# Send Grok Imagine Video Generation to your agent Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually. ## Fast path - 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. ## Suggested prompts ### New install ```text I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Then review README.md for any prerequisites, environment setup, or post-install checks. Tell me what you changed and call out any manual steps you could not complete. ``` ### Upgrade existing ```text 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. Then review README.md for any prerequisites, environment setup, or post-install checks. Summarize what changed and any follow-up checks I should run. ``` ## Machine-readable fields ```json { "schemaVersion": "1.0", "item": { "slug": "grok-imagine-video", "name": "Grok Imagine Video Generation", "source": "tencent", "type": "skill", "category": "开发工具", "sourceUrl": "https://clawhub.ai/DevvGwardo/grok-imagine-video", "canonicalUrl": "https://clawhub.ai/DevvGwardo/grok-imagine-video", "targetPlatform": "OpenClaw" }, "install": { "downloadUrl": "/downloads/grok-imagine-video", "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=grok-imagine-video", "sourcePlatform": "tencent", "targetPlatform": "OpenClaw", "packageFormat": "ZIP package", "primaryDoc": "SKILL.md", "includedAssets": [ "CHANGELOG.md", "README.md", "references/api_reference.md", "scripts/grok_video_api.py", "SKILL.md" ], "downloadMode": "redirect", "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/grok-imagine-video" }, "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." ] } }, "links": { "detailUrl": "https://openagent3.xyz/skills/grok-imagine-video", "downloadUrl": "https://openagent3.xyz/downloads/grok-imagine-video", "agentUrl": "https://openagent3.xyz/skills/grok-imagine-video/agent", "manifestUrl": "https://openagent3.xyz/skills/grok-imagine-video/agent.json", "briefUrl": "https://openagent3.xyz/skills/grok-imagine-video/agent.md" } } ``` ## Documentation ### Grok Imagine Video Generate videos using xAI's Grok Imagine API directly from your messaging interface. ### Setup Important: You need your own xAI API key. Get it from https://console.x.ai/ For full installation instructions, see README.md Quick setup: # Set your xAI API key (YOUR key, not pre-configured) export XAI_API_KEY="your-api-key-here" ### Capabilities Text-to-image: Generate images from text descriptions (up to 10 variations) Image editing: Modify images using natural language Text-to-video: Create videos from text descriptions Image-to-video: Animate static images into motion Video editing: Modify videos using natural language Async generation: Handles long-running video jobs with polling Auto-delivery: Downloads and delivers images/videos via chat ### 1. Image Generation User says: "Create an image of a cyberpunk cityscape at night" python3 - << 'EOF' import os import sys sys.path.insert(0, 'scripts') from grok_video_api import GrokImagineVideoClient client = GrokImagineVideoClient(os.getenv("XAI_API_KEY")) result = client.generate_image("A cyberpunk cityscape at night, neon lights reflecting on wet streets") print(f"Image URL: {result}") EOF Images are generated instantly (no polling needed). Download promptly as URLs are temporary. ### 1b. Image Editing User says: "Edit this image — make it look like a watercolor" python3 - << 'EOF' import os import sys sys.path.insert(0, 'scripts') from grok_video_api import GrokImagineVideoClient client = GrokImagineVideoClient(os.getenv("XAI_API_KEY")) result = client.edit_image( image_url="https://example.com/photo.jpg", prompt="Make it look like a watercolor painting" ) print(f"Edited image: {result}") EOF ### 2. Text-to-Video User says: "Generate a video of a sunset over the ocean" # Use the Python client python3 - << 'EOF' import os import sys sys.path.insert(0, 'scripts') from grok_video_api import GrokImagineVideoClient client = GrokImagineVideoClient(os.getenv("XAI_API_KEY")) result = client.text_to_video("A beautiful sunset over the ocean", duration=10) print(f"Job started: {result['job_id']}") EOF ### 3. Wait for Video Completion Video generation takes 1-3 minutes. Poll with progress: python3 - << 'EOF' import os import sys sys.path.insert(0, 'scripts') from grok_video_api import GrokImagineVideoClient client = GrokImagineVideoClient(os.getenv("XAI_API_KEY")) def progress(response): print(f"Polling... {'Done!' if 'video' in response else 'Pending'}") final = client.wait_for_completion("request-id-here", progress_callback=progress) print(f"Video ready: {final['video']['url']}") EOF ### 4. Download and Deliver Download the completed video to the workspace: python3 - << 'EOF' import os import sys sys.path.insert(0, 'scripts') from grok_video_api import GrokImagineVideoClient client = GrokImagineVideoClient(os.getenv("XAI_API_KEY")) output = "/data/workspace/videos/sunset.mp4" client.download_video(final, output) # pass the full response dict print(f"Downloaded: {output}") EOF ### Image-to-Video Animate an image: from grok_video_api import GrokImagineVideoClient client = GrokImagineVideoClient(api_key) result = client.image_to_video( image_url="https://example.com/photo.jpg", prompt="Make the clouds move slowly", duration=10 ) ### Video Editing Edit an existing video: result = client.edit_video( video_url="https://example.com/source.mp4", edit_prompt="Add a warm sunset filter and slow down to 50% speed" ) ### Configuration Important: Get your own API key from https://console.x.ai/ - do NOT use pre-configured keys. export XAI_API_KEY="sk-..." For OpenClaw integration, add to workspace .env or manage via gateway config. See README.md for complete setup instructions. ### Error Handling Common errors and responses: Unauthorized / API key not set: → Get your key from https://console.x.ai/ and set export XAI_API_KEY="your-key" - See README.md for details Rate limit: "Too many requests" → Wait and retry Content policy: "Prompt violates content policies" → Rephrase prompt Timeout: Job took too long → Reduce duration or complexity Always wrap API calls in try/except and provide user-friendly messages. ### Best Practices Prompt engineering (images): Be descriptive: "A collage of London landmarks in a stenciled street-art style" Specify style: "Watercolor painting of a mountain lake at dawn" Use multiple variations (n=4) to explore interpretations Prompt engineering (videos): Be specific: "A golden retriever running through a sunny meadow" Include camera movement: "Slow pan from left to right" Specify lighting: "Warm golden hour lighting" Performance: Images generate instantly — no polling needed Use 480p for faster video generation, 720p for higher quality Keep videos under 10 seconds unless essential Start with text-to-video, then edit if needed User experience: Images: deliver immediately after generation Videos: send progress updates: "Generating video... 45% complete" Estimate time for videos: "This takes about 2-3 minutes" Confirm delivery: "Here's your image/video!" ### Limits Images per request: 1-10 Video duration: 1-15 seconds Video resolution: 480p (default) or 720p Rate limit: 60 requests/minute Max concurrent jobs: 15 See references/api_reference.md for full API documentation. ### Integration with Other Skills Combine with ffmpeg-video-editor for post-processing (trimming, concatenation, filters) Use fal-ai for additional video effects Integrate with image-generation skills for source images ### Troubleshooting Job stuck in "pending": Check API key and quota Video generation slow: Try 720p instead of 1080p Failed jobs: Check error_code in response; see API reference Download errors: Verify video_url is accessible and has not expired ## Trust - Source: tencent - Verification: Indexed source record - Publisher: DevvGwardo - Version: 1.0.4 ## Source health - Status: healthy - Source download looks usable. - Yavira can redirect you to the upstream package for this source. - Health scope: source - Reason: direct_download_ok - Checked at: 2026-04-30T16:55:25.780Z - Expires at: 2026-05-07T16:55:25.780Z - Recommended action: Download for OpenClaw ## Links - [Detail page](https://openagent3.xyz/skills/grok-imagine-video) - [Send to Agent page](https://openagent3.xyz/skills/grok-imagine-video/agent) - [JSON manifest](https://openagent3.xyz/skills/grok-imagine-video/agent.json) - [Markdown brief](https://openagent3.xyz/skills/grok-imagine-video/agent.md) - [Download page](https://openagent3.xyz/downloads/grok-imagine-video)