{ "schemaVersion": "1.0", "item": { "slug": "nano-banana-pro", "name": "Nano Banana Pro", "source": "tencent", "type": "skill", "category": "AI 智能", "sourceUrl": "https://clawhub.ai/steipete/nano-banana-pro", "canonicalUrl": "https://clawhub.ai/steipete/nano-banana-pro", "targetPlatform": "OpenClaw" }, "install": { "downloadMode": "redirect", "downloadUrl": "/downloads/nano-banana-pro", "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=nano-banana-pro", "sourcePlatform": "tencent", "targetPlatform": "OpenClaw", "installMethod": "Manual import", "extraction": "Extract archive", "prerequisites": [ "OpenClaw" ], "packageFormat": "ZIP package", "includedAssets": [ "SKILL.md", "scripts/generate_image.py" ], "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": "nano-banana-pro", "status": "healthy", "reason": "direct_download_ok", "recommendedAction": "download", "checkedAt": "2026-05-02T17:18:09.916Z", "expiresAt": "2026-05-09T17:18:09.916Z", "httpStatus": 200, "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=nano-banana-pro", "contentType": "application/zip", "probeMethod": "head", "details": { "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=nano-banana-pro", "contentDisposition": "attachment; filename=\"nano-banana-pro-1.0.1.zip\"", "redirectLocation": null, "bodySnippet": null, "slug": "nano-banana-pro" }, "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/nano-banana-pro" }, "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/nano-banana-pro", "agentPageUrl": "https://openagent3.xyz/skills/nano-banana-pro/agent", "manifestUrl": "https://openagent3.xyz/skills/nano-banana-pro/agent.json", "briefUrl": "https://openagent3.xyz/skills/nano-banana-pro/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": "Nano Banana Pro Image Generation & Editing", "body": "Generate new images or edit existing ones using Google's Nano Banana Pro API (Gemini 3 Pro Image)." }, { "title": "Usage", "body": "Run the script using absolute path (do NOT cd to skill directory first):\n\nGenerate new image:\n\nuv run ~/.codex/skills/nano-banana-pro/scripts/generate_image.py --prompt \"your image description\" --filename \"output-name.png\" [--resolution 1K|2K|4K] [--api-key KEY]\n\nEdit existing image:\n\nuv run ~/.codex/skills/nano-banana-pro/scripts/generate_image.py --prompt \"editing instructions\" --filename \"output-name.png\" --input-image \"path/to/input.png\" [--resolution 1K|2K|4K] [--api-key KEY]\n\nImportant: Always run from the user's current working directory so images are saved where the user is working, not in the skill directory." }, { "title": "Default Workflow (draft → iterate → final)", "body": "Goal: fast iteration without burning time on 4K until the prompt is correct.\n\nDraft (1K): quick feedback loop\n\nuv run ~/.codex/skills/nano-banana-pro/scripts/generate_image.py --prompt \"\" --filename \"yyyy-mm-dd-hh-mm-ss-draft.png\" --resolution 1K\n\n\nIterate: adjust prompt in small diffs; keep filename new per run\n\nIf editing: keep the same --input-image for every iteration until you’re happy.\n\n\nFinal (4K): only when prompt is locked\n\nuv run ~/.codex/skills/nano-banana-pro/scripts/generate_image.py --prompt \"\" --filename \"yyyy-mm-dd-hh-mm-ss-final.png\" --resolution 4K" }, { "title": "Resolution Options", "body": "The Gemini 3 Pro Image API supports three resolutions (uppercase K required):\n\n1K (default) - ~1024px resolution\n2K - ~2048px resolution\n4K - ~4096px resolution\n\nMap user requests to API parameters:\n\nNo mention of resolution → 1K\n\"low resolution\", \"1080\", \"1080p\", \"1K\" → 1K\n\"2K\", \"2048\", \"normal\", \"medium resolution\" → 2K\n\"high resolution\", \"high-res\", \"hi-res\", \"4K\", \"ultra\" → 4K" }, { "title": "API Key", "body": "The script checks for API key in this order:\n\n--api-key argument (use if user provided key in chat)\nGEMINI_API_KEY environment variable\n\nIf neither is available, the script exits with an error message." }, { "title": "Preflight + Common Failures (fast fixes)", "body": "Preflight:\n\ncommand -v uv (must exist)\ntest -n \\\"$GEMINI_API_KEY\\\" (or pass --api-key)\nIf editing: test -f \\\"path/to/input.png\\\"\n\n\n\nCommon failures:\n\nError: No API key provided. → set GEMINI_API_KEY or pass --api-key\nError loading input image: → wrong path / unreadable file; verify --input-image points to a real image\n“quota/permission/403” style API errors → wrong key, no access, or quota exceeded; try a different key/account" }, { "title": "Filename Generation", "body": "Generate filenames with the pattern: yyyy-mm-dd-hh-mm-ss-name.png\n\nFormat: {timestamp}-{descriptive-name}.png\n\nTimestamp: Current date/time in format yyyy-mm-dd-hh-mm-ss (24-hour format)\nName: Descriptive lowercase text with hyphens\nKeep the descriptive part concise (1-5 words typically)\nUse context from user's prompt or conversation\nIf unclear, use random identifier (e.g., x9k2, a7b3)\n\nExamples:\n\nPrompt \"A serene Japanese garden\" → 2025-11-23-14-23-05-japanese-garden.png\nPrompt \"sunset over mountains\" → 2025-11-23-15-30-12-sunset-mountains.png\nPrompt \"create an image of a robot\" → 2025-11-23-16-45-33-robot.png\nUnclear context → 2025-11-23-17-12-48-x9k2.png" }, { "title": "Image Editing", "body": "When the user wants to modify an existing image:\n\nCheck if they provide an image path or reference an image in the current directory\nUse --input-image parameter with the path to the image\nThe prompt should contain editing instructions (e.g., \"make the sky more dramatic\", \"remove the person\", \"change to cartoon style\")\nCommon editing tasks: add/remove elements, change style, adjust colors, blur background, etc." }, { "title": "Prompt Handling", "body": "For generation: Pass user's image description as-is to --prompt. Only rework if clearly insufficient.\n\nFor editing: Pass editing instructions in --prompt (e.g., \"add a rainbow in the sky\", \"make it look like a watercolor painting\")\n\nPreserve user's creative intent in both cases." }, { "title": "Prompt Templates (high hit-rate)", "body": "Use templates when the user is vague or when edits must be precise.\n\nGeneration template:\n\n“Create an image of: . Style: