{ "schemaVersion": "1.0", "item": { "slug": "image", "name": "Image", "source": "tencent", "type": "skill", "category": "内容创作", "sourceUrl": "https://clawhub.ai/ivangdavila/image", "canonicalUrl": "https://clawhub.ai/ivangdavila/image", "targetPlatform": "OpenClaw" }, "install": { "downloadMode": "redirect", "downloadUrl": "/downloads/image", "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=image", "sourcePlatform": "tencent", "targetPlatform": "OpenClaw", "installMethod": "Manual import", "extraction": "Extract archive", "prerequisites": [ "OpenClaw" ], "packageFormat": "ZIP package", "includedAssets": [ "SKILL.md", "accessibility.md", "branding.md", "commands.md", "ecommerce.md", "photography.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": "image", "status": "healthy", "reason": "direct_download_ok", "recommendedAction": "download", "checkedAt": "2026-04-29T21:20:13.311Z", "expiresAt": "2026-05-06T21:20:13.311Z", "httpStatus": 200, "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=image", "contentType": "application/zip", "probeMethod": "head", "details": { "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=image", "contentDisposition": "attachment; filename=\"image-1.0.4.zip\"", "redirectLocation": null, "bodySnippet": null, "slug": "image" }, "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/image" }, "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/image", "agentPageUrl": "https://openagent3.xyz/skills/image/agent", "manifestUrl": "https://openagent3.xyz/skills/image/agent.json", "briefUrl": "https://openagent3.xyz/skills/image/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": "When to Use", "body": "Use when the main artifact is an image file or visual asset, especially when format choice, resizing, cropping, compression, metadata, transparency, color profile, responsive delivery, social specs, marketplace requirements, or print readiness matter.\n\nIf the task is destination-specific, load the matching file before deciding:\n\nweb.md for responsive delivery, LCP/CLS, srcset, lazy loading, SVG, and modern web formats.\nsocial.md for platform dimensions, safe zones, and feed/story/banner exports.\necommerce.md for marketplace product-image rules, white backgrounds, zoom, and catalog consistency.\nphotography.md for RAW, ICC profiles, print export, EXIF, and non-destructive editing.\nbranding.md for logos, icons, favicons, app icons, SVG consistency, and small-size legibility.\nscreenshots.md for UI captures, documentation images, annotations, redaction, and marketing/device frames.\naccessibility.md for alt text, decorative vs informative images, text in images, charts, and contrast-aware image delivery.\ncommands.md when the user needs concrete ImageMagick or Pillow examples.\n\nKeep the main workflow in this file, then pull in the specialized file for the exact delivery context instead of guessing from generic image advice." }, { "title": "Quick Reference", "body": "SituationLoadWhyWeb optimization, responsive images, lazy loading, SVGweb.mdAvoid CLS/LCP mistakes, oversized assets, and wrong web formatsColor profiles, metadata, RAW, print, non-destructive workflowsphotography.mdProtect color intent, print readiness, and master-file qualitySocial platform dimensions, safe zones, banners, previewssocial.mdPrevent unsafe crops, unreadable text, and uploader recompression surprisesProduct photos, marketplace standards, catalog consistencyecommerce.mdPreserve zoom detail, white-background compliance, and catalog consistencyLogos, favicons, SVGs, app icons, icon setsbranding.mdProtect small-size legibility, SVG consistency, and multi-format icon deliveryUI screenshots, docs captures, redaction, annotationsscreenshots.mdAvoid blurry captures, privacy leaks, and misleading before/after comparisonsAlt text, text-in-image risk, charts, decorative vs informative imagesaccessibility.mdKeep image work usable and compliant, not only visually correctImageMagick and Pillow commandscommands.mdUse concrete commands once the export decision is already clear" }, { "title": "Fast Workflow", "body": "Identify the asset type: photo, screenshot, UI capture, logo, diagram, social card, product image, or print source.\nIdentify the destination: web page, social upload, marketplace gallery, print handoff, internal archive, or further editing pipeline.\nDecide whether the source should remain vector, layered, or RAW instead of being flattened too early.\nInspect the file before editing: dimensions, aspect ratio, orientation, transparency, color profile, metadata, and current compression damage.\nLoad the destination-specific file if the job is web, social, ecommerce, photography/print, branding, screenshots, accessibility, or command-heavy.\nMake the minimum safe transformation set: crop, resize, convert, compress, strip or preserve metadata, and export.\nValidate the exported result in the destination context, not only in the editor." }, { "title": "Asset-Type Defaults", "body": "Asset typeUsually best starting pointWatch out forPhotoWebP or AVIF for web, JPEG fallback, layered/RAW master for editingColor profile shifts, overcompression, platform recompressionProduct photoJPEG or WebP for delivery, high-res clean masterWhite background, edge cleanup, zoom detail, consistencyScreenshot or UI capturePNG or lossless WebPJPEG blur, privacy leaks, unreadable textLogo or simple iconSVG master, PNG fallbacks only when neededTiny details, unsupported SVG pipelines, dark/light contrastSocial/OG cardPNG or high-quality JPEG sized for previewUnsafe crop, tiny text, double compressionDiagram or chartSVG when possible, PNG when fixed raster neededThin lines, low contrast, missing explanatory textPrint imageTIFF or high-quality JPEG with correct profileWrong profile, wrong physical size, no bleed" }, { "title": "1. Choose the workflow by destination, not by habit", "body": "Web delivery, social export, ecommerce prep, print output, and archive preservation are different image jobs.\nA screenshot, product photo, logo, infographic, and print asset should not default to the same format or compression strategy.\nImage generation is a different workflow from image processing; treat generated assets as inputs that still need inspection and export discipline.\nIf the destination is specialized, read the matching file before locking format, crop, quality, or metadata decisions.\nIf the file will be edited again later, preserve a master-grade source before making lightweight delivery exports." }, { "title": "2. Pick formats by content, not by trend", "body": "Photos usually want AVIF or WebP for modern web delivery, with JPEG fallback when compatibility matters.\nScreenshots, UI captures, diagrams, and text-heavy graphics often need PNG or lossless WebP to avoid blurry edges.\nLogos, icons, and simple illustrations should stay vector (.svg) when the target supports it.\nTransparency changes the decision: JPEG drops alpha, while PNG, WebP, and AVIF can preserve it.\nAnimated GIF is rarely the best output; animated WebP, MP4, or WebM are usually smaller and cleaner.\nTIFF, PSD, layered formats, and RAW files are working formats or masters, not normal delivery outputs.\nIf a platform re-encodes uploads aggressively, optimize for how that platform recompresses rather than for ideal local viewing.\nScreenshots, diagrams, and charts with sharp edges often benefit from lossless output even when photos do not." }, { "title": "3. Preserve color, transparency, and detail deliberately", "body": "Web assets should usually end in sRGB unless the destination explicitly needs something else.\nStripping or changing ICC profiles can shift colors even when the pixels themselves did not change.\nTransparent assets need alpha-safe formats and validation against both light and dark backgrounds.\nRepeated lossy saves compound damage, so keep a clean source and minimize recompression loops.\nUpscaling, denoising, sharpening, and background removal should be treated as visible edits, not harmless export steps." }, { "title": "4. Resize, crop, and compress in the right order", "body": "Decide aspect ratio first, crop second, resize third, and compress last.\nDo not upscale by default; extra pixels do not create missing detail.\nRetina or HiDPI exports should be intentional, not automatic overkill.\nAs a starting point, 2x is the normal Retina export and 3x should be deliberate, not default.\nSocial cards, ecommerce slots, and marketplace galleries often crop aggressively, so protect the real focal area and any critical text.\nA file that fits the pixel spec can still fail if the crop cuts off faces, products, labels, or UI affordances.\nIf text is embedded inside the image, validate at the smallest realistic preview size, not only at full resolution." }, { "title": "5. Treat metadata and orientation as real delivery concerns", "body": "EXIF orientation can make an image look upright in one viewer and rotated in another after export.\nPublic web assets usually should strip GPS and unnecessary camera metadata.\nCopyright, author, or provenance metadata may need to be preserved for editorial, legal, or archive use.\nMetadata decisions are part of the workflow, not an afterthought.\nPreserve filenames and output naming conventions when downstream systems map assets by exact names or SKU patterns.\nDo not strip metadata blindly if the workflow depends on authoring info, rights data, timestamps, or orientation." }, { "title": "6. Use practical budgets and delivery defaults", "body": "For web work, use budgets as a forcing function, not as decoration.\nA useful default starting point is: hero image under 200 KB, content image under 100 KB, thumbnail under 30 KB, raster icon under 5 KB.\nReserve layout space with explicit dimensions or aspect ratio when the image ships on the web.\nDo not lazy-load the primary hero or likely LCP image.\nA file that \"looks fine locally\" is not finished if it breaks CLS, LCP, or responsive delivery in the real page.\nA small file is not automatically good if detail, text legibility, product edges, or gradients collapse.\nIf a platform will recompress the image anyway, leave enough headroom that the second compression does not destroy the result." }, { "title": "7. Validate against the actual destination", "body": "Platform specs are not interchangeable: web hero, social preview, app store art, marketplace gallery, and print ad all have different constraints.\nEcommerce images may need background consistency, edge cleanliness, square-safe crops, and zoom-friendly detail.\nSocial images need safe composition because feeds crop previews differently across platforms.\nPrint assets care about physical size, bleed, and color handling in ways web exports do not.\nIf the asset ships on the web, remember the surrounding delivery too: width, height, alt text, and whether the image should carry text at all.\nIf the asset will be uploaded to a third-party platform, check the post-upload result because many pipelines resize, strip profiles, flatten metadata, or recompress again.\nIf the image carries meaning, validate its accessibility too: alt text strategy, text legibility, decorative vs informative role, and whether the meaning should have stayed in HTML or surrounding copy." }, { "title": "8. Batch safely and keep the original reversible", "body": "Work from originals or clean masters, not from already-optimized outputs.\nBatch processing should apply consistent rules, but still spot-check representative files before touching the whole set.\nOne wrong crop preset, color conversion, or lossy export can damage an entire batch quickly.\nKeep per-destination exports separated from masters so the next edit does not accidentally start from a degraded derivative." }, { "title": "Specialized Cases Worth Loading", "body": "Load branding.md when the asset is a logo, app icon, favicon, social avatar, badge, or reusable icon set.\nLoad screenshots.md when the asset is a UI capture, bug report image, tutorial screenshot, release-note image, or device-framed marketing visual.\nLoad accessibility.md when the image needs alt text, contains embedded text, carries chart/diagram meaning, or may be decorative instead of informative." }, { "title": "What Good Looks Like", "body": "The chosen format matches the content and the destination, not a blanket preference.\nThe exported file keeps the right focal area, text legibility, transparency, and color intent.\nMetadata is preserved or stripped deliberately.\nThe file size is efficient without obvious visual damage.\nThe asset still works after the actual upload, embed, or platform preview step.\nThe agent has not flattened a vector, layered, or RAW source earlier than necessary.\nThe asset is still understandable in its real use context, not just visually attractive in isolation." }, { "title": "Common Traps", "body": "Saving transparent images as JPEG and silently losing the alpha channel.\nUsing JPEG for screenshots or UI captures and turning sharp text into mush.\nShipping a file that matches the requested dimensions but has the wrong aspect ratio or unsafe crop.\nRecompressing the same JPEG multiple times and blaming the tool instead of the workflow.\nStripping metadata and accidentally breaking orientation, licensing context, or provenance needs.\nForgetting sRGB and wondering why colors shift between editing tools, browsers, and marketplaces.\nUsing SVG where the target platform strips it, rasterizes it badly, or blocks it entirely.\nAssuming AVIF or WebP is safe everywhere when some platforms, email clients, or upload pipelines still normalize back to JPEG or PNG.\nEmbedding critical text into images where HTML or native UI text should have carried the meaning.\nHitting the file-size budget but missing visual quality because the image was resized, cropped, or sharpened badly.\nRasterizing a logo too early and then fighting blurry exports forever.\nShipping a screenshot with secrets, personal data, or unstable timestamps still visible.\nTreating alt text, captions, or chart summaries as someone else's problem after the pixels look good." }, { "title": "Related Skills", "body": "Install with clawhub install if user confirms:\n\nimage-edit — Masking, cleanup, inpainting, and targeted visual edits.\nimage-generation — AI image generation and editing across current model providers.\nphotography — Capture, color, and print-oriented photo workflows.\nsvg — Vector graphics workflows when raster files are the wrong output.\necommerce — Marketplace and product-listing requirements that often constrain image delivery." }, { "title": "Feedback", "body": "If useful: clawhub star image\nStay updated: clawhub sync" } ], "body": "When to Use\n\nUse when the main artifact is an image file or visual asset, especially when format choice, resizing, cropping, compression, metadata, transparency, color profile, responsive delivery, social specs, marketplace requirements, or print readiness matter.\n\nIf the task is destination-specific, load the matching file before deciding:\n\nweb.md for responsive delivery, LCP/CLS, srcset, lazy loading, SVG, and modern web formats.\nsocial.md for platform dimensions, safe zones, and feed/story/banner exports.\necommerce.md for marketplace product-image rules, white backgrounds, zoom, and catalog consistency.\nphotography.md for RAW, ICC profiles, print export, EXIF, and non-destructive editing.\nbranding.md for logos, icons, favicons, app icons, SVG consistency, and small-size legibility.\nscreenshots.md for UI captures, documentation images, annotations, redaction, and marketing/device frames.\naccessibility.md for alt text, decorative vs informative images, text in images, charts, and contrast-aware image delivery.\ncommands.md when the user needs concrete ImageMagick or Pillow examples.\n\nKeep the main workflow in this file, then pull in the specialized file for the exact delivery context instead of guessing from generic image advice.\n\nQuick Reference\nSituation\tLoad\tWhy\nWeb optimization, responsive images, lazy loading, SVG\tweb.md\tAvoid CLS/LCP mistakes, oversized assets, and wrong web formats\nColor profiles, metadata, RAW, print, non-destructive workflows\tphotography.md\tProtect color intent, print readiness, and master-file quality\nSocial platform dimensions, safe zones, banners, previews\tsocial.md\tPrevent unsafe crops, unreadable text, and uploader recompression surprises\nProduct photos, marketplace standards, catalog consistency\tecommerce.md\tPreserve zoom detail, white-background compliance, and catalog consistency\nLogos, favicons, SVGs, app icons, icon sets\tbranding.md\tProtect small-size legibility, SVG consistency, and multi-format icon delivery\nUI screenshots, docs captures, redaction, annotations\tscreenshots.md\tAvoid blurry captures, privacy leaks, and misleading before/after comparisons\nAlt text, text-in-image risk, charts, decorative vs informative images\taccessibility.md\tKeep image work usable and compliant, not only visually correct\nImageMagick and Pillow commands\tcommands.md\tUse concrete commands once the export decision is already clear\nFast Workflow\nIdentify the asset type: photo, screenshot, UI capture, logo, diagram, social card, product image, or print source.\nIdentify the destination: web page, social upload, marketplace gallery, print handoff, internal archive, or further editing pipeline.\nDecide whether the source should remain vector, layered, or RAW instead of being flattened too early.\nInspect the file before editing: dimensions, aspect ratio, orientation, transparency, color profile, metadata, and current compression damage.\nLoad the destination-specific file if the job is web, social, ecommerce, photography/print, branding, screenshots, accessibility, or command-heavy.\nMake the minimum safe transformation set: crop, resize, convert, compress, strip or preserve metadata, and export.\nValidate the exported result in the destination context, not only in the editor.\nAsset-Type Defaults\nAsset type\tUsually best starting point\tWatch out for\nPhoto\tWebP or AVIF for web, JPEG fallback, layered/RAW master for editing\tColor profile shifts, overcompression, platform recompression\nProduct photo\tJPEG or WebP for delivery, high-res clean master\tWhite background, edge cleanup, zoom detail, consistency\nScreenshot or UI capture\tPNG or lossless WebP\tJPEG blur, privacy leaks, unreadable text\nLogo or simple icon\tSVG master, PNG fallbacks only when needed\tTiny details, unsupported SVG pipelines, dark/light contrast\nSocial/OG card\tPNG or high-quality JPEG sized for preview\tUnsafe crop, tiny text, double compression\nDiagram or chart\tSVG when possible, PNG when fixed raster needed\tThin lines, low contrast, missing explanatory text\nPrint image\tTIFF or high-quality JPEG with correct profile\tWrong profile, wrong physical size, no bleed\nCore Rules\n1. Choose the workflow by destination, not by habit\nWeb delivery, social export, ecommerce prep, print output, and archive preservation are different image jobs.\nA screenshot, product photo, logo, infographic, and print asset should not default to the same format or compression strategy.\nImage generation is a different workflow from image processing; treat generated assets as inputs that still need inspection and export discipline.\nIf the destination is specialized, read the matching file before locking format, crop, quality, or metadata decisions.\nIf the file will be edited again later, preserve a master-grade source before making lightweight delivery exports.\n2. Pick formats by content, not by trend\nPhotos usually want AVIF or WebP for modern web delivery, with JPEG fallback when compatibility matters.\nScreenshots, UI captures, diagrams, and text-heavy graphics often need PNG or lossless WebP to avoid blurry edges.\nLogos, icons, and simple illustrations should stay vector (.svg) when the target supports it.\nTransparency changes the decision: JPEG drops alpha, while PNG, WebP, and AVIF can preserve it.\nAnimated GIF is rarely the best output; animated WebP, MP4, or WebM are usually smaller and cleaner.\nTIFF, PSD, layered formats, and RAW files are working formats or masters, not normal delivery outputs.\nIf a platform re-encodes uploads aggressively, optimize for how that platform recompresses rather than for ideal local viewing.\nScreenshots, diagrams, and charts with sharp edges often benefit from lossless output even when photos do not.\n3. Preserve color, transparency, and detail deliberately\nWeb assets should usually end in sRGB unless the destination explicitly needs something else.\nStripping or changing ICC profiles can shift colors even when the pixels themselves did not change.\nTransparent assets need alpha-safe formats and validation against both light and dark backgrounds.\nRepeated lossy saves compound damage, so keep a clean source and minimize recompression loops.\nUpscaling, denoising, sharpening, and background removal should be treated as visible edits, not harmless export steps.\n4. Resize, crop, and compress in the right order\nDecide aspect ratio first, crop second, resize third, and compress last.\nDo not upscale by default; extra pixels do not create missing detail.\nRetina or HiDPI exports should be intentional, not automatic overkill.\nAs a starting point, 2x is the normal Retina export and 3x should be deliberate, not default.\nSocial cards, ecommerce slots, and marketplace galleries often crop aggressively, so protect the real focal area and any critical text.\nA file that fits the pixel spec can still fail if the crop cuts off faces, products, labels, or UI affordances.\nIf text is embedded inside the image, validate at the smallest realistic preview size, not only at full resolution.\n5. Treat metadata and orientation as real delivery concerns\nEXIF orientation can make an image look upright in one viewer and rotated in another after export.\nPublic web assets usually should strip GPS and unnecessary camera metadata.\nCopyright, author, or provenance metadata may need to be preserved for editorial, legal, or archive use.\nMetadata decisions are part of the workflow, not an afterthought.\nPreserve filenames and output naming conventions when downstream systems map assets by exact names or SKU patterns.\nDo not strip metadata blindly if the workflow depends on authoring info, rights data, timestamps, or orientation.\n6. Use practical budgets and delivery defaults\nFor web work, use budgets as a forcing function, not as decoration.\nA useful default starting point is: hero image under 200 KB, content image under 100 KB, thumbnail under 30 KB, raster icon under 5 KB.\nReserve layout space with explicit dimensions or aspect ratio when the image ships on the web.\nDo not lazy-load the primary hero or likely LCP image.\nA file that \"looks fine locally\" is not finished if it breaks CLS, LCP, or responsive delivery in the real page.\nA small file is not automatically good if detail, text legibility, product edges, or gradients collapse.\nIf a platform will recompress the image anyway, leave enough headroom that the second compression does not destroy the result.\n7. Validate against the actual destination\nPlatform specs are not interchangeable: web hero, social preview, app store art, marketplace gallery, and print ad all have different constraints.\nEcommerce images may need background consistency, edge cleanliness, square-safe crops, and zoom-friendly detail.\nSocial images need safe composition because feeds crop previews differently across platforms.\nPrint assets care about physical size, bleed, and color handling in ways web exports do not.\nIf the asset ships on the web, remember the surrounding delivery too: width, height, alt text, and whether the image should carry text at all.\nIf the asset will be uploaded to a third-party platform, check the post-upload result because many pipelines resize, strip profiles, flatten metadata, or recompress again.\nIf the image carries meaning, validate its accessibility too: alt text strategy, text legibility, decorative vs informative role, and whether the meaning should have stayed in HTML or surrounding copy.\n8. Batch safely and keep the original reversible\nWork from originals or clean masters, not from already-optimized outputs.\nBatch processing should apply consistent rules, but still spot-check representative files before touching the whole set.\nOne wrong crop preset, color conversion, or lossy export can damage an entire batch quickly.\nKeep per-destination exports separated from masters so the next edit does not accidentally start from a degraded derivative.\nSpecialized Cases Worth Loading\nLoad branding.md when the asset is a logo, app icon, favicon, social avatar, badge, or reusable icon set.\nLoad screenshots.md when the asset is a UI capture, bug report image, tutorial screenshot, release-note image, or device-framed marketing visual.\nLoad accessibility.md when the image needs alt text, contains embedded text, carries chart/diagram meaning, or may be decorative instead of informative.\nWhat Good Looks Like\nThe chosen format matches the content and the destination, not a blanket preference.\nThe exported file keeps the right focal area, text legibility, transparency, and color intent.\nMetadata is preserved or stripped deliberately.\nThe file size is efficient without obvious visual damage.\nThe asset still works after the actual upload, embed, or platform preview step.\nThe agent has not flattened a vector, layered, or RAW source earlier than necessary.\nThe asset is still understandable in its real use context, not just visually attractive in isolation.\nCommon Traps\nSaving transparent images as JPEG and silently losing the alpha channel.\nUsing JPEG for screenshots or UI captures and turning sharp text into mush.\nShipping a file that matches the requested dimensions but has the wrong aspect ratio or unsafe crop.\nRecompressing the same JPEG multiple times and blaming the tool instead of the workflow.\nStripping metadata and accidentally breaking orientation, licensing context, or provenance needs.\nForgetting sRGB and wondering why colors shift between editing tools, browsers, and marketplaces.\nUsing SVG where the target platform strips it, rasterizes it badly, or blocks it entirely.\nAssuming AVIF or WebP is safe everywhere when some platforms, email clients, or upload pipelines still normalize back to JPEG or PNG.\nEmbedding critical text into images where HTML or native UI text should have carried the meaning.\nHitting the file-size budget but missing visual quality because the image was resized, cropped, or sharpened badly.\nRasterizing a logo too early and then fighting blurry exports forever.\nShipping a screenshot with secrets, personal data, or unstable timestamps still visible.\nTreating alt text, captions, or chart summaries as someone else's problem after the pixels look good.\nRelated Skills\n\nInstall with clawhub install if user confirms:\n\nimage-edit — Masking, cleanup, inpainting, and targeted visual edits.\nimage-generation — AI image generation and editing across current model providers.\nphotography — Capture, color, and print-oriented photo workflows.\nsvg — Vector graphics workflows when raster files are the wrong output.\necommerce — Marketplace and product-listing requirements that often constrain image delivery.\nFeedback\nIf useful: clawhub star image\nStay updated: clawhub sync" }, "trust": { "sourceLabel": "tencent", "provenanceUrl": "https://clawhub.ai/ivangdavila/image", "publisherUrl": "https://clawhub.ai/ivangdavila/image", "owner": "ivangdavila", "version": "1.0.4", "license": null, "verificationStatus": "Indexed source record" }, "links": { "detailUrl": "https://openagent3.xyz/skills/image", "downloadUrl": "https://openagent3.xyz/downloads/image", "agentUrl": "https://openagent3.xyz/skills/image/agent", "manifestUrl": "https://openagent3.xyz/skills/image/agent.json", "briefUrl": "https://openagent3.xyz/skills/image/agent.md" } }