{ "schemaVersion": "1.0", "item": { "slug": "i-love-you-mom", "name": "I Love You Mom", "source": "tencent", "type": "skill", "category": "通讯协作", "sourceUrl": "https://clawhub.ai/SaharCarmel/i-love-you-mom", "canonicalUrl": "https://clawhub.ai/SaharCarmel/i-love-you-mom", "targetPlatform": "OpenClaw" }, "install": { "downloadMode": "redirect", "downloadUrl": "/downloads/i-love-you-mom", "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=i-love-you-mom", "sourcePlatform": "tencent", "targetPlatform": "OpenClaw", "installMethod": "Manual import", "extraction": "Extract archive", "prerequisites": [ "OpenClaw" ], "packageFormat": "ZIP package", "includedAssets": [ "SKILL.md", "scripts/collect-photos.sh" ], "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": "2026-04-23T16:43:11.935Z", "expiresAt": "2026-04-30T16:43:11.935Z", "httpStatus": 200, "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=4claw-imageboard", "contentType": "application/zip", "probeMethod": "head", "details": { "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=4claw-imageboard", "contentDisposition": "attachment; filename=\"4claw-imageboard-1.0.1.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/i-love-you-mom" }, "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/i-love-you-mom", "agentPageUrl": "https://openagent3.xyz/skills/i-love-you-mom/agent", "manifestUrl": "https://openagent3.xyz/skills/i-love-you-mom/agent.json", "briefUrl": "https://openagent3.xyz/skills/i-love-you-mom/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": "Mixtiles Monthly Pipeline", "body": "Automatically collect the best family photos from a WhatsApp group each month, curate them, and generate a ready-to-order Mixtiles cart link." }, { "title": "Configuration", "body": "These environment variables control the pipeline. Set them before running:\n\nVariableDescriptionDefaultMIXTILES_GROUP_JIDWhatsApp group JID to collect photos from(required)MIXTILES_SEND_TOWhere to send the cart link (group JID or phone number)Same as MIXTILES_GROUP_JIDMIXTILES_PHOTO_COUNTHow many photos to select4MIXTILES_TILE_SIZETile size for the orderRECTANGLE_12X16" }, { "title": "Step 1: Collect Photos", "body": "Calculate the date range for last month and download all photos from the group:\n\n# Calculate first day of last month\nYEAR_MONTH=$(date -v-1m +%Y-%m) # macOS\nAFTER_DATE=\"${YEAR_MONTH}-01\"\nOUTPUT_DIR=~/mixtiles-queue/${YEAR_MONTH}\n\n# Run the collection script\nbash /scripts/collect-photos.sh \"$MIXTILES_GROUP_JID\" \"$AFTER_DATE\" \"$OUTPUT_DIR\"\n\nThe script outputs a JSON manifest on stdout with {id, sender, timestamp, filepath} for each downloaded photo." }, { "title": "Step 2: Curate with Vision", "body": "Read each downloaded photo using your vision capability. For each photo, evaluate:\n\nInclude if:\n\nReal family/life moment (people, gatherings, milestones, kids, travel, pets)\nGood image quality (clear, well-lit, in focus)\nUnique scene (not a near-duplicate of another photo)\n\nExclude if:\n\nScreenshot, meme, forwarded image, or link preview\nBlurry, too dark, or very low quality\nNear-duplicate of a better version already selected\nText-heavy image (WhatsApp forwards, news articles)\nPromotional content or ads" }, { "title": "Step 3: Select Top Photos", "body": "From the curated set, pick the top $MIXTILES_PHOTO_COUNT photos (default: 4). Prioritize:\n\nPeople and faces (especially kids, family gatherings)\nMilestone moments (birthdays, first steps, graduations)\nTravel and experiences\nVariety — don't pick 4 photos from the same event if there are others\n\nIf fewer than $MIXTILES_PHOTO_COUNT good photos exist, use whatever passes curation." }, { "title": "Step 4: Build Multi-Photo Cart", "body": "Use the mixtiles-it skill's script with the --batch flag:\n\nMIXTILES_CART_SCRIPT=\"$(find ~/.openclaw/workspace/skills/mixtiles-it/scripts -name 'mixtiles-cart.py')\"\n\npython3 \"$MIXTILES_CART_SCRIPT\" \\\n --batch \\\n --size \"${MIXTILES_TILE_SIZE:-RECTANGLE_12X16}\"\n\nThis uploads each photo to Cloudinary and outputs a single Mixtiles cart URL with all photos." }, { "title": "Step 5: Send the Link", "body": "Send the cart link to the target chat:\n\nSEND_TO=\"${MIXTILES_SEND_TO:-$MIXTILES_GROUP_JID}\"\n\nwacli send text \\\n --to \"$SEND_TO\" \\\n --message \"Your monthly tiles are ready! Here are the best ${MIXTILES_PHOTO_COUNT:-4} photos from last month. Tap to customize and order: $CART_URL\"" }, { "title": "Error Handling", "body": "If collect-photos.sh finds 0 photos: report that no images were found for the period and skip the pipeline.\nIf fewer photos pass curation than MIXTILES_PHOTO_COUNT: use all that passed — even 1 photo is worth sending.\nIf Cloudinary upload fails for a photo: skip that photo, continue with the rest.\nIf wacli send fails: print the cart URL so the user can send it manually." }, { "title": "Manual Trigger", "body": "To run the pipeline outside the monthly schedule:\n\nRun the mixtiles-monthly skill: collect photos from the family group for the past month, curate the best ones, build a multi-photo cart link, and send it." } ], "body": "Mixtiles Monthly Pipeline\n\nAutomatically collect the best family photos from a WhatsApp group each month, curate them, and generate a ready-to-order Mixtiles cart link.\n\nConfiguration\n\nThese environment variables control the pipeline. Set them before running:\n\nVariable\tDescription\tDefault\nMIXTILES_GROUP_JID\tWhatsApp group JID to collect photos from\t(required)\nMIXTILES_SEND_TO\tWhere to send the cart link (group JID or phone number)\tSame as MIXTILES_GROUP_JID\nMIXTILES_PHOTO_COUNT\tHow many photos to select\t4\nMIXTILES_TILE_SIZE\tTile size for the order\tRECTANGLE_12X16\nPipeline Steps\nStep 1: Collect Photos\n\nCalculate the date range for last month and download all photos from the group:\n\n# Calculate first day of last month\nYEAR_MONTH=$(date -v-1m +%Y-%m) # macOS\nAFTER_DATE=\"${YEAR_MONTH}-01\"\nOUTPUT_DIR=~/mixtiles-queue/${YEAR_MONTH}\n\n# Run the collection script\nbash /scripts/collect-photos.sh \"$MIXTILES_GROUP_JID\" \"$AFTER_DATE\" \"$OUTPUT_DIR\"\n\n\nThe script outputs a JSON manifest on stdout with {id, sender, timestamp, filepath} for each downloaded photo.\n\nStep 2: Curate with Vision\n\nRead each downloaded photo using your vision capability. For each photo, evaluate:\n\nInclude if:\n\nReal family/life moment (people, gatherings, milestones, kids, travel, pets)\nGood image quality (clear, well-lit, in focus)\nUnique scene (not a near-duplicate of another photo)\n\nExclude if:\n\nScreenshot, meme, forwarded image, or link preview\nBlurry, too dark, or very low quality\nNear-duplicate of a better version already selected\nText-heavy image (WhatsApp forwards, news articles)\nPromotional content or ads\nStep 3: Select Top Photos\n\nFrom the curated set, pick the top $MIXTILES_PHOTO_COUNT photos (default: 4). Prioritize:\n\nPeople and faces (especially kids, family gatherings)\nMilestone moments (birthdays, first steps, graduations)\nTravel and experiences\nVariety — don't pick 4 photos from the same event if there are others\n\nIf fewer than $MIXTILES_PHOTO_COUNT good photos exist, use whatever passes curation.\n\nStep 4: Build Multi-Photo Cart\n\nUse the mixtiles-it skill's script with the --batch flag:\n\nMIXTILES_CART_SCRIPT=\"$(find ~/.openclaw/workspace/skills/mixtiles-it/scripts -name 'mixtiles-cart.py')\"\n\npython3 \"$MIXTILES_CART_SCRIPT\" \\\n --batch \\\n --size \"${MIXTILES_TILE_SIZE:-RECTANGLE_12X16}\"\n\n\nThis uploads each photo to Cloudinary and outputs a single Mixtiles cart URL with all photos.\n\nStep 5: Send the Link\n\nSend the cart link to the target chat:\n\nSEND_TO=\"${MIXTILES_SEND_TO:-$MIXTILES_GROUP_JID}\"\n\nwacli send text \\\n --to \"$SEND_TO\" \\\n --message \"Your monthly tiles are ready! Here are the best ${MIXTILES_PHOTO_COUNT:-4} photos from last month. Tap to customize and order: $CART_URL\"\n\nError Handling\nIf collect-photos.sh finds 0 photos: report that no images were found for the period and skip the pipeline.\nIf fewer photos pass curation than MIXTILES_PHOTO_COUNT: use all that passed — even 1 photo is worth sending.\nIf Cloudinary upload fails for a photo: skip that photo, continue with the rest.\nIf wacli send fails: print the cart URL so the user can send it manually.\nManual Trigger\n\nTo run the pipeline outside the monthly schedule:\n\nRun the mixtiles-monthly skill: collect photos from the family group for the past month, curate the best ones, build a multi-photo cart link, and send it." }, "trust": { "sourceLabel": "tencent", "provenanceUrl": "https://clawhub.ai/SaharCarmel/i-love-you-mom", "publisherUrl": "https://clawhub.ai/SaharCarmel/i-love-you-mom", "owner": "SaharCarmel", "version": "1.0.0", "license": null, "verificationStatus": "Indexed source record" }, "links": { "detailUrl": "https://openagent3.xyz/skills/i-love-you-mom", "downloadUrl": "https://openagent3.xyz/downloads/i-love-you-mom", "agentUrl": "https://openagent3.xyz/skills/i-love-you-mom/agent", "manifestUrl": "https://openagent3.xyz/skills/i-love-you-mom/agent.json", "briefUrl": "https://openagent3.xyz/skills/i-love-you-mom/agent.md" } }