUrl": "/downloads/video-prompting-guide",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=video-prompting-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",
      "status": "healthy",
      "reason": "direct_download_ok",
      "recommendedAction": "download",
      "checkedAt": "2026-04-30T16:55:25.780Z",
      "expiresAt": "2026-05-07T16:55:25.780Z",
      "httpStatus": 200,
      "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=network",
      "contentType": "application/zip",
      "probeMethod": "head",
      "details": {
        "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=network",
        "contentDisposition": "attachment; filename=\"network-1.0.0.zip\"",
        "redirectLocation": null,
        "bodySnippet": null
      },
      "scope": "source",
      "summary": "Source download looks usable.",
      "detail": "Yavira can redirect you to the upstream package for this source.",
      "primaryActionLabel": "Download for OpenClaw",
      "primaryActionHref": "/downloads/video-prompting-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/video-prompting-guide",
    "agentPageUrl": "https://openagent3.xyz/skills/video-prompting-guide/agent",
    "manifestUrl": "https://openagent3.xyz/skills/video-prompting-guide/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/video-prompting-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": "Video Prompting Guide",
        "body": "Best practices for writing effective AI video generation prompts via inference.sh."
      },
      {
        "title": "Quick Start",
        "body": "curl -fsSL https://cli.inference.sh | sh && infsh login\n\n# Well-structured video prompt\ninfsh app run google/veo-3-1-fast --input '{\n  \"prompt\": \"Cinematic tracking shot of a red sports car driving through Tokyo at night, neon lights reflecting on wet streets, rain falling, 4K, shallow depth of field\"\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": "Prompt Structure Formula",
        "body": "[Shot Type] + [Subject] + [Action] + [Setting] + [Lighting] + [Style] + [Technical]"
      },
      {
        "title": "Example Breakdown",
        "body": "\"Slow motion close-up of coffee being poured into a white ceramic cup,\nsteam rising, morning sunlight streaming through window, warm color grading,\ncinematic, 4K, shallow depth of field\"\n\nShot Type: Slow motion close-up\nSubject: Coffee\nAction: Being poured\nSetting: White ceramic cup, window\nLighting: Morning sunlight\nStyle: Warm color grading, cinematic\nTechnical: 4K, shallow depth of field"
      },
      {
        "title": "Shot Types",
        "body": "Shot TypeDescriptionUse ForWide shotShows entire sceneEstablishing locationMedium shotWaist-up framingConversations, actionsClose-upFace or detailEmotion, product detailExtreme close-upSingle featureDrama, textureAerial shotBird's eye viewLandscapes, scaleLow angleCamera looking upPower, grandeurHigh angleCamera looking downVulnerabilityDutch angleTilted cameraUnease, tensionPOV shotFirst person viewImmersion"
      },
      {
        "title": "Camera Movements",
        "body": "MovementDescriptionEffectTracking shotCamera follows subjectDynamic, engagingDolly in/outCamera moves toward/awayFocus, revealPanHorizontal rotationSurvey sceneTiltVertical rotationReveal heightCrane shotVertical + horizontalDramatic revealHandheldSlight shakeRealism, urgencySteadicamSmooth followingProfessional, cinematicZoomLens zoom in/outQuick focus changeStaticNo movementContemplation, stability"
      },
      {
        "title": "Lighting Keywords",
        "body": "KeywordEffectGolden hourWarm, soft, romanticBlue hourCool, moody, twilightHigh keyBright, minimal shadowsLow keyDark, dramatic shadowsRim lightingSubject outlined with lightBacklitLight from behind subjectSoft lightingGentle, flatteringHard lightingSharp shadows, contrastNeonColorful, urban, cyberpunkNatural lightingRealistic, documentary"
      },
      {
        "title": "Cinematic Styles",
        "body": "cinematic, film grain, anamorphic lens, letterbox,\nshallow depth of field, bokeh, 35mm film,\ncolor grading, theatrical"
      },
      {
        "title": "Visual Aesthetics",
        "body": "minimalist, maximalist, vintage, retro, futuristic,\ncyberpunk, steampunk, noir, pastel, vibrant,\nmuted colors, high contrast, desaturated"
      },
      {
        "title": "Quality Keywords",
        "body": "4K, 8K, high resolution, photorealistic,\nhyperrealistic, ultra detailed, professional,\nbroadcast quality, HDR"
      },
      {
        "title": "Product Demo",
        "body": "infsh app run google/veo-3-1-fast --input '{\n  \"prompt\": \"Smooth tracking shot around a sleek smartphone on a white pedestal, soft studio lighting, product photography style, reflections on surface, 4K, shallow depth of field\"\n}'"
      },
      {
        "title": "Nature Documentary",
        "body": "infsh app run google/veo-3-1 --input '{\n  \"prompt\": \"Slow motion extreme close-up of a hummingbird hovering at a red flower, wings in motion blur, shallow depth of field, golden hour lighting, National Geographic style\"\n}'"
      },
      {
        "title": "Urban Lifestyle",
        "body": "infsh app run google/veo-3 --input '{\n  \"prompt\": \"Tracking shot following a cyclist through busy city streets, morning rush hour, natural lighting, handheld camera feel, documentary style, authentic and candid\"\n}'"
      },
      {
        "title": "Food Content",
        "body": "infsh app run bytedance/seedance-1-5-pro --input '{\n  \"prompt\": \"Close-up of chocolate sauce being drizzled over ice cream, slow motion, steam rising, soft lighting, food photography style, appetizing, commercial quality\"\n}'"
      },
      {
        "title": "Tech/Futuristic",
        "body": "infsh app run xai/grok-imagine-video --input '{\n  \"prompt\": \"Futuristic control room with holographic displays, camera slowly pans across the space, blue and cyan lighting, sci-fi atmosphere, Blade Runner aesthetic, 4K\",\n  \"duration\": 5\n}'"
      },
      {
        "title": "Common Mistakes to Avoid",
        "body": "MistakeProblemBetter ApproachToo vague\"A nice video\"Specify shot, subject, styleToo complexMultiple scenesOne scene per promptNo motionStatic descriptionInclude camera movement or actionConflicting styles\"Minimalist maximalist\"Choose one aestheticNo lightingUndefined moodSpecify lighting conditions"
      },
      {
        "title": "Google Veo",
        "body": "Excels at realistic, cinematic content\nSupports audio generation (Veo 3+)\nBest with detailed, professional prompts\nFrame interpolation available in 3.1"
      },
      {
        "title": "Seedance",
        "body": "Strong at dance and human motion\nFirst-frame control available\nGood for consistent character motion\nWorks well with reference images"
      },
      {
        "title": "Wan 2.5",
        "body": "Best for image-to-video\nAnimates still images naturally\nGood motion prediction\nWorks with any image style"
      },
      {
        "title": "Grok",
        "body": "Good general-purpose video\nConfigurable duration (5-10s)\nCreative interpretations\nWorks well with abstract concepts"
      },
      {
        "title": "Workflow: Iterative Prompting",
        "body": "# 1. Start with basic prompt\ninfsh app run google/veo-3-1-fast --input '{\n  \"prompt\": \"A woman walking through a forest\"\n}'\n\n# 2. Add specificity\ninfsh app run google/veo-3-1-fast --input '{\n  \"prompt\": \"Medium tracking shot of a woman in a red dress walking through an autumn forest\"\n}'\n\n# 3. Add style and technical details\ninfsh app run google/veo-3-1-fast --input '{\n  \"prompt\": \"Cinematic medium tracking shot of a woman in a flowing red dress walking through an autumn forest, golden hour sunlight filtering through leaves, shallow depth of field, film grain, 4K\"\n}'"
      },
      {
        "title": "Related Skills",
        "body": "# Generate videos\nnpx skills add inference-sh/skills@ai-video-generation\n\n# Google Veo specific\nnpx skills add inference-sh/skills@google-veo\n\n# Generate images for image-to-video\nnpx skills add inference-sh/skills@ai-image-generation\n\n# General prompt engineering\nnpx skills add inference-sh/skills@prompt-engineering\n\n# Full platform skill\nnpx skills add inference-sh/skills@inference-sh\n\nBrowse all video apps: infsh app list --category video"
      },
      {
        "title": "Documentation",
        "body": "Running Apps - How to run apps via CLI\nVideo Generation Guide - Comprehensive video guide"
      }
    ],
    "body": "Video Prompting Guide\n\nBest practices for writing effective AI video generation prompts via inference.sh.\n\nQuick Start\ncurl -fsSL https://cli.inference.sh | sh && infsh login\n\n# Well-structured video prompt\ninfsh app run google/veo-3-1-fast --input '{\n  \"prompt\": \"Cinematic tracking shot of a red sports car driving through Tokyo at night, neon lights reflecting on wet streets, rain falling, 4K, shallow depth of field\"\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\nPrompt Structure Formula\n[Shot Type] + [Subject] + [Action] + [Setting] + [Lighting] + [Style] + [Technical]\n\nExample Breakdown\n\"Slow motion close-up of coffee being poured into a white ceramic cup,\nsteam rising, morning sunlight streaming through window, warm color grading,\ncinematic, 4K, shallow depth of field\"\n\nShot Type: Slow motion close-up\nSubject: Coffee\nAction: Being poured\nSetting: White ceramic cup, window\nLighting: Morning sunlight\nStyle: Warm color grading, cinematic\nTechnical: 4K, shallow depth of field\nShot Types\nShot Type\tDescription\tUse For\nWide shot\tShows entire scene\tEstablishing location\nMedium shot\tWaist-up framing\tConversations, actions\nClose-up\tFace or detail\tEmotion, product detail\nExtreme close-up\tSingle feature\tDrama, texture\nAerial shot\tBird's eye view\tLandscapes, scale\nLow angle\tCamera looking up\tPower, grandeur\nHigh angle\tCamera looking down\tVulnerability\nDutch angle\tTilted camera\tUnease, tension\nPOV shot\tFirst person view\tImmersion\nCamera Movements\nMovement\tDescription\tEffect\nTracking shot\tCamera follows subject\tDynamic, engaging\nDolly in/out\tCamera moves toward/away\tFocus, reveal\nPan\tHorizontal rotation\tSurvey scene\nTilt\tVertical rotation\tReveal height\nCrane shot\tVertical + horizontal\tDramatic reveal\nHandheld\tSlight shake\tRealism, urgency\nSteadicam\tSmooth following\tProfessional, cinematic\nZoom\tLens zoom in/out\tQuick focus change\nStatic\tNo movement\tContemplation, stability\nLighting Keywords\nKeyword\tEffect\nGolden hour\tWarm, soft, romantic\nBlue hour\tCool, moody, twilight\nHigh key\tBright, minimal shadows\nLow key\tDark, dramatic shadows\nRim lighting\tSubject outlined with light\nBacklit\tLight from behind subject\nSoft lighting\tGentle, flattering\nHard lighting\tSharp shadows, contrast\nNeon\tColorful, urban, cyberpunk\nNatural lighting\tRealistic, documentary\nStyle Keywords\nCinematic Styles\ncinematic, film grain, anamorphic lens, letterbox,\nshallow depth of field, bokeh, 35mm film,\ncolor grading, theatrical\n\nVisual Aesthetics\nminimalist, maximalist, vintage, retro, futuristic,\ncyberpunk, steampunk, noir, pastel, vibrant,\nmuted colors, high contrast, desaturated\n\nQuality Keywords\n4K, 8K, high resolution, photorealistic,\nhyperrealistic, ultra detailed, professional,\nbroadcast quality, HDR\n\nPrompt Examples by Use Case\nProduct Demo\ninfsh app run google/veo-3-1-fast --input '{\n  \"prompt\": \"Smooth tracking shot around a sleek smartphone on a white pedestal, soft studio lighting, product photography style, reflections on surface, 4K, shallow depth of field\"\n}'\n\nNature Documentary\ninfsh app run google/veo-3-1 --input '{\n  \"prompt\": \"Slow motion extreme close-up of a hummingbird hovering at a red flower, wings in motion blur, shallow depth of field, golden hour lighting, National Geographic style\"\n}'\n\nUrban Lifestyle\ninfsh app run google/veo-3 --input '{\n  \"prompt\": \"Tracking shot following a cyclist through busy city streets, morning rush hour, natural lighting, handheld camera feel, documentary style, authentic and candid\"\n}'\n\nFood Content\ninfsh app run bytedance/seedance-1-5-pro --input '{\n  \"prompt\": \"Close-up of chocolate sauce being drizzled over ice cream, slow motion, steam rising, soft lighting, food photography style, appetizing, commercial quality\"\n}'\n\nTech/Futuristic\ninfsh app run xai/grok-imagine-video --input '{\n  \"prompt\": \"Futuristic control room with holographic displays, camera slowly pans across the space, blue and cyan lighting, sci-fi atmosphere, Blade Runner aesthetic, 4K\",\n  \"duration\": 5\n}'\n\nCommon Mistakes to Avoid\nMistake\tProblem\tBetter Approach\nToo vague\t\"A nice video\"\tSpecify shot, subject, style\nToo complex\tMultiple scenes\tOne scene per prompt\nNo motion\tStatic description\tInclude camera movement or action\nConflicting styles\t\"Minimalist maximalist\"\tChoose one aesthetic\nNo lighting\tUndefined mood\tSpecify lighting conditions\nModel-Specific Tips\nGoogle Veo\nExcels at realistic, cinematic content\nSupports audio generation (Veo 3+)\nBest with detailed, professional prompts\nFrame interpolation available in 3.1\nSeedance\nStrong at dance and human motion\nFirst-frame control available\nGood for consistent character motion\nWorks well with reference images\nWan 2.5\nBest for image-to-video\nAnimates still images naturally\nGood motion prediction\nWorks with any image style\nGrok\nGood general-purpose video\nConfigurable duration (5-10s)\nCreative interpretations\nWorks well with abstract concepts\nWorkflow: Iterative Prompting\n# 1. Start with basic prompt\ninfsh app run google/veo-3-1-fast --input '{\n  \"prompt\": \"A woman walking through a forest\"\n}'\n\n# 2. Add specificity\ninfsh app run google/veo-3-1-fast --input '{\n  \"prompt\": \"Medium tracking shot of a woman in a red dress walking through an autumn forest\"\n}'\n\n# 3. Add style and technical details\ninfsh app run google/veo-3-1-fast --input '{\n  \"prompt\": \"Cinematic medium tracking shot of a woman in a flowing red dress walking through an autumn forest, golden hour sunlight filtering through leaves, shallow depth of field, film grain, 4K\"\n}'\n\nRelated Skills\n# Generate videos\nnpx skills add inference-sh/skills@ai-video-generation\n\n# Google Veo specific\nnpx skills add inference-sh/skills@google-veo\n\n# Generate images for image-to-video\nnpx skills add inference-sh/skills@ai-image-generation\n\n# General prompt engineering\nnpx skills add inference-sh/skills@prompt-engineering\n\n# Full platform skill\nnpx skills add inference-sh/skills@inference-sh\n\n\nBrowse all video apps: infsh app list --category video\n\nDocumentation\nRunning Apps - How to run apps via CLI\nVideo Generation Guide - Comprehensive video guide"
  },
  "trust": {
    "sourceLabel": "tencent",
    "provenanceUrl": "https://clawhub.ai/okaris/video-prompting-guide",
    "publisherUrl": "https://clawhub.ai/okaris/video-prompting-guide",
    "owner": "okaris",
    "version": "0.1.5",
    "license": null,
    "verificationStatus": "Indexed source record"
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/video-prompting-guide",
    "downloadUrl": "https://openagent3.xyz/downloads/video-prompting-guide",
    "agentUrl": "https://openagent3.xyz/skills/video-prompting-guide/agent",
    "manifestUrl": "https://openagent3.xyz/skills/video-prompting-guide/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/video-prompting-guide/agent.md"
  }
}