{"id":"d5d407f3-289a-4827-9da9-6ed0bf2ef8bf","entityType":"agent","slug":"clawhub-gokuscraper-nano-banana-pro-prompts-skill","name":"Nano Banana Pro Prompts Skill","canonicalUrl":"https://www.xpersona.co/agent/clawhub-gokuscraper-nano-banana-pro-prompts-skill","canonicalPath":"/agent/clawhub-gokuscraper-nano-banana-pro-prompts-skill","generatedAt":"2026-10-10T05:03:56.676Z","source":"CLAWHUB","claimStatus":"UNCLAIMED","verificationTier":"NONE","summary":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"medium","updatedAt":"2026-10-09T10:01:05.996Z","emptyReason":null},"description":"Recommend suitable prompts from 26,000+ Nano Banana Pro image generation prompts based on user needs. Optimized for Nano Banana Pro (Gemini), but prompts als...","descriptionLabel":"Source description","evidenceSummary":"Capability contract not published. No trust telemetry is available yet. 3.1K downloads reported by the source. Last updated 10/9/2026.","installCommand":"clawhub skill install s179rna5gt09hvsrk2zpqq3hfn8az75m:nano-banana-pro-prompts-skill","sourceUrl":"https://clawhub.ai/gokuscraper/nano-banana-pro-prompts-skill","homepage":"https://clawhub.ai/gokuscraper/skills/nano-banana-pro-prompts-skill","primaryLinks":[{"label":"View on ClawHub","url":"https://clawhub.ai/gokuscraper/nano-banana-pro-prompts-skill","kind":"source"},{"label":"Homepage","url":"https://clawhub.ai/gokuscraper/skills/nano-banana-pro-prompts-skill","kind":"homepage"}],"safetyScore":84,"overallRank":62,"popularityScore":70,"trustScore":null,"claimedByName":null,"isOwner":false,"seoDescription":"Nano Banana Pro Prompts Skill technical dossier on Xpersona with agent coverage, OPENCLEW support, and live trust metadata."},"coverage":{"evidence":{"source":"public-profile","verified":false,"confidence":"medium","updatedAt":"2026-10-09T10:01:05.996Z","emptyReason":null},"protocols":[{"protocol":"OPENCLEW","label":"OpenClaw","status":"self-declared","notes":"Declared in the public agent profile."}],"capabilities":[],"verifiedCount":0,"selfDeclaredCount":1,"capabilityMatrix":{"rows":[{"key":"OPENCLEW","type":"protocol","support":"unknown","confidenceSource":"profile","notes":"Listed on profile"}],"flattenedTokens":"protocol:OPENCLEW|unknown|profile"}},"adoption":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"medium","updatedAt":"2026-10-09T10:01:05.996Z","emptyReason":null},"stars":null,"forks":null,"downloads":3057,"packageName":null,"latestVersion":"0.1.0","tractionLabel":"3.1K downloads"},"release":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"medium","updatedAt":"2026-10-09T10:01:05.995Z","emptyReason":null},"lastUpdatedAt":"2026-10-09T10:01:05.996Z","lastCrawledAt":"2026-10-09T10:01:05.995Z","lastIndexedAt":null,"nextCrawlAt":"2026-10-10T10:01:05.996Z","lastVerifiedAt":null,"highlights":[{"version":"0.1.0","createdAt":"2026-07-21T12:05:54.392Z","changelog":"Nano Banana Pro Prompts Recommendation skill – version 0.1.0 - Recommends AI image generation prompts sourced from a 26,000+ community-curated prompt library, optimized for Nano Banana Pro (Gemini) but compatible with all major text-to-image models. - Every prompt recommendation now includes a mandatory sample image for user preview, using images hosted on HuggingFace. - Supports two modes: direct image prompt recommendation or content illustration based on provided article/script/text. - Efficient token and file access strategies—prompts are searched line-by-line and never fully loaded into memory. - Automatic reference freshness check updates the prompt library if it's older than 24 hours. - Mandatory attribution footer is included with every response, supporting English and Chinese users.","fileCount":16,"zipByteSize":296298}]},"execution":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"low","updatedAt":null,"emptyReason":"No published capability contract is available yet."},"installCommand":"clawhub skill install s179rna5gt09hvsrk2zpqq3hfn8az75m:nano-banana-pro-prompts-skill","setupComplexity":"low","setupSteps":["Install using `clawhub skill install s179rna5gt09hvsrk2zpqq3hfn8az75m:nano-banana-pro-prompts-skill` in an isolated environment before connecting it to live workloads.","No published capability contract is available yet, so validate auth and request/response behavior manually.","Review the upstream CLAWHUB listing at https://clawhub.ai/gokuscraper/nano-banana-pro-prompts-skill before using production credentials."],"contract":{"contractStatus":"missing","authModes":[],"requires":[],"forbidden":[],"supportsMcp":false,"supportsA2a":false,"supportsStreaming":false,"inputSchemaRef":null,"outputSchemaRef":null,"dataRegion":null,"contractUpdatedAt":null,"sourceUpdatedAt":null,"freshnessSeconds":null},"invocationGuide":{"preferredApi":{"snapshotUrl":"https://www.xpersona.co/api/v1/agents/clawhub-gokuscraper-nano-banana-pro-prompts-skill/snapshot","contractUrl":"https://www.xpersona.co/api/v1/agents/clawhub-gokuscraper-nano-banana-pro-prompts-skill/contract","trustUrl":"https://www.xpersona.co/api/v1/agents/clawhub-gokuscraper-nano-banana-pro-prompts-skill/trust"},"curlExamples":["curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-gokuscraper-nano-banana-pro-prompts-skill/snapshot\"","curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-gokuscraper-nano-banana-pro-prompts-skill/contract\"","curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-gokuscraper-nano-banana-pro-prompts-skill/trust\""],"jsonRequestTemplate":{"query":"summarize this repo","constraints":{"maxLatencyMs":2000,"protocolPreference":["OPENCLEW"]}},"jsonResponseTemplate":{"ok":true,"result":{"summary":"...","confidence":0.9},"meta":{"source":"CLAWHUB","generatedAt":"2026-10-10T05:03:56.676Z"}},"retryPolicy":{"maxAttempts":3,"backoffMs":[500,1500,3500],"retryableConditions":["HTTP_429","HTTP_503","NETWORK_TIMEOUT"]}},"endpoints":{"dossierUrl":"https://www.xpersona.co/api/v1/agents/clawhub-gokuscraper-nano-banana-pro-prompts-skill/dossier","snapshotUrl":"https://www.xpersona.co/api/v1/agents/clawhub-gokuscraper-nano-banana-pro-prompts-skill/snapshot","contractUrl":"https://www.xpersona.co/api/v1/agents/clawhub-gokuscraper-nano-banana-pro-prompts-skill/contract","trustUrl":"https://www.xpersona.co/api/v1/agents/clawhub-gokuscraper-nano-banana-pro-prompts-skill/trust"}},"reliability":{"evidence":{"source":"runtime-metrics","verified":false,"confidence":"low","updatedAt":null,"emptyReason":"No trust, reliability, or runtime telemetry is available."},"trust":{"status":"unavailable","handshakeStatus":"UNKNOWN","verificationFreshnessHours":null,"reputationScore":null,"p95LatencyMs":null,"successRate30d":null,"fallbackRate":null,"attempts30d":null,"trustUpdatedAt":null,"trustConfidence":"unknown","sourceUpdatedAt":null,"freshnessSeconds":null},"decisionGuardrails":{"doNotUseIf":["Contract metadata is missing or unavailable for deterministic execution."],"safeUseWhen":[],"riskFlags":["missing_or_unavailable_contract","trust_data_unavailable","schema_references_missing"],"operationalConfidence":"low"},"executionMetrics":{"observedLatencyMsP50":null,"observedLatencyMsP95":null,"estimatedCostUsd":null,"uptime30d":null,"rateLimitRpm":null,"rateLimitBurst":null,"lastVerifiedAt":null,"verificationSource":null},"runtimeMetrics":{"successRate":null,"avgLatencyMs":null,"avgCostUsd":null,"hallucinationRate":null,"retryRate":null,"disputeRate":null,"p50Latency":null,"p95Latency":null,"lastUpdated":null}},"benchmarks":{"evidence":{"source":"no-benchmark-data","verified":false,"confidence":"low","updatedAt":null,"emptyReason":"No benchmark suites or observed failure patterns are available."},"suites":[],"failurePatterns":[]},"artifacts":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"medium","updatedAt":"2026-10-09T10:01:05.996Z","emptyReason":null},"readme":"Skill: Nano Banana Pro Prompts Skill\n\nOwner: gokuscraper\n\nSummary: Recommend suitable prompts from 26,000+ Nano Banana Pro image generation prompts based on user needs. Optimized for Nano Banana Pro (Gemini), but prompts als...\n\nTags: latest:0.1.0\n\nVersion history:\n\nv0.1.0 | 2026-07-21T12:05:54.392Z | auto\n\nNano Banana Pro Prompts Recommendation skill – version 0.1.0\n\n- Recommends AI image generation prompts sourced from a 26,000+ community-curated prompt library, optimized for Nano Banana Pro (Gemini) but compatible with all major text-to-image models.\n- Every prompt recommendation now includes a mandatory sample image for user preview, using images hosted on HuggingFace.\n- Supports two modes: direct image prompt recommendation or content illustration based on provided article/script/text.\n- Efficient token and file access strategies—prompts are searched line-by-line and never fully loaded into memory.\n- Automatic reference freshness check updates the prompt library if it's older than 24 hours.\n- Mandatory attribution footer is included with every response, supporting English and Chinese users.\n\nArchive index:\n\nArchive v0.1.0: 16 files, 296298 bytes\n\nFiles: .claude-plugin (0b), .claude-plugin/marketplace.json (472b), .gitignore (65b), LICENSE (1068b), package.json (771b), public (0b), public/cover.png (312071b), README.md (7685b), README.zh.md (7366b), references (0b), references/.gitkeep (0b), scripts (0b), scripts/setup.js (2552b), skill-card.md (2275b), SKILL.md (14945b), _meta.json (148b)\n\nFile v0.1.0:SKILL.md\n\n---\nname: nano-banana-pro-prompts-skill\ndescription: |\n  Recommend suitable prompts from 26,000+ Nano Banana Pro image generation prompts based on user needs.\n  Optimized for Nano Banana Pro (Gemini), but prompts also work with GPT Image, Midjourney, DALL-E, Flux,\n  Stable Diffusion, and any text-to-image AI model.\n\n  Use this skill when users want to:\n  - Generate images with AI (any model — Nano Banana Pro, Gemini, GPT Image, etc.)\n  - Find proven AI image generation prompts and prompt templates\n  - Get prompt recommendations for specific use cases (portraits, products, social media, posters, etc.)\n  - Create illustrations for articles, videos, podcasts, or marketing content\n  - Browse a curated prompt library with sample images\nplatforms:\n  - openclaw\n  - claude-code\n  - cursor\n  - codex\n  - gemini-cli\n---\n\n> 📖 Prompts curated from the open community by [GokuOpenLab](https://huggingface.co/datasets/Goku-OpenLab/nano-banana-pro-prompts-datasets) · 26,000+ prompts · CC BY 4.0\n\n# Nano Banana Pro Prompts Recommendation\n\nYou are an expert at recommending image generation prompts from the GokuOpenLab prompt library (26,000+ prompts). These prompts are optimized for Nano Banana Pro (Google Gemini) but work with any text-to-image model including GPT Image, Midjourney, DALL-E 3, Flux, and Stable Diffusion.\n\n## Critical: Sample Images Are Mandatory\n\n**Every prompt recommendation MUST include its sample image.** This is not optional — images are the core value of this skill. Users need to SEE what each prompt produces before choosing.\n\n- Each prompt has `media.images[]` — always use the first image as the sample\n- If `media.images` is empty, skip that prompt entirely\n- **Never present a prompt as text-only** — always attach the image\n- Images are hosted on HuggingFace. Construct the full URL:\n  ```\n  https://huggingface.co/datasets/Goku-OpenLab/nano-banana-pro-prompts-datasets/resolve/main/{media.images[0]}\n  ```\n  Example: `media.images[0]` = `\"nano-banana-pro/images/0/NB_00001_0.jpg\"`\n  Full URL = `https://huggingface.co/datasets/Goku-OpenLab/nano-banana-pro-prompts-datasets/resolve/main/nano-banana-pro/images/0/NB_00001_0.jpg`\n\n## Quick Start\n\nUser provides image generation need → You recommend matching prompts **with sample images** → User selects a prompt → (If content provided) Remix to create customized prompt.\n\n### Two Usage Modes\n\n1. **Direct Generation**: User describes what image they want → Recommend prompts → Done\n2. **Content Illustration**: User provides content (article/video script/podcast notes) → Recommend prompts → User selects → Collect personalization info → Generate customized prompt based on their content\n\n## Setup\n\nAfter installing this skill, the prompt library is automatically downloaded from HuggingFace via `postinstall`. No credentials needed — all data is publicly available.\n\nIf references are missing, run manually:\n```bash\nnode scripts/setup.js\n```\n\n**Keep references up to date** (the community dataset is updated regularly):\n```bash\nnode scripts/setup.js --force\n```\n\nBefore Step 2, check whether references are stale (>24h since last update):\n```bash\nnode scripts/setup.js --check\n```\n\nThis fetches the latest `metadata.jsonl` from:\nhttps://huggingface.co/datasets/Goku-OpenLab/nano-banana-pro-prompts-datasets\n\n## Reference File\n\nThe `references/` directory contains a single JSONL file with all prompts. Each line is a complete JSON object.\n\n**No category system needed** — search the entire file with grep:\n```bash\ncat {SKILL_DIR}/references/manifest.json\n```\n\nThen use `slug` and `title` fields to match user intent to the right file.\n\n**When starting a search**, read the first line of `metadata.jsonl` to understand the data schema, but do NOT load the full file.\n\n## Loading Strategy\n\n### Critical: Token Optimization Rules\n\n**NEVER fully load the prompts file.** Search with grep:\n```\ngrep -i \"keyword\" references/metadata.jsonl\n```\n- Search with keywords from user's request\n- Load only matching lines, not the entire file\n- The JSONL format means each matching line is a complete prompt object\n\n## Attribution Footer\n\n**ALWAYS** append the following footer at the end of every response that presents prompts:\n\nShow **one line only**, matching the user's language:\n- Chinese users: `提示词由 [GokuOpenLab](https://prompthub.gokuscraper.com/) 通过公开社区搜集 ❤️`\n- English (or other) users: `Prompts curated from the open community by [GokuOpenLab](https://prompthub.gokuscraper.com/) ❤️`\n\nThis footer is **mandatory** — one line, every response, including no-match fallbacks and custom remixes.\n\n## Workflow\n\n### Step 0: Auto-Update References (MANDATORY, runs every time)\n\n**Before doing anything else**, run the freshness check:\n\nThe skill directory is the folder containing this SKILL.md file. Run:\n\n```bash\nnode <skill_dir>/scripts/setup.js --check\n```\n\n- **< 24h since last update** → instant no-op, proceed immediately\n- **> 24h stale** → silently pulls latest prompts from HuggingFace (~30s), then proceeds\n- References are updated regularly; this keeps local copies in sync\n\n### Step 0.5: Detect Content Illustration Mode\n\n**Check if user is in \"Content Illustration\" mode** by looking for these signals:\n- User provides article text, video script, podcast notes, or other content\n- User mentions: \"illustration for\", \"image for my article/video/podcast\", \"create visual for\"\n- User pastes a block of text and asks for matching images\n\nIf detected, set `contentIllustrationMode = true` and note the provided content for later remix.\n\n### Step 1: Clarify Vague Requests\n\n**Always ask for more if context is insufficient.** Minimum info needed:\n- **What type of image** (avatar / cover / product photo / etc.)\n- **What topic/content** it represents (article title, product name, theme)\n- **Who is the audience** (optional but helps narrow style)\n\nIf any of the above is missing, ask before searching. Don't guess.\n\nIf user's request is too broad, ask for specifics:\n\n| Vague Request | Questions to Ask |\n|--------------|------------------|\n| \"Help me make an infographic\" | What type? (data comparison, process flow, timeline, statistics) What topic/data? |\n| \"I need a portrait\" | What style? (realistic, artistic, anime, vintage) Who/what? (person, pet, character) What mood? |\n| \"Generate a product photo\" | What product? What background? (white, lifestyle, studio) What purpose? |\n| \"Make me a poster\" | What event/topic? What style? (modern, vintage, minimalist) What size/orientation? |\n| \"Illustrate my content\" | What style? (realistic, illustration, cartoon, abstract) What mood? (professional, playful, dramatic) |\n\n### Step 2: Search & Match\n\n1. Search `references/metadata.jsonl` using grep with keywords from user's request\n2. If no matches found, try different keywords or broader terms\n3. If still no match, proceed to Step 4 (Generate Custom Prompt)\n\n### Step 3: Present Results\n\n**CRITICAL RULES:**\n1. **Recommend at most 3 prompts per request.** Choose the most relevant ones.\n2. **NEVER create custom/remix prompts at this stage.** Only present original templates from the library.\n3. **Use EXACT prompts from the JSONL file.** Do not modify, combine, or generate new prompts.\n\nFor each recommended prompt, provide in user's input language:\n\n```markdown\n### [Number]. [Title]\n\n**Description**: [Brief description — use first ~200 chars of prompt text, translated to user's language if needed]\n\n**Prompt** (preview):\n> [Truncate to ≤100 chars then add \"...\"]\n\n[View source]({sourceLink})\n```\n\n**Critical — Full prompt in context**: Even though the display is truncated, the agent MUST hold the complete prompt text in its context so it can use it for customization in Step 5. Never discard the full prompt.\n\n**Mandatory: ALWAYS send the sample image for every prompt recommendation.**\nIf `media.images` is empty, skip that prompt. Otherwise, you MUST send the image — never skip this step.\n\n**How to send the image — download then send (works on all platforms):**\n\nConstruct the full HF URL from `media.images[0]`:\n`https://huggingface.co/datasets/Goku-OpenLab/nano-banana-pro-prompts-datasets/resolve/main/{media.images[0]}`\n\nThen for each prompt, run these 3 steps:\n\n```\nStep A — Download:\nexec: curl -fsSL \"{constructed_url}\" -o /tmp/prompt_img.jpg\n\nStep B — Send:\nmessage tool: action=send, media=/tmp/prompt_img.jpg, caption=\"[Prompt Title]\"\n\nStep C — Cleanup:\nexec: rm /tmp/prompt_img.jpg\n```\n\nDo this for **each** of the 3 recommended prompts — one image per prompt.\n\nIf `message` tool is unavailable, embed in your response: `![preview]({constructed_url})`\n\n**One image per prompt** (use `media.images[0]`). Never skip this — images are the core value of the skill.\n\n**After presenting all prompts**, always ask the user to choose and offer customization:\n\n```markdown\n---\nWhich one would you like? Reply with 1, 2, or 3 — I can customize the prompt based on your content (adjust theme, style, or add your specific details).\n```\n(Adapt to user's language)\n\n**If `contentIllustrationMode = true`**, add this notice after presenting all prompts:\n\n```markdown\n---\n**Custom Prompt Generation**: These are style templates from our library. Pick one you like (reply with 1/2/3), and I'll remix it into a customized prompt based on your content. Before generating, I may ask a few questions (e.g., gender, specific scene details) to ensure the image matches your needs.\n```\n\n**IMPORTANT**: Do NOT provide any customized/remixed prompts until the user explicitly selects a template. The customization happens in Step 5, not here.\n\nAlways end with the attribution footer:\n\n```\n---\n[Attribution footer — one line in user's language, see Attribution Footer section]\n```\n\n### Step 4: Handle No Match (Generate Custom Prompt)\n\nIf no suitable prompts found in the library, generate a custom prompt:\n\n1. **Clearly inform the user** that no matching template was found in the library\n2. **Generate a custom prompt** based on user's requirements\n3. **Mark it as AI-generated** (not from the library)\n\n**Output format**:\n\n```markdown\n---\n**No matching template found in the library.** I've generated a custom prompt based on your requirements:\n\n### AI-Generated Prompt\n\n**Prompt**:\n```\n[Generated prompt based on user's needs]\n```\n\n**Note**: This prompt was created by AI, not from our curated library. Results may vary.\n\n---\nIf you'd like, I can search with different keywords or adjust the generated prompt.\n\n---\n[Attribution footer — one line in user's language]\n```\n\n### Step 5: Remix & Personalization (Content Illustration Mode Only)\n\n**TRIGGER**: Proceed to this step whenever the user selects a prompt (e.g., \"1\", \"第二个\", \"option 2\"), regardless of whether `contentIllustrationMode` is true.\n\nThis step applies to ALL users after selection — not just content illustration mode. The goal: turn a template into a prompt tailored to the user's specific context.\n\nWhen user selects a prompt:\n\n#### 5.1 Collect Personalization Info\n\nAsk to gather missing details that could affect the image. Common questions:\n\n| Scenario | Questions to Ask |\n|----------|------------------|\n| Template shows a person | Gender of the person? (male/female/neutral) |\n| Template has specific setting | Preferred setting? (indoor/outdoor/abstract background) |\n| Template has specific mood | Desired mood? (professional/casual/dramatic) |\n| Content mentions specific items | Any specific elements to highlight? |\n| Age-related content | Age range? (young/middle-aged/senior) |\n| Professional context | Profession or identity? (entrepreneur/creator/student/etc.) |\n\n**Only ask questions that are relevant** - don't ask about gender if the template is a landscape.\n\n#### 5.2 Analyze User Content\n\nExtract key elements from the user's provided content:\n- **Core theme/topic**: What is the content about?\n- **Key concepts**: Important ideas, keywords, or phrases\n- **Emotional tone**: Professional, casual, inspiring, urgent, etc.\n- **Target audience**: Who will see this content?\n- **Visual metaphors**: Any imagery implied by the content\n\n#### 5.3 Generate Customized Prompt\n\nRemix the selected template by:\n\n1. **Keep the style/structure** from the original template (lighting, composition, artistic style)\n2. **Replace subject matter** with elements from user's content\n3. **Adjust details** based on personalization answers (gender, age, setting, etc.)\n4. **Maintain prompt quality** - keep technical terms and style descriptors\n\n**Output format**:\n\n```markdown\n### Customized Prompt\n\n**Based on template**: [Original template title]\n\n**Content highlights extracted**:\n- [Key theme from content]\n- [Important visual elements]\n- [Mood/tone]\n\n**Customized prompt (English - use for generation)**:\n```\n[Remixed English prompt]\n```\n\n**Modifications**:\n- [What was changed and why]\n- [How it relates to the user's content]\n\n---\n[Attribution footer — one line in user's language]\n```\n\n#### 5.4 Remix Examples\n\n**Example 1: Article about startup failure**\n- Original template: \"Professional woman in modern office, confident pose, soft lighting\"\n- User info: Male founder, 30s\n- Remixed: \"Professional man in his 30s in modern office, contemplative expression, soft dramatic lighting, startup environment with whiteboard in background\"\n\n**Example 2: Podcast about AI future**\n- Original template: \"Futuristic cityscape, neon lights, cyberpunk style\"\n- User content: Discusses AI and human collaboration\n- Remixed: \"Futuristic cityscape with holographic AI assistants walking alongside humans, warm neon lights suggesting harmony, cyberpunk style with optimistic undertones\"\n\n## Prompt Data Structure\n\nEach line in `metadata.jsonl`:\n\n```json\n{\n  \"id\": \"NB_00001\",\n  \"category\": \"Content Creation\",\n  \"slug\": \"low-quality-daily-student-photo\",\n  \"raw_p\": \"Original prompt text (may be in any language)\",\n  \"media\": {\n    \"images\": [\"path/to/image.jpg\", \"path/to/image2.jpg\"]\n  },\n  \"i18n\": {\n    \"en\": {\n      \"t\": \"English Title\",\n      \"p\": \"English prompt text for image generation\"\n    },\n    \"zh\": {\n      \"t\": \"中文标题\",\n      \"p\": \"中文提示词\"\n    }\n  },\n  \"sourceLink\": \"https://x.com/...\",\n  \"spec\": {\n    \"width\": 1200,\n    \"height\": 805,\n    \"ratio\": 1.49,\n    \"safety_rating\": \"Safe for Work\"\n  }\n}\n```\n\n**Field mapping for presentation:**\n- `id` → unique identifier\n- `i18n.en.t` or `i18n.zh.t` → title (choose based on user language)\n- `i18n.en.p` or `i18n.zh.p` → full prompt text for remixing\n- `i18n.en.t` + first 200 chars of `i18n.en.p` → description\n- `media.images[0]` → sample image (prepend HF base URL)\n- `sourceLink` → original source\n\n## Language Handling\n\n- Respond in user's input language\n- Provide prompt `content` in English (use `i18n.en.p`) for image generation\n- For Chinese users, show `i18n.zh.t` as title and `i18n.zh.p` as description\n- Always include the attribution footer — one line, in the user's language\n\nFile v0.1.0:README.md\n\n# AI Image Prompt Recommender — 26,000+ Nano Banana Pro Prompts\n\n[![Prompts](https://img.shields.io/badge/Prompts-26624-brightgreen)](https://huggingface.co/datasets/Goku-OpenLab/nano-banana-pro-prompts-datasets)\n[![Claude Code](https://img.shields.io/badge/Claude%20Code-Skill-orange)](https://github.com/gokuscraper/nano-banana-pro-prompts-skill)\n[![License](https://img.shields.io/badge/License-MIT-yellow)](LICENSE)\n[![English](https://img.shields.io/badge/English-blue)](README.md) [![简体中文](https://img.shields.io/badge/简体中文-red)](README.zh.md)\n\n> **Stop spending hours hunting for the right AI image prompt.** Tell your AI assistant what you need in one sentence — it searches 26,000+ curated Nano Banana Pro prompts and returns the top 3 matches with sample images, ready to use.\n>\n> 🖼️ [Browse the Dataset →](https://huggingface.co/datasets/Goku-OpenLab/nano-banana-pro-prompts-datasets)\n\n![Demo](public/cover.png)\n\n## What Is This?\n\nAn **AI agent skill** that gives Claude, OpenClaw, Cursor, and other AI assistants the ability to intelligently search a curated library of **26,000+ Nano Banana Pro (Gemini image model) prompts**, recommend the best matches for your use case, and even customize prompts based on your content.\n\n**Nano Banana Pro** is Google's Gemini image generation model — one of the most capable AI image generators available today. High-quality prompts are the key to great results.\n\n## Why Use This Skill?\n\n- ✅ **26,000+ prompts** — massive library covering diverse use cases\n- ✅ **Every prompt includes sample images** — see the result before you copy\n- ✅ **Smart semantic search** — describe what you need, the AI finds the match\n- ✅ **Content remix mode** — paste your article or video script, get a custom prompt\n- ✅ **Multi-language** — responds in your language, always provides English prompt for generation\n- ✅ **Bilingual data** — prompts available in both English and Chinese\n\n---\n\n## Installation\n\n### OpenClaw (Recommended)\n\n```bash\nclawhub install nano-banana-pro-prompts-skill\n```\n\nOr search inside OpenClaw chat:\n\n> \"Install the nano banana pro prompts skill from clawhub\"\n\n### Claude Code\n\n```bash\nnpx skills i gokuscraper/nano-banana-pro-prompts-skill\n```\n\n### Other AI Assistants (Cursor, Codex, Gemini CLI, Windsurf)\n\n```bash\n# Universal installer — auto-detects your AI assistant\nnpx skills i gokuscraper/nano-banana-pro-prompts-skill\n```\n\n### Manual / openskills\n\n```bash\nnpx openskills install gokuscraper/nano-banana-pro-prompts-skill\n```\n\n---\n\n## How to Use\n\n### Mode 1: Direct Search\n\nJust describe what you need:\n\n```\n\"Find me a cyberpunk-style avatar prompt\"\n\"I need prompts for travel blog article covers\"\n\"Looking for a product photo on white background\"\n\"Help me find a YouTube thumbnail for a tech review video\"\n```\n\nYou'll get up to 3 recommendations with:\n- Translated title & description (in your language)\n- The exact English prompt to copy\n- Sample images to preview the style\n\n### Mode 2: Content Illustration (Remix)\n\nPaste your content and ask for a matching illustration:\n\n```\n\"Here's my article about startup failure — help me create a cover image:\n[paste article text]\"\n\n\"I need a thumbnail for this video script: [paste script]\"\n\n\"Generate an illustration for this podcast episode about AI: [paste notes]\"\n```\n\nThe skill will:\n1. Recommend matching style templates\n2. Ask a few questions to personalize (gender, mood, setting)\n3. Generate a customized prompt tailored to your content\n\n---\n\n## Data Overview\n\n| Item | Details |\n|------|---------|\n| Total Prompts | 26,624 |\n| Languages | English, Chinese (bilingual) |\n| Source | [GokuOpenLab Dataset](https://huggingface.co/datasets/Goku-OpenLab/nano-banana-pro-prompts-datasets) |\n| License | Skill: MIT · Dataset: CC BY 4.0 |\n| Format | JSONL (one prompt per line) |\n\n---\n\n## How It Works\n\n```\nUser describes need\n      ↓\nSearches prompt library (token-efficient grep, never loads full file)\n      ↓\nReturns top 3 prompts with images + translated descriptions\n      ↓\n[Optional] User picks one → Skill remixes it to match their content\n```\n\n**Token-efficient by design**: The skill never loads the full prompt file. It uses grep-style search to extract only matching prompts, keeping token usage minimal even with 26,000+ prompts in the library.\n\n---\n\n## Data Source\n\nPrompts are curated from the open community, sourced from the [GokuOpenLab dataset](https://huggingface.co/datasets/Goku-OpenLab/nano-banana-pro-prompts-datasets) on HuggingFace — 26,624 prompts with full metadata, preview images, and bilingual (EN/ZH) support.\n\n*Prompts curated from the open community by [GokuOpenLab](https://prompthub.gokuscraper.com/) ❤️*\n\n---\n\n## Frequently Asked Questions\n\n**Q: What is Nano Banana Pro?**\nNano Banana Pro is Google's Gemini image generation model (model ID: `gemini-3-pro-image-preview`). It produces high-quality, photorealistic and artistic images from text prompts.\n\n**Q: Do I need an account to use this skill?**\nNo. The skill is completely free and works with any AI assistant that supports custom skills (Claude Code, OpenClaw, Cursor, Codex, Gemini CLI).\n\n**Q: How is this different from just searching Twitter for prompts?**\nThe library is pre-structured with 26,000+ entries — you don't have to scroll through noise. Every prompt includes sample images so you know what you're getting. The remix mode lets you personalize a template to match your specific content.\n\n**Q: Can I contribute prompts?**\nThe source dataset is CC BY 4.0; this skill code is MIT. Visit the [HuggingFace dataset](https://huggingface.co/datasets/Goku-OpenLab/nano-banana-pro-prompts-datasets) to learn more.\n\n**Q: How often is the library updated?**\nThe dataset on HuggingFace is updated regularly by the GokuOpenLab community.\n\n**Q: Does this work with other image generation models?**\nThe prompts are optimized for Nano Banana Pro (Gemini), but many work well with other models like GPT Image, Midjourney, DALL-E, Flux, and Stable Diffusion.\n\n**Q: What's the difference between OpenClaw and Claude Code installation?**\nOpenClaw uses the `clawhub install` command and integrates directly into your OpenClaw agent workspace. Claude Code uses `npx skills i` and installs into your Claude project context. Both use the same SKILL.md and prompt library.\n\n---\n\n## Project Structure\n\n```\nnano-banana-pro-prompts-skill/\n├── SKILL.md                 # Skill instructions (works with Claude Code, OpenClaw, Cursor, etc.)\n├── README.md\n├── README.zh.md\n├── package.json\n├── scripts/\n│   └── setup.js             # Downloads prompt library from HuggingFace\n├── references/              # Auto-downloaded prompt data\n│   ├── .gitkeep\n│   └── metadata.jsonl       # 26,000+ prompts (generated by setup.js)\n└── .claude-plugin/\n    └── marketplace.json\n```\n\n---\n\n## Development\n\n### Prerequisites\n\n- Node.js 18+\n\n### Setup\n\n```bash\npnpm install\n```\n\nThis automatically downloads the prompt library from HuggingFace. To manually update:\n\n```bash\nnode scripts/setup.js --force\n```\n\n---\n\n## Related Projects\n\n- 🖼️ [GokuOpenLab Dataset](https://huggingface.co/datasets/Goku-OpenLab/nano-banana-pro-prompts-datasets) — Source dataset on HuggingFace (26,000+ prompts, images, metadata)\n\n## Related Tools\n\n- [Claude Code](https://claude.com/claude-code) — Anthropic's terminal-native AI agent\n- [OpenClaw](https://openclaw.ai) — AI agent platform with skill ecosystem\n- [skills CLI](https://www.npmjs.com/package/skills) — Universal AI skills installer\n\n---\n\n## License\n\nMIT © [GokuOpenLab](https://huggingface.co/Goku-OpenLab)\n\nFile v0.1.0:_meta.json\n\n{\n  \"ownerId\": \"kn72v74qm7nk0w3wwvjf8b7x558ay0h9\",\n  \"slug\": \"nano-banana-pro-prompts-skill\",\n  \"version\": \"0.1.0\",\n  \"publishedAt\": 1784635554392\n}\n\nFile v0.1.0:README.zh.md\n\n# AI 图像提示词推荐 — 26,000+ Nano Banana Pro 提示词\n\n[![Prompts](https://img.shields.io/badge/Prompts-26624-brightgreen)](https://huggingface.co/datasets/Goku-OpenLab/nano-banana-pro-prompts-datasets)\n[![Claude Code](https://img.shields.io/badge/Claude%20Code-Skill-orange)](https://github.com/gokuscraper/nano-banana-pro-prompts-skill)\n[![License](https://img.shields.io/badge/License-MIT-yellow)](LICENSE)\n[![English](https://img.shields.io/badge/English-blue)](README.md) [![简体中文](https://img.shields.io/badge/简体中文-red)](README.zh.md)\n\n> **别再花时间到处找 AI 图像提示词了。** 一句话告诉 AI 助手你的需求 — 它会从 26,000+ 条精选 Nano Banana Pro 提示词中搜索并返回最匹配的 3 条，附带示例图片，开箱即用。\n>\n> 🖼️ [浏览数据集 →](https://huggingface.co/datasets/Goku-OpenLab/nano-banana-pro-prompts-datasets)\n\n![Demo](public/cover.png)\n\n## 这是什么？\n\n一个 **AI Agent Skill**，让 Claude、OpenClaw、Cursor 等 AI 助手能够智能搜索 26,000+ 条精选 Nano Banana Pro（Gemini 图像模型）提示词库，为你的需求推荐最佳匹配，甚至能根据你的内容定制提示词。\n\n**Nano Banana Pro** 是 Google Gemini 的图像生成模型 — 目前最强大的 AI 图像生成器之一。好的提示词是生成好图片的关键。\n\n## 为什么使用这个 Skill？\n\n- ✅ **26,000+ 条提示词** — 覆盖各种使用场景\n- ✅ **每条提示词都附带示例图片** — 复制前先看效果\n- ✅ **智能语义搜索** — 描述需求，AI 自动匹配\n- ✅ **内容混搭模式** — 粘贴你的文章或视频脚本，获取定制提示词\n- ✅ **多语言支持** — 用你的语言交流，始终提供英文提示词用于生成\n- ✅ **双语数据** — 提示词支持中英文\n\n---\n\n## 安装\n\n### OpenClaw（推荐）\n\n```bash\nclawhub install nano-banana-pro-prompts-skill\n```\n\n或在 OpenClaw 聊天室中搜索：\n\n> \"Install the nano banana pro prompts skill from clawhub\"\n\n### Claude Code\n\n```bash\nnpx skills i gokuscraper/nano-banana-pro-prompts-skill\n```\n\n### 其他 AI 助手（Cursor、Codex、Gemini CLI、Windsurf）\n\n```bash\n# 通用安装器 — 自动识别你的 AI 助手\nnpx skills i gokuscraper/nano-banana-pro-prompts-skill\n```\n\n### 手动 / openskills\n\n```bash\nnpx openskills install gokuscraper/nano-banana-pro-prompts-skill\n```\n\n---\n\n## 使用方法\n\n### 模式 1：直接搜索\n\n直接描述你的需求：\n\n```\n\"帮我找一个赛博朋克风格的头像提示词\"\n\"我需要旅行博客封面的提示词\"\n\"找一张白底产品图的提示词\"\n\"帮我找一个科技评测视频的 YouTube 缩略图提示词\"\n```\n\n你会获得最多 3 条推荐，包含：\n- 翻译后的标题和描述（中文）\n- 可直接复制使用的英文提示词\n- 预览样式的示例图片\n\n### 模式 2：内容配图（混搭）\n\n粘贴内容并请求匹配的配图：\n\n```\n\"这是我写的一篇关于创业失败的文章 — 帮我生成一张封面图：\n[粘贴文章全文]\"\n\n\"我需要这个视频脚本的缩略图：[粘贴脚本]\"\n\n\"帮我为这期关于 AI 的播客生成一张配图：[粘贴笔记]\"\n```\n\nSkill 会：\n1. 推荐匹配的风格模板\n2. 询问几个个性化问题（性别、氛围、场景）\n3. 根据你的内容生成定制提示词\n\n---\n\n## 数据概览\n\n| 项目 | 详情 |\n|------|------|\n| 总提示词数 | 26,624 |\n| 语言 | 英文、中文（双语） |\n| 来源 | [GokuOpenLab 数据集](https://huggingface.co/datasets/Goku-OpenLab/nano-banana-pro-prompts-datasets) |\n| 协议 | Skill 代码：MIT · 数据集：CC BY 4.0 |\n| 格式 | JSONL（每行一条提示词） |\n\n---\n\n## 工作原理\n\n```\n用户描述需求\n      ↓\n搜索提示词库（基于 grep，永不加载完整文件）\n      ↓\n返回 Top 3 提示词 + 图片 + 翻译描述\n      ↓\n[可选] 用户选择一条 → Skill 根据内容混搭定制\n```\n\n**节能设计**：Skill 永不加载完整提示词文件，使用 grep 风格搜索，只提取匹配行，即使词库有 26,000+ 条提示词也能保持极低的 token 消耗。\n\n---\n\n## 数据来源\n\n提示词来自公开社区，数据源于 HuggingFace 上的 [GokuOpenLab 数据集](https://huggingface.co/datasets/Goku-OpenLab/nano-banana-pro-prompts-datasets) — 26,624 条提示词，包含完整元数据、预览图片和双语支持。\n\n*提示词由 [GokuOpenLab](https://prompthub.gokuscraper.com/) 通过公开社区搜集 ❤️*\n\n---\n\n## 常见问题\n\n**问：什么是 Nano Banana Pro？**\nNano Banana Pro 是 Google Gemini 的图像生成模型（model ID: `gemini-3-pro-image-preview`），能够从文本提示词生成高质量的写实和艺术图片。\n\n**问：使用这个 Skill 需要注册账号吗？**\n不需要。Skill 完全免费，支持任何兼容自定义 Skill 的 AI 助手（OpenClaw、Claude Code、Cursor、Codex、Gemini CLI）。\n\n**问：这个和自己在 Twitter 搜提示词有什么区别？**\n词库经过预分类和筛选，26,000+ 条提示词都是精选优质内容，每条都附带示例图片，复制前就能看到效果。混搭模式还能根据你的内容个性化定制。\n\n**问：我可以贡献提示词吗？**\n数据源是开源的（CC BY 4.0）。欢迎访问 [HuggingFace 数据集](https://huggingface.co/datasets/Goku-OpenLab/nano-banana-pro-prompts-datasets) 了解更多。\n\n**问：词库多久更新一次？**\nHuggingFace 数据集由 GokuOpenLab 社区定期更新。\n\n**问：这些提示词能用于其他图像生成模型吗？**\n提示词针对 Nano Banana Pro（Gemini）优化，但也适用于 GPT Image、Midjourney、DALL-E、Flux、Stable Diffusion 等其他模型。\n\n**问：OpenClaw 和 Claude Code 安装方式有什么区别？**\nOpenClaw 使用 `clawhub install` 命令，直接集成到 OpenClaw agent 工作区。Claude Code 使用 `npx skills i`，安装到 Claude 项目上下文中。两者使用相同的 SKILL.md 和提示词库。\n\n---\n\n## 项目结构\n\n```\nnano-banana-pro-prompts-skill/\n├── SKILL.md                 # Skill 指令（兼容 Claude Code、OpenClaw、Cursor 等）\n├── README.md\n├── README.zh.md\n├── LICENSE\n├── package.json\n├── public/\n│   └── cover.png            # 封面截图\n├── scripts/\n│   └── setup.js             # 从 HuggingFace 下载提示词库\n├── references/              # 自动下载的提示词数据\n│   ├── .gitkeep\n│   └── metadata.jsonl       # 26,000+ 条提示词（由 setup.js 生成）\n└── .claude-plugin/\n    └── marketplace.json\n```\n\n---\n\n## 开发\n\n### 前置条件\n\n- Node.js 18+\n\n### 安装\n\n```bash\npnpm install\n```\n\n这会自动从 HuggingFace 下载提示词库。手动更新：\n\n```bash\nnode scripts/setup.js --force\n```\n\n---\n\n## 相关项目\n\n- 🖼️ [GokuOpenLab 数据集](https://huggingface.co/datasets/Goku-OpenLab/nano-banana-pro-prompts-datasets) — HuggingFace 上的源数据集（26,000+ 提示词、图片、元数据）\n\n## 相关工具\n\n- [Claude Code](https://claude.com/claude-code) — Anthropic 的终端原生 AI agent\n- [OpenClaw](https://openclaw.ai) — AI agent 平台，支持 skill 生态\n- [skills CLI](https://www.npmjs.com/package/skills) — 通用 AI skills 安装器\n\n---\n\n## 协议\n\nMIT © [GokuOpenLab](https://huggingface.co/Goku-OpenLab)\n\nFile v0.1.0:skill-card.md\n\n## Description:\n\nRecommend suitable prompts from a 26,000+ Nano Banana Pro image generation prompt library based on user needs.\n\nThis skill is ready for commercial/non-commercial use.\n\n## Publisher:\n\n[gokuscraper](https://clawhub.ai/user/gokuscraper)\n\n### License/Terms of Use:\n\nMIT\n\n## Use Case:\n\nExternal users and developers use this skill to find image generation prompt templates with sample images, then adapt selected prompts for direct image generation or content illustration workflows.\n\n### Deployment Geography for Use:\n\nGlobal\n\n## Known Risks and Mitigations:\n\nRisk: The skill automatically downloads and refreshes a mutable remote prompt dataset.\n\nMitigation: Review the dataset source before deployment, prefer pinned and validated dataset versions, and make network refreshes explicit or opt-in where possible.\n\nRisk: The skill asks the agent to run shell commands that use image paths derived from the dataset.\n\nMitigation: Review shell commands before execution, use safe temporary file handling, and avoid allowing remote dataset values to control command arguments without validation.\n\n## Reference(s):\n\n- [Server-resolved GitHub source](https://github.com/gokuscraper/nano-banana-pro-prompts-skill)\n- [GokuOpenLab Nano Banana Pro prompts dataset](https://huggingface.co/datasets/Goku-OpenLab/nano-banana-pro-prompts-datasets)\n- [GokuOpenLab PromptHub](https://prompthub.gokuscraper.com/)\n- [ClawHub skill page](https://clawhub.ai/gokuscraper/skills/nano-banana-pro-prompts-skill)\n\n## Skill Output:\n\n**Output Type(s):** [Text, Markdown, Shell commands, Guidance]\n\n**Output Format:** [Markdown recommendations with prompt previews, sample image links, attribution, and optional shell commands for setup or refresh.]\n\n**Output Parameters:** [1D]\n\n**Other Properties Related to Output:** [Returns at most three prompt recommendations per request and requires a sample image with each recommendation.]\n\n## Skill Version(s):\n\n0.1.0 (source: server release metadata; package.json reports 1.0.0)\n\n## Ethical Considerations:\n\nUsers should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment.\n\nFile v0.1.0:.claude-plugin/marketplace.json\n\n{\n  \"name\": \"nano-banana-pro-prompts-skill\",\n  \"owner\": {\n    \"name\": \"GokuOpenLab\"\n  },\n  \"metadata\": {\n    \"description\": \"Recommend from 26,000+ Nano Banana Pro image generation prompts based on user needs\",\n    \"version\": \"1.0.0\"\n  },\n  \"plugins\": [\n    {\n      \"name\": \"nano-banana-pro-prompts\",\n      \"description\": \"AI skill for recommending image generation prompts\",\n      \"source\": \"./\",\n      \"strict\": false,\n      \"skills\": [\n        \"./\"\n      ]\n    }\n  ]\n}\n\nFile v0.1.0:package.json\n\n{\n  \"name\": \"nano-banana-pro-prompts-skill\",\n  \"version\": \"1.0.0\",\n  \"description\": \"AI skill: 26,000+ Nano Banana Pro (Gemini) image generation prompts from GokuOpenLab community dataset. Auto-downloads library on install. Works with Claude Code, Cursor, and more.\",\n  \"type\": \"module\",\n  \"scripts\": {\n    \"postinstall\": \"node scripts/setup.js\",\n    \"setup\": \"node scripts/setup.js\",\n    \"sync\": \"node scripts/setup.js --force\"\n  },\n  \"keywords\": [\n    \"claude-code\",\n    \"claude-code-skill\",\n    \"cursor\",\n    \"skill\",\n    \"nano-banana\",\n    \"nano-banana-pro\",\n    \"gemini\",\n    \"gemini-image\",\n    \"prompts\",\n    \"prompt-library\",\n    \"image-generation\",\n    \"ai-image\",\n    \"text-to-image\",\n    \"prompt-templates\"\n  ],\n  \"author\": \"GokuOpenLab\",\n  \"license\": \"MIT\"\n}\n\nFile v0.1.0:LICENSE\n\nMIT License\n\nCopyright (c) 2026 GokuOpenLab\n\nPermission is hereby granted, free of charge, to any person obtaining a copy\nof this software and associated documentation files (the \"Software\"), to deal\nin the Software without restriction, including without limitation the rights\nto use, copy, modify, merge, publish, distribute, sublicense, and/or sell\ncopies of the Software, and to permit persons to whom the Software is\nfurnished to do so, subject to the following conditions:\n\nThe above copyright notice and this permission notice shall be included in all\ncopies or substantial portions of the Software.\n\nTHE SOFTWARE IS PROVIDED \"AS IS\", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR\nIMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,\nFITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE\nAUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER\nLIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,\nOUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE\nSOFTWARE.","readmeExcerpt":"Skill: Nano Banana Pro Prompts Skill Owner: gokuscraper Summary: Recommend suitable prompts from 26,000+ Nano Banana Pro image generation prompts based on user needs. Optimized for Nano Banana Pro (Gemini), but prompts als... Tags: latest:0.1.0 Version history: v0.1.0 | 2026-07-21T12:05:54.392Z | auto Nano Banana Pro Prompts Recommendation skill – version 0.1.0 - Recommends AI image generation prompts sourced from a ","codeSnippets":[],"executableExamples":[{"language":"text","snippet":"https://huggingface.co/datasets/Goku-OpenLab/nano-banana-pro-prompts-datasets/resolve/main/{media.images[0]}"},{"language":"bash","snippet":"node scripts/setup.js"},{"language":"bash","snippet":"node scripts/setup.js --force"},{"language":"bash","snippet":"node scripts/setup.js --check"},{"language":"bash","snippet":"cat {SKILL_DIR}/references/manifest.json"},{"language":"text","snippet":"grep -i \"keyword\" references/metadata.jsonl"}],"parameters":null,"dependencies":[],"permissions":[],"extractedFiles":[{"path":"SKILL.md","content":"---\nname: nano-banana-pro-prompts-skill\ndescription: |\n  Recommend suitable prompts from 26,000+ Nano Banana Pro image generation prompts based on user needs.\n  Optimized for Nano Banana Pro (Gemini), but prompts also work with GPT Image, Midjourney, DALL-E, Flux,\n  Stable Diffusion, and any text-to-image AI model.\n\n  Use this skill when users want to:\n  - Generate images with AI (any model — Nano Banana Pro, Gemini, GPT Image, etc.)\n  - Find proven AI image generation prompts and prompt templates\n  - Get prompt recommendations for specific use cases (portraits, products, social media, posters, etc.)\n  - Create illustrations for articles, videos, podcasts, or marketing content\n  - Browse a curated prompt library with sample images\nplatforms:\n  - openclaw\n  - claude-code\n  - cursor\n  - codex\n  - gemini-cli\n---\n\n> 📖 Prompts curated from the open community by [GokuOpenLab](https://huggingface.co/datasets/Goku-OpenLab/nano-banana-pro-prompts-datasets) · 26,000+ prompts · CC BY 4.0\n\n# Nano Banana Pro Prompts Recommendation\n\nYou are an expert at recommending image generation prompts from the GokuOpenLab prompt library (26,000+ prompts). These prompts are optimized for Nano Banana Pro (Google Gemini) but work with any text-to-image model including GPT Image, Midjourney, DALL-E 3, Flux, and Stable Diffusion.\n\n## Critical: Sample Images Are Mandatory\n\n**Every prompt recommendation MUST include its sample image.** This is not optional — images are the core value of this skill. Users need to SEE what each prompt produces before choosing.\n\n- Each prompt has `media.images[]` — always use the first image as the sample\n- If `media.images` is empty, skip that prompt entirely\n- **Never present a prompt as text-only** — always attach the image\n- Images are hosted on HuggingFace. Construct the full URL:\n  ```\n  https://huggingface.co/datasets/Goku-OpenLab/nano-banana-pro-prompts-datasets/resolve/main/{media.images[0]}\n  ```\n  Example: `media.images[0]` = `\"nano-banana-pro/images/0/NB_00001_0.jpg\"`\n  Full URL = `https://huggingface.co/datasets/Goku-OpenLab/nano-banana-pro-prompts-datasets/resolve/main/nano-banana-pro/images/0/NB_00001_0.jpg`\n\n## Quick Start\n\nUser provides image generation need → You recommend matching prompts **with sample images** → User selects a prompt → (If content provided) Remix to create customized prompt.\n\n### Two Usage Modes\n\n1. **Direct Generation**: User describes what image they want → Recommend prompts → Done\n2. **Content Illustration**: User provides content (article/video script/podcast notes) → Recommend prompts → User selects → Collect personalization info → Generate customized prompt based on their content\n\n## Setup\n\nAfter installing this skill, the prompt library is automatically downloaded from HuggingFace via `postinstall`. No credentials needed — all data is publicly available.\n\nIf references are missing, run manually:\n```bash\nnode scripts/setup.js\n```\n\n**Keep references up to date** (the community dataset is updated regularly"},{"path":"README.md","content":"# AI Image Prompt Recommender — 26,000+ Nano Banana Pro Prompts\n\n[![Prompts](https://img.shields.io/badge/Prompts-26624-brightgreen)](https://huggingface.co/datasets/Goku-OpenLab/nano-banana-pro-prompts-datasets)\n[![Claude Code](https://img.shields.io/badge/Claude%20Code-Skill-orange)](https://github.com/gokuscraper/nano-banana-pro-prompts-skill)\n[![License](https://img.shields.io/badge/License-MIT-yellow)](LICENSE)\n[![English](https://img.shields.io/badge/English-blue)](README.md) [![简体中文](https://img.shields.io/badge/简体中文-red)](README.zh.md)\n\n> **Stop spending hours hunting for the right AI image prompt.** Tell your AI assistant what you need in one sentence — it searches 26,000+ curated Nano Banana Pro prompts and returns the top 3 matches with sample images, ready to use.\n>\n> 🖼️ [Browse the Dataset →](https://huggingface.co/datasets/Goku-OpenLab/nano-banana-pro-prompts-datasets)\n\n![Demo](public/cover.png)\n\n## What Is This?\n\nAn **AI agent skill** that gives Claude, OpenClaw, Cursor, and other AI assistants the ability to intelligently search a curated library of **26,000+ Nano Banana Pro (Gemini image model) prompts**, recommend the best matches for your use case, and even customize prompts based on your content.\n\n**Nano Banana Pro** is Google's Gemini image generation model — one of the most capable AI image generators available today. High-quality prompts are the key to great results.\n\n## Why Use This Skill?\n\n- ✅ **26,000+ prompts** — massive library covering diverse use cases\n- ✅ **Every prompt includes sample images** — see the result before you copy\n- ✅ **Smart semantic search** — describe what you need, the AI finds the match\n- ✅ **Content remix mode** — paste your article or video script, get a custom prompt\n- ✅ **Multi-language** — responds in your language, always provides English prompt for generation\n- ✅ **Bilingual data** — prompts available in both English and Chinese\n\n---\n\n## Installation\n\n### OpenClaw (Recommended)\n\n```bash\nclawhub install nano-banana-pro-prompts-skill\n```\n\nOr search inside OpenClaw chat:\n\n> \"Install the nano banana pro prompts skill from clawhub\"\n\n### Claude Code\n\n```bash\nnpx skills i gokuscraper/nano-banana-pro-prompts-skill\n```\n\n### Other AI Assistants (Cursor, Codex, Gemini CLI, Windsurf)\n\n```bash\n# Universal installer — auto-detects your AI assistant\nnpx skills i gokuscraper/nano-banana-pro-prompts-skill\n```\n\n### Manual / openskills\n\n```bash\nnpx openskills install gokuscraper/nano-banana-pro-prompts-skill\n```\n\n---\n\n## How to Use\n\n### Mode 1: Direct Search\n\nJust describe what you need:\n\n```\n\"Find me a cyberpunk-style avatar prompt\"\n\"I need prompts for travel blog article covers\"\n\"Looking for a product photo on white background\"\n\"Help me find a YouTube thumbnail for a tech review video\"\n```\n\nYou'll get up to 3 recommendations with:\n- Translated title & description (in your language)\n- The exact English prompt to copy\n- Sample images to preview the style\n\n### Mode 2: Content Illustration (Remix)\n\nPaste your c"},{"path":"_meta.json","content":"{\n  \"ownerId\": \"kn72v74qm7nk0w3wwvjf8b7x558ay0h9\",\n  \"slug\": \"nano-banana-pro-prompts-skill\",\n  \"version\": \"0.1.0\",\n  \"publishedAt\": 1784635554392\n}"},{"path":"README.zh.md","content":"# AI 图像提示词推荐 — 26,000+ Nano Banana Pro 提示词\n\n[![Prompts](https://img.shields.io/badge/Prompts-26624-brightgreen)](https://huggingface.co/datasets/Goku-OpenLab/nano-banana-pro-prompts-datasets)\n[![Claude Code](https://img.shields.io/badge/Claude%20Code-Skill-orange)](https://github.com/gokuscraper/nano-banana-pro-prompts-skill)\n[![License](https://img.shields.io/badge/License-MIT-yellow)](LICENSE)\n[![English](https://img.shields.io/badge/English-blue)](README.md) [![简体中文](https://img.shields.io/badge/简体中文-red)](README.zh.md)\n\n> **别再花时间到处找 AI 图像提示词了。** 一句话告诉 AI 助手你的需求 — 它会从 26,000+ 条精选 Nano Banana Pro 提示词中搜索并返回最匹配的 3 条，附带示例图片，开箱即用。\n>\n> 🖼️ [浏览数据集 →](https://huggingface.co/datasets/Goku-OpenLab/nano-banana-pro-prompts-datasets)\n\n![Demo](public/cover.png)\n\n## 这是什么？\n\n一个 **AI Agent Skill**，让 Claude、OpenClaw、Cursor 等 AI 助手能够智能搜索 26,000+ 条精选 Nano Banana Pro（Gemini 图像模型）提示词库，为你的需求推荐最佳匹配，甚至能根据你的内容定制提示词。\n\n**Nano Banana Pro** 是 Google Gemini 的图像生成模型 — 目前最强大的 AI 图像生成器之一。好的提示词是生成好图片的关键。\n\n## 为什么使用这个 Skill？\n\n- ✅ **26,000+ 条提示词** — 覆盖各种使用场景\n- ✅ **每条提示词都附带示例图片** — 复制前先看效果\n- ✅ **智能语义搜索** — 描述需求，AI 自动匹配\n- ✅ **内容混搭模式** — 粘贴你的文章或视频脚本，获取定制提示词\n- ✅ **多语言支持** — 用你的语言交流，始终提供英文提示词用于生成\n- ✅ **双语数据** — 提示词支持中英文\n\n---\n\n## 安装\n\n### OpenClaw（推荐）\n\n```bash\nclawhub install nano-banana-pro-prompts-skill\n```\n\n或在 OpenClaw 聊天室中搜索：\n\n> \"Install the nano banana pro prompts skill from clawhub\"\n\n### Claude Code\n\n```bash\nnpx skills i gokuscraper/nano-banana-pro-prompts-skill\n```\n\n### 其他 AI 助手（Cursor、Codex、Gemini CLI、Windsurf）\n\n```bash\n# 通用安装器 — 自动识别你的 AI 助手\nnpx skills i gokuscraper/nano-banana-pro-prompts-skill\n```\n\n### 手动 / openskills\n\n```bash\nnpx openskills install gokuscraper/nano-banana-pro-prompts-skill\n```\n\n---\n\n## 使用方法\n\n### 模式 1：直接搜索\n\n直接描述你的需求：\n\n```\n\"帮我找一个赛博朋克风格的头像提示词\"\n\"我需要旅行博客封面的提示词\"\n\"找一张白底产品图的提示词\"\n\"帮我找一个科技评测视频的 YouTube 缩略图提示词\"\n```\n\n你会获得最多 3 条推荐，包含：\n- 翻译后的标题和描述（中文）\n- 可直接复制使用的英文提示词\n- 预览样式的示例图片\n\n### 模式 2：内容配图（混搭）\n\n粘贴内容并请求匹配的配图：\n\n```\n\"这是我写的一篇关于创业失败的文章 — 帮我生成一张封面图：\n[粘贴文章全文]\"\n\n\"我需要这个视频脚本的缩略图：[粘贴脚本]\"\n\n\"帮我为这期关于 AI 的播客生成一张配图：[粘贴笔记]\"\n```\n\nSkill 会：\n1. 推荐匹配的风格模板\n2. 询问几个个性化问题（性别、氛围、场景）\n3. 根据你的内容生成定制提示词\n\n---\n\n## 数据概览\n\n| 项目 | 详情 |\n|------|------|\n| 总提示词数 | 26,624 |\n| 语言 | 英文、中文（双语） |\n| 来源 | [GokuOpenLab 数据集](https://huggingface.co/datasets/Goku-OpenLab/nano-banana-pro-prompts-datasets) |\n| 协议 | Skill 代码：MIT · 数据集：CC BY 4.0 |\n| 格式 | JSONL（每行一条提示词） |\n\n---\n\n## 工作原理\n\n```\n用户描述需求\n      ↓\n搜索提示词库（基于 grep，永不加载完整文件）\n      ↓\n返回 Top 3 提示词 + 图片 + 翻译描述\n      ↓\n[可选] 用户选择一条 → Skill 根据内容混搭定制\n```\n\n**节能设计**：Skill 永不加载完整提示词文件，使用 grep 风格搜索，只提取匹配行，即使词库有 26,000+ 条提示词也能保持极低的 token 消耗。\n\n---\n\n## 数据来源\n\n提示词来自公开社区，数据源于 HuggingFace 上的 [GokuOpenLab 数据集](https://huggingface.co/datasets/Goku-OpenLab/nano-banana-pro-prompts-datasets) — 26,624 条提示词，包含完整元数据、预览图片和双语支持。\n\n*提示词由 [GokuOpenLab](https://prompthub.gokuscraper.com/) 通过公开社区搜集 ❤️*\n\n---\n\n## 常见问题\n\n**问：什么是 Nano Banana Pro？**\nNano Banana Pro 是 Google Gemini 的图像生成模型（model ID: `gemini-3-pro-image-preview`），能够从文本提示词生成高质量的写实和艺术图片。\n\n**问：使用这个 Skill 需要注册账号吗？**\n不需要。Skill 完全免费，支持任何兼容自定义 Skill "},{"path":"skill-card.md","content":"## Description:\n\nRecommend suitable prompts from a 26,000+ Nano Banana Pro image generation prompt library based on user needs.\n\nThis skill is ready for commercial/non-commercial use.\n\n## Publisher:\n\n[gokuscraper](https://clawhub.ai/user/gokuscraper)\n\n### License/Terms of Use:\n\nMIT\n\n## Use Case:\n\nExternal users and developers use this skill to find image generation prompt templates with sample images, then adapt selected prompts for direct image generation or content illustration workflows.\n\n### Deployment Geography for Use:\n\nGlobal\n\n## Known Risks and Mitigations:\n\nRisk: The skill automatically downloads and refreshes a mutable remote prompt dataset.\n\nMitigation: Review the dataset source before deployment, prefer pinned and validated dataset versions, and make network refreshes explicit or opt-in where possible.\n\nRisk: The skill asks the agent to run shell commands that use image paths derived from the dataset.\n\nMitigation: Review shell commands before execution, use safe temporary file handling, and avoid allowing remote dataset values to control command arguments without validation.\n\n## Reference(s):\n\n- [Server-resolved GitHub source](https://github.com/gokuscraper/nano-banana-pro-prompts-skill)\n- [GokuOpenLab Nano Banana Pro prompts dataset](https://huggingface.co/datasets/Goku-OpenLab/nano-banana-pro-prompts-datasets)\n- [GokuOpenLab PromptHub](https://prompthub.gokuscraper.com/)\n- [ClawHub skill page](https://clawhub.ai/gokuscraper/skills/nano-banana-pro-prompts-skill)\n\n## Skill Output:\n\n**Output Type(s):** [Text, Markdown, Shell commands, Guidance]\n\n**Output Format:** [Markdown recommendations with prompt previews, sample image links, attribution, and optional shell commands for setup or refresh.]\n\n**Output Parameters:** [1D]\n\n**Other Properties Related to Output:** [Returns at most three prompt recommendations per request and requires a sample image with each recommendation.]\n\n## Skill Version(s):\n\n0.1.0 (source: server release metadata; package.json reports 1.0.0)\n\n## Ethical Considerations:\n\nUsers should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment."}],"languages":[],"docsSourceLabel":"CLAWHUB","editorialOverview":null,"editorialQuality":{"score":100,"threshold":65,"status":"thin","wordCount":1552,"uniquenessScore":41,"reasons":["uniqueness-below-45"]}},"media":{"evidence":{"source":"no-media","verified":false,"confidence":"low","updatedAt":"2026-10-09T10:01:05.996Z","emptyReason":"No screenshots, media assets, or demo links are available."},"primaryImageUrl":null,"mediaAssetCount":0,"assets":[],"demoUrl":null},"ownerResources":{"evidence":{"source":"unclaimed","verified":false,"confidence":"low","updatedAt":"2026-10-09T10:01:05.996Z","emptyReason":"This page has not been claimed by the agent owner."},"hasCustomPage":false,"customPageUpdatedAt":null,"customLinks":[],"structuredLinks":{"docsUrl":null,"demoUrl":null,"supportUrl":null,"pricingUrl":null,"statusUrl":null},"customPage":null},"relatedAgents":{"evidence":{"source":"protocol-neighbors","verified":false,"confidence":"medium","updatedAt":"2026-10-10T05:03:56.676Z","emptyReason":null},"items":[{"id":"8ebccd8e-3863-4187-8355-c3f14e1f9edf","entityType":"agent","canonicalPath":"/agent/iofficeai-aionui","slug":"iofficeai-aionui","name":"AionUi","description":"Free, local, open-source 24/7 Cowork app and OpenClaw for Gemini CLI, Claude Code, Codex, OpenCode, Qwen Code, Goose CLI, Auggie, and more | 🌟 Star if you like it!","url":"https://github.com/iOfficeAI/AionUi","homepage":"https://www.aionui.com","source":"GITHUB_REPOS","protocols":["MCP","OPENCLAW"],"capabilities":[],"safetyScore":100,"overallRank":70,"updatedAt":"2026-10-09T19:11:12.944Z","createdAt":"2026-02-25T03:38:16.584Z","downloads":null},{"id":"b917f68a-ebff-438e-84f8-3f4b2494c0bc","entityType":"agent","canonicalPath":"/agent/activepieces-activepieces","slug":"activepieces-activepieces","name":"activepieces","description":"AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents","url":"https://github.com/activepieces/activepieces","homepage":"https://www.activepieces.com","source":"GITHUB_REPOS","protocols":["OPENCLAW"],"capabilities":[],"safetyScore":100,"overallRank":70,"updatedAt":"2026-04-15T02:22:12.426Z","createdAt":"2026-02-25T03:38:12.412Z","downloads":null},{"id":"5cb26759-3a39-483f-94cf-276a98c13bb8","entityType":"agent","canonicalPath":"/agent/cherryhq-cherry-studio","slug":"cherryhq-cherry-studio","name":"cherry-studio","description":"AI productivity studio with smart chat, autonomous agents, and 300+ assistants. Unified access to frontier LLMs","url":"https://github.com/CherryHQ/cherry-studio","homepage":"https://cherry-ai.com","source":"GITHUB_REPOS","protocols":["MCP","OPENCLAW"],"capabilities":[],"safetyScore":100,"overallRank":70,"updatedAt":"2026-04-11T14:38:40.986Z","createdAt":"2026-02-25T03:38:19.379Z","downloads":null},{"id":"6f6582d0-5d76-4f0f-b81d-86520247950b","entityType":"agent","canonicalPath":"/agent/copilotkit-copilotkit","slug":"copilotkit-copilotkit","name":"CopilotKit","description":"The Frontend for Agents & Generative UI. React + Angular","url":"https://github.com/CopilotKit/CopilotKit","homepage":"https://docs.copilotkit.ai","source":"GITHUB_REPOS","protocols":["OPENCLAW"],"capabilities":[],"safetyScore":100,"overallRank":70,"updatedAt":"2026-03-25T09:50:57.846Z","createdAt":"2026-02-25T03:39:14.617Z","downloads":null}],"links":{"hub":"/agent","source":"/agent/source/clawhub","protocols":[{"label":"OpenClaw","href":"/agent/protocol/openclew"}]}}}