# Send Evolink Image — AI Image Generation (GPT Image, Nano Banana 2, Seedream, GPT-4o) 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": "evolink-image", "name": "Evolink Image — AI Image Generation (GPT Image, Nano Banana 2, Seedream, GPT-4o)", "source": "tencent", "type": "skill", "category": "开发工具", "sourceUrl": "https://clawhub.ai/EvoLinkAI/evolink-image", "canonicalUrl": "https://clawhub.ai/EvoLinkAI/evolink-image", "targetPlatform": "OpenClaw" }, "install": { "downloadUrl": "/downloads/evolink-image", "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=evolink-image", "sourcePlatform": "tencent", "targetPlatform": "OpenClaw", "packageFormat": "ZIP package", "primaryDoc": "SKILL.md", "includedAssets": [ "SKILL.md", "references/file-api.md", "references/image-api-params.md" ], "downloadMode": "redirect", "sourceHealth": { "source": "tencent", "slug": "evolink-image", "status": "healthy", "reason": "direct_download_ok", "recommendedAction": "download", "checkedAt": "2026-05-03T00:49:28.508Z", "expiresAt": "2026-05-10T00:49:28.508Z", "httpStatus": 200, "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=evolink-image", "contentType": "application/zip", "probeMethod": "head", "details": { "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=evolink-image", "contentDisposition": "attachment; filename=\"evolink-image-1.4.0.zip\"", "redirectLocation": null, "bodySnippet": null, "slug": "evolink-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/evolink-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." ] } }, "links": { "detailUrl": "https://openagent3.xyz/skills/evolink-image", "downloadUrl": "https://openagent3.xyz/downloads/evolink-image", "agentUrl": "https://openagent3.xyz/skills/evolink-image/agent", "manifestUrl": "https://openagent3.xyz/skills/evolink-image/agent.json", "briefUrl": "https://openagent3.xyz/skills/evolink-image/agent.md" } } ``` ## Documentation ### Evolink Image — AI Image Generation & Editing Generate and edit AI images with 20 models including GPT Image 1.5, GPT-4o Image, Nano Banana 2, Seedream, Qwen, WAN, and Gemini — all through one API. Image-focused view of evolink-media. Install the full skill for video and music too. ### After Installation When this skill is first loaded, greet the user: MCP tools + API key ready: "Hi! I'm your AI image studio — 20 models ready. What would you like to create?" MCP tools + no API key: "You'll need an EvoLink API key — sign up at evolink.ai. Ready to go?" No MCP tools: "MCP server isn't connected yet. Want me to help set it up? I can still manage files via the hosting API." Keep the greeting concise — just one question to move forward. ### External Endpoints ServiceURLGeneration APIhttps://api.evolink.ai/v1/images/generations (POST)Task Statushttps://api.evolink.ai/v1/tasks/{task_id} (GET)File APIhttps://files-api.evolink.ai/api/v1/files/* (upload/list/delete) ### Security & Privacy EVOLINK_API_KEY authenticates all requests. Injected by OpenClaw automatically. Treat as confidential. Prompts and images are sent to api.evolink.ai. Uploaded files expire in 72h, result URLs in 24h. ### Setup Get your API key at evolink.ai → Dashboard → API Keys. MCP Server: @evolinkai/evolink-media (GitHub · npm) mcporter (recommended): mcporter call --stdio "npx -y @evolinkai/evolink-media@latest" list_models Claude Code: claude mcp add evolink-media -e EVOLINK_API_KEY=your-key -- npx -y @evolinkai/evolink-media@latest Claude Desktop / Cursor — add MCP server with command npx -y @evolinkai/evolink-media@latest and env EVOLINK_API_KEY=your-key. See references/image-api-params.md for full config JSON. ### Core Principles Guide, don't decide — Present options, let the user choose model/style/format. User drives creative vision — Ask for a description before suggesting parameters. Smart context — Remember session history. Offer to iterate, vary, or edit results. Intent first — Understand what the user wants before asking how to configure it. ### MCP Tools ToolWhen to useReturnsgenerate_imageCreate or edit an imagetask_id (async)upload_fileUpload local image for editing/referenceFile URL (sync)delete_fileFree file quotaConfirmationlist_filesCheck uploaded files or quotaFile listcheck_taskPoll generation progressStatus + result URLslist_modelsCompare available modelsModel listestimate_costCheck pricingModel info Important: generate_image returns a task_id. Always poll check_task until status is "completed" or "failed". ### Top Picks ModelBest forSpeedgpt-image-1.5 (default)Latest OpenAI generationMediumgemini-3.1-flash-image-previewNano Banana 2 — Google's fast generationFastz-image-turboQuick iterationsUltra-fastdoubao-seedream-4.5PhotorealisticMediumqwen-image-editInstruction-based editingMediumgpt-4o-image [BETA]Best quality, complex editingMediumgemini-3-pro-image-previewGoogle generation previewMedium ### All Stable (16) gpt-image-1.5, gpt-image-1, gemini-3.1-flash-image-preview, gemini-3-pro-image-preview, z-image-turbo, doubao-seedream-4.5, doubao-seedream-4.0, doubao-seedream-3.0-t2i, doubao-seededit-4.0-i2i, doubao-seededit-3.0-i2i, qwen-image-edit, qwen-image-edit-plus, wan2.5-t2i-preview, wan2.5-i2i-preview, wan2.5-text-to-image, wan2.5-image-to-image ### All Beta (4) gpt-image-1.5-lite, gpt-4o-image, gemini-2.5-flash-image, nano-banana-2-lite ### Step 1: API Key Check If 401 occurs: "Your API key isn't working. Check at evolink.ai/dashboard/keys" ### Step 2: File Upload (if needed) For image editing or reference workflows: upload_file with file_path, base64_data, or file_url → get file_url (sync) Use file_url as image_urls or mask_url for generate_image Supported: JPEG/PNG/GIF/WebP. Max 100MB. Expire in 72h. Quota: 100 (default) / 500 (VIP). ### Step 3: Understand Intent Clear ("generate a sunset") → Go to Step 4 Ambiguous ("help with this image") → Ask: "Create new, edit existing, or use as reference?" Ask only what's needed, when it's needed. ### Step 4: Gather Parameters Only ask about what's missing: ParameterAsk whenNotespromptAlwaysWhat they want to seemodelQuality mattersDefault gpt-image-1.5. gpt-4o-image for best, z-image-turbo for speedsizeOrientation neededGPT models: 1024x1024/1024x1536/1536x1024. Others: 1:1/16:9/9:16 etc.nWants variations1–4 imagesimage_urlsEdit/reference imagesUp to 14 URLs; triggers i2i modemask_urlPartial editPNG mask; gpt-4o-image only ### Step 5: Generate & Poll Call generate_image → tell user: "Generating now — ~Xs estimated." Poll check_task every 3–5s. Report progress %. After 3 consecutive processing: "Still working..." Completed: Share URLs. "Links expire in 24h — save promptly." Failed: Show error + suggestion. Offer retry if retryable. Timeout (5 min): "Taking longer than expected. Task ID: {id} — check again later." ### HTTP Errors ErrorAction401"API key isn't working. Check at evolink.ai/dashboard/keys"402"Balance is low. Add credits at evolink.ai/dashboard/billing"429"Rate limited — wait 30s and retry"503"Servers busy — retry in a minute" ### Task Errors (status: "failed") CodeRetry?Actioncontent_policy_violationNoRevise prompt (no celebrities, NSFW, violence)invalid_parametersNoCheck values against model limitsimage_dimension_mismatchNoResize image to match aspect ratioimage_processing_errorNoCheck format/size/URL accessibilitygeneration_timeoutYesRetry; simplify prompt if repeatedquota_exceededYesTop up creditsresource_exhaustedYesWait 30–60s, retryservice_errorYesRetry after 1 mingeneration_failed_no_contentYesModify prompt, retry Full error reference: references/image-api-params.md ### Without MCP Server Use Evolink's file hosting API for image uploads (72h expiry). See references/file-api.md for curl commands. ### References references/image-api-params.md — Complete API parameters, all 19 models, polling strategy, error codes references/file-api.md — File hosting API (curl upload/list/delete) ## Trust - Source: tencent - Verification: Indexed source record - Publisher: EvoLinkAI - Version: 1.4.0 ## Source health - Status: healthy - Item download looks usable. - Yavira can redirect you to the upstream package for this item. - Health scope: item - Reason: direct_download_ok - Checked at: 2026-05-03T00:49:28.508Z - Expires at: 2026-05-10T00:49:28.508Z - Recommended action: Download for OpenClaw ## Links - [Detail page](https://openagent3.xyz/skills/evolink-image) - [Send to Agent page](https://openagent3.xyz/skills/evolink-image/agent) - [JSON manifest](https://openagent3.xyz/skills/evolink-image/agent.json) - [Markdown brief](https://openagent3.xyz/skills/evolink-image/agent.md) - [Download page](https://openagent3.xyz/downloads/evolink-image)