# Send Video Downloader 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. 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. Summarize what changed and any follow-up checks I should run. ``` ## Machine-readable fields ```json { "schemaVersion": "1.0", "item": { "slug": "video-downloader", "name": "Video Downloader", "source": "tencent", "type": "skill", "category": "开发工具", "sourceUrl": "https://clawhub.ai/ivangdavila/video-downloader", "canonicalUrl": "https://clawhub.ai/ivangdavila/video-downloader", "targetPlatform": "OpenClaw" }, "install": { "downloadUrl": "/downloads/video-downloader", "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=video-downloader", "sourcePlatform": "tencent", "targetPlatform": "OpenClaw", "packageFormat": "ZIP package", "primaryDoc": "SKILL.md", "includedAssets": [ "SKILL.md", "commands.md", "download_video.py", "memory-template.md", "setup.md" ], "downloadMode": "redirect", "sourceHealth": { "source": "tencent", "status": "healthy", "reason": "direct_download_ok", "recommendedAction": "download", "checkedAt": "2026-05-07T17:22:31.273Z", "expiresAt": "2026-05-14T17:22:31.273Z", "httpStatus": 200, "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=afrexai-annual-report", "contentType": "application/zip", "probeMethod": "head", "details": { "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=afrexai-annual-report", "contentDisposition": "attachment; filename=\"afrexai-annual-report-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-downloader" }, "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/video-downloader", "downloadUrl": "https://openagent3.xyz/downloads/video-downloader", "agentUrl": "https://openagent3.xyz/skills/video-downloader/agent", "manifestUrl": "https://openagent3.xyz/skills/video-downloader/agent.json", "briefUrl": "https://openagent3.xyz/skills/video-downloader/agent.md" } } ``` ## Documentation ### Video Downloader Download single videos from user-provided URLs with predictable quality, format, and output paths. ### Setup On first use, read setup.md for integration guidelines. ### When to Use Use this skill when the user asks to download a video or extract audio from a video URL. It is optimized for one-off downloads with explicit quality and format requirements. ### Architecture Memory lives in ~/video-downloader/. See memory-template.md for structure. ~/video-downloader/ ├── memory.md # Status + user preferences ├── downloads-log.md # Optional history of completed downloads └── failed-downloads.md # Optional retries and failure reasons ### Quick Reference Load only what you need to keep context small during execution. TopicFileSetup flowsetup.mdMemory templatememory-template.mdCommand recipescommands.mdDownload scriptdownload_video.py ### 1. Confirm Rights and Target First Ask for the exact URL and intended use when unclear. If the request implies unauthorized copying, refuse and suggest legal alternatives. ### 2. Inspect Metadata Before Downloading Run metadata check first to confirm title, duration, and available formats. If metadata fetch fails, stop and report the exact error instead of retrying blindly. ### 3. Match Quality to User Intent Use best when user says "highest quality". Use capped quality (1080p, 720p, etc.) for smaller files or device limits. Use audio-only mode only when they explicitly want audio extraction. ### 4. Use Deterministic Output Names Save files as %(title)s [%(id)s].%(ext)s to reduce collisions. Keep downloads in a user-approved directory and never write outside it. ### 5. Prefer the Local Wrapper Script Use python3 download_video.py "" ... for consistent behavior. Fall back to raw yt-dlp commands only if the user asks for custom flags not covered by the script. ### 6. Verify Output Before Declaring Success Confirm file exists, extension matches request, and size is non-zero. For audio-only downloads, confirm output is .mp3. ### Common Traps Downloading playlists accidentally -> use --no-playlist by default. Choosing best for limited storage -> oversized files and slow transfers. Re-trying blocked URLs repeatedly -> temporary ban risk and no progress. Saving with title only -> filename collisions across similar uploads. Skipping metadata check -> wrong media downloaded from redirected links. ### External Endpoints The downloader only contacts domains implied by the user-provided URL. EndpointData SentPurposeUser-provided video host URL domains (via yt-dlp)Requested media URL and standard downloader headersFetch metadata and media streams No other data is sent externally. ### Security & Privacy Data that leaves your machine: Only the target media URL and standard downloader request headers sent by yt-dlp. Data that stays local: Downloaded files in the selected output folder. Optional memory notes under ~/video-downloader/. This skill does NOT: Store credentials in plain text. Access files outside user-approved output paths. Download playlists unless the user explicitly asks. Make undeclared network requests outside the target media host. ### Trust By using this skill, requests are sent to the video host domains behind the provided URL. Only install if you trust those services with your request metadata. ### Related Skills Install with clawhub install if user confirms: video — video processing workflows ffmpeg — codec conversion tasks audio — audio cleanup workflows youtube-video-transcript — transcript extraction ### Feedback If useful: clawhub star video-downloader Stay updated: clawhub sync ## Trust - Source: tencent - Verification: Indexed source record - Publisher: ivangdavila - Version: 1.0.0 ## 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: 2026-05-07T17:22:31.273Z - Expires at: 2026-05-14T17:22:31.273Z - Recommended action: Download for OpenClaw ## Links - [Detail page](https://openagent3.xyz/skills/video-downloader) - [Send to Agent page](https://openagent3.xyz/skills/video-downloader/agent) - [JSON manifest](https://openagent3.xyz/skills/video-downloader/agent.json) - [Markdown brief](https://openagent3.xyz/skills/video-downloader/agent.md) - [Download page](https://openagent3.xyz/downloads/video-downloader)