{ "schemaVersion": "1.0", "item": { "slug": "best-image-generation", "name": "Best Image Generation", "source": "tencent", "type": "skill", "category": "开发工具", "sourceUrl": "https://clawhub.ai/EvoLinkAI/best-image-generation", "canonicalUrl": "https://clawhub.ai/EvoLinkAI/best-image-generation", "targetPlatform": "OpenClaw" }, "install": { "downloadMode": "redirect", "downloadUrl": "/downloads/best-image-generation", "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=best-image-generation", "sourcePlatform": "tencent", "targetPlatform": "OpenClaw", "installMethod": "Manual import", "extraction": "Extract archive", "prerequisites": [ "OpenClaw" ], "packageFormat": "ZIP package", "includedAssets": [ "SKILL.md", "references/curl_heredoc.md", "references/powershell.md", "references/python.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": "2026-04-23T16:43:11.935Z", "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/best-image-generation" }, "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/best-image-generation", "agentPageUrl": "https://openagent3.xyz/skills/best-image-generation/agent", "manifestUrl": "https://openagent3.xyz/skills/best-image-generation/agent.json", "briefUrl": "https://openagent3.xyz/skills/best-image-generation/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": "EvoLink Best Image", "body": "Generate and edit images via the EvoLink Nano Banana Pro (gemini-3-pro-image-preview) API." }, { "title": "API Endpoint", "body": "Base: https://api.evolink.ai/v1\nSubmit: POST /images/generations\nPoll: GET /tasks/{id}" }, { "title": "Text-to-image", "body": "{\n \"model\": \"gemini-3-pro-image-preview\",\n \"prompt\": \"\",\n \"size\": \"\",\n \"quality\": \"\"\n}" }, { "title": "Image-to-image / editing", "body": "{\n \"model\": \"gemini-3-pro-image-preview\",\n \"prompt\": \"\",\n \"size\": \"\",\n \"quality\": \"\",\n \"image_urls\": [\"\", \"\"]\n}\n\nParameterValuessizeauto, 1:1, 2:3, 3:2, 3:4, 4:3, 4:5, 5:4, 9:16, 16:9, 21:9quality1K, 2K (default), 4K (extra cost)image_urlsup to 10 URLs (each ≤10MB, formats: jpeg/jpg/png/webp)" }, { "title": "Step 2 — Poll for Result", "body": "GET /tasks/{id} — poll every 10 s, up to 72 retries (~12 min).\n\nWait until status is completed or failed." }, { "title": "Step 3 — Download & Output", "body": "Download the URL from results[0]. Auto-detect format from URL (png/jpg/webp). Save as evolink-..\n\nCRITICAL SECURITY: Before passing to shell commands, sanitize it:\n\nStrip all shell metacharacters: tr -cd 'A-Za-z0-9._-'\nEnsure valid extension (.png, .jpg, .jpeg, .webp)\nFallback to evolink-.png if empty\n\nPrint MEDIA: for OC auto-attach." }, { "title": "Reference Implementations", "body": "PlatformFilePython (all platforms, zero deps){baseDir}/references/python.mdPowerShell 5.1+ (Windows){baseDir}/references/powershell.mdcurl + bash (Unix/macOS){baseDir}/references/curl_heredoc.md" }, { "title": "API Key", "body": "EVOLINK_API_KEY env var (required)\nGet key: https://evolink.ai" }, { "title": "Triggers", "body": "Chinese: \"高质量生图：xxx\" / \"编辑图片：xxx\"\nEnglish: \"best image: xxx\" / \"edit image: xxx\"\n\nTreat the text after the colon as prompt, use default size auto and quality 2K, generate immediately.\n\nFor image-to-image or editing, the user provides image URLs alongside the prompt." }, { "title": "Notes", "body": "Print MEDIA: for OC auto-attach — no extra delivery logic needed.\nImage saved locally (format auto-detected from URL: png/jpg/webp). URL expires ~24h but local file persists.\nquality: 4K incurs additional charges.\nimage_urls accepts up to 10 URLs (each ≤10MB, formats: jpeg/jpg/png/webp)." } ], "body": "EvoLink Best Image\n\nGenerate and edit images via the EvoLink Nano Banana Pro (gemini-3-pro-image-preview) API.\n\nAPI Endpoint\nBase: https://api.evolink.ai/v1\nSubmit: POST /images/generations\nPoll: GET /tasks/{id}\nStep 1 — Submit Task\nText-to-image\n{\n \"model\": \"gemini-3-pro-image-preview\",\n \"prompt\": \"\",\n \"size\": \"\",\n \"quality\": \"\"\n}\n\nImage-to-image / editing\n{\n \"model\": \"gemini-3-pro-image-preview\",\n \"prompt\": \"\",\n \"size\": \"\",\n \"quality\": \"\",\n \"image_urls\": [\"\", \"\"]\n}\n\nParameter\tValues\nsize\tauto, 1:1, 2:3, 3:2, 3:4, 4:3, 4:5, 5:4, 9:16, 16:9, 21:9\nquality\t1K, 2K (default), 4K (extra cost)\nimage_urls\tup to 10 URLs (each ≤10MB, formats: jpeg/jpg/png/webp)\nStep 2 — Poll for Result\n\nGET /tasks/{id} — poll every 10 s, up to 72 retries (~12 min).\n\nWait until status is completed or failed.\n\nStep 3 — Download & Output\n\nDownload the URL from results[0]. Auto-detect format from URL (png/jpg/webp). Save as evolink-..\n\nCRITICAL SECURITY: Before passing to shell commands, sanitize it:\n\nStrip all shell metacharacters: tr -cd 'A-Za-z0-9._-'\nEnsure valid extension (.png, .jpg, .jpeg, .webp)\nFallback to evolink-.png if empty\n\nPrint MEDIA: for OC auto-attach.\n\nReference Implementations\nPlatform\tFile\nPython (all platforms, zero deps)\t{baseDir}/references/python.md\nPowerShell 5.1+ (Windows)\t{baseDir}/references/powershell.md\ncurl + bash (Unix/macOS)\t{baseDir}/references/curl_heredoc.md\nAPI Key\nEVOLINK_API_KEY env var (required)\nGet key: https://evolink.ai\nTriggers\nChinese: \"高质量生图：xxx\" / \"编辑图片：xxx\"\nEnglish: \"best image: xxx\" / \"edit image: xxx\"\n\nTreat the text after the colon as prompt, use default size auto and quality 2K, generate immediately.\n\nFor image-to-image or editing, the user provides image URLs alongside the prompt.\n\nNotes\nPrint MEDIA: for OC auto-attach — no extra delivery logic needed.\nImage saved locally (format auto-detected from URL: png/jpg/webp). URL expires ~24h but local file persists.\nquality: 4K incurs additional charges.\nimage_urls accepts up to 10 URLs (each ≤10MB, formats: jpeg/jpg/png/webp)." }, "trust": { "sourceLabel": "tencent", "provenanceUrl": "https://clawhub.ai/EvoLinkAI/best-image-generation", "publisherUrl": "https://clawhub.ai/EvoLinkAI/best-image-generation", "owner": "EvoLinkAI", "version": "1.0.2", "license": null, "verificationStatus": "Indexed source record" }, "links": { "detailUrl": "https://openagent3.xyz/skills/best-image-generation", "downloadUrl": "https://openagent3.xyz/downloads/best-image-generation", "agentUrl": "https://openagent3.xyz/skills/best-image-generation/agent", "manifestUrl": "https://openagent3.xyz/skills/best-image-generation/agent.json", "briefUrl": "https://openagent3.xyz/skills/best-image-generation/agent.md" } }