[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M75PR17E2FST409CJRDERNCT":3,"skill-same:01M75PR17E2FST409CJRDERNCT":55},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":32,"commitSha":33,"skillDirectory":34,"forksCount":35,"repositoryHtmlUrl":36,"repositoryHomepageUrl":6,"ownerHtmlUrl":37,"ownerBlogUrl":38,"ownerDescription":39,"updatedAt":40,"install":41,"resources":54},"01M75PR17E2FST409CJRDERNCT","grok-imagine-image-pro",null,"Generiert hochwertige Bilder mit xAI Grok\u002FFlux API. Use when user asks for image generation (\"mach a Bild von...\", \"generier PNG...\", \"Bild erstellen\") or image editing (\"ändere das Bild\", \"mach daraus...\"). Handles Prompts, styles, aspect ratios, edits, batch generation. Outputs PNG via base64 or file.","javimosch\u002Fopen-claw-skills","javimosch","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F12900508?v=4","01M6D3F2AS6PV75ET9PZ1QGP8J","Javier Leandro Arancibia","01M75B8NCTAJG9WH5YNZH7C3D8",0,"MIT","https:\u002F\u002Fgithub.com\u002Fjavimosch\u002Fopen-claw-skills\u002Fblob\u002Fmain\u002Fskills\u002Fnixeifoit\u002Fgrok-imagine-image-pro\u002FSKILL.md",[],[],"2026-11-12 13:55:43",false,"---\nname: grok-imagine-image-pro\ndescription: Generiert hochwertige Bilder mit xAI Grok\u002FFlux API. Use when user asks for image generation (\"mach a Bild von...\", \"generier PNG...\", \"Bild erstellen\") or image editing (\"ändere das Bild\", \"mach daraus...\"). Handles Prompts, styles, aspect ratios, edits, batch generation. Outputs PNG via base64 or file.\nmetadata:\n  openclaw:\n    requires:\n      env:\n        - XAI_API_KEY\n      bins:\n        - curl\n        - python3\n---\n\n# Grok Imagine Image Pro\n\nAPI Key: `$XAI_API_KEY` (already configured)\nSave dir: `~\u002F.openclaw\u002Fmedia\u002F` (resolves to `\u002Fdata\u002F.openclaw\u002Fmedia\u002F` — allowed for Telegram sending)\n\n## Available Models\n\n- `grok-imagine-image` — standard quality, faster\n- `grok-imagine-image-pro` — higher quality (default for generation)\n\n## 1. Image Generation\n\n```bash\ncurl -s https:\u002F\u002Fapi.x.ai\u002Fv1\u002Fimages\u002Fgenerations \\\n  -H \"Authorization: Bearer $XAI_API_KEY\" \\\n  -H \"Content-Type: application\u002Fjson\" \\\n  --data '{\n    \"model\": \"grok-imagine-image-pro\",\n    \"prompt\": \"\u003CPROMPT>\",\n    \"n\": 1,\n    \"response_format\": \"b64_json\"\n  }' | python3 -c \"\nimport json, sys, base64, os, time\nos.makedirs(os.path.expanduser('~\u002F.openclaw\u002Fmedia'), exist_ok=True)\nr = json.load(sys.stdin)\nts = int(time.time())\nfor i, img in enumerate(r['data']):\n    img_data = base64.b64decode(img['b64_json'])\n    fpath = os.path.expanduser(f'~\u002F.openclaw\u002Fmedia\u002Fgenerated_{ts}_{i}.png')\n    with open(fpath, 'wb') as f:\n        f.write(img_data)\n    print(fpath)\n\"\n```\n\n### Aspect Ratios\n\nAdd `\"aspect_ratio\": \"\u003Cratio>\"` to the JSON body. Supported values:\n\n| Ratio | Use case |\n|-------|----------|\n| `1:1` | Social media, thumbnails |\n| `16:9` \u002F `9:16` | Widescreen, mobile stories |\n| `4:3` \u002F `3:4` | Presentations, portraits |\n| `3:2` \u002F `2:3` | Photography |\n| `2:1` \u002F `1:2` | Banners, headers |\n| `auto` | Model picks best ratio (default) |\n\n### Batch Generation\n\nSet `\"n\": \u003Ccount>` (1-10) to generate multiple images in one request.\n\n## 2. Image Editing \u002F Style Transfer\n\nEdit an existing image by providing a source image plus an edit prompt.\nUses the same `\u002Fv1\u002Fimages\u002Fgenerations` endpoint with an added `image_url` field.\n\n**Do NOT use `\u002Fv1\u002Fimages\u002Fedits` with multipart — xAI requires JSON.**\n\n**IMPORTANT:** For local files, use Python to build the payload JSON file, then curl with `@file`.\nInline base64 in curl args causes \"Argument list too long\" for images >~100KB.\n\n**NOTE:** This is NOT true image editing — the API generates a new image inspired by the source.\nIt cannot make pixel-precise edits (e.g. changing only a car's color while keeping everything else identical).\n\n### Edit from local file (recommended approach):\n\n```bash\npython3 -c \"\nimport json, base64\nwith open('\u003CSOURCE_PATH>', 'rb') as f:\n    b64 = base64.b64encode(f.read()).decode()\npayload = {\n    'model': 'grok-imagine-image',\n    'prompt': '\u003CEDIT_PROMPT>',\n    'image_url': f'data:image\u002Fpng;base64,{b64}',\n    'n': 1,\n    'response_format': 'b64_json'\n}\nwith open('\u002Ftmp\u002Fimg_edit_payload.json', 'w') as f:\n    json.dump(payload, f)\nprint('Payload ready')\n\" && \\\ncurl -s https:\u002F\u002Fapi.x.ai\u002Fv1\u002Fimages\u002Fgenerations \\\n  -H \"Authorization: Bearer $XAI_API_KEY\" \\\n  -H \"Content-Type: application\u002Fjson\" \\\n  -d @\u002Ftmp\u002Fimg_edit_payload.json | python3 -c \"\nimport json, sys, base64, os, time\nos.makedirs(os.path.expanduser('~\u002F.openclaw\u002Fmedia'), exist_ok=True)\nr = json.load(sys.stdin)\nimg_data = base64.b64decode(r['data'][0]['b64_json'])\nfpath = os.path.expanduser(f'~\u002F.openclaw\u002Fmedia\u002Fedited_{int(time.time())}.png')\nwith open(fpath, 'wb') as f:\n    f.write(img_data)\nprint(fpath)\n\"\n```\n\n### Edit from URL:\n\n```bash\ncurl -s https:\u002F\u002Fapi.x.ai\u002Fv1\u002Fimages\u002Fgenerations \\\n  -H \"Authorization: Bearer $XAI_API_KEY\" \\\n  -H \"Content-Type: application\u002Fjson\" \\\n  --data '{\n    \"model\": \"grok-imagine-image\",\n    \"prompt\": \"\u003CEDIT_PROMPT>\",\n    \"image_url\": \"\u003CPUBLIC_IMAGE_URL>\",\n    \"n\": 1,\n    \"response_format\": \"b64_json\"\n  }' | python3 -c \"\nimport json, sys, base64, os, time\nos.makedirs(os.path.expanduser('~\u002F.openclaw\u002Fmedia'), exist_ok=True)\nr = json.load(sys.stdin)\nimg_data = base64.b64decode(r['data'][0]['b64_json'])\nfpath = os.path.expanduser(f'~\u002F.openclaw\u002Fmedia\u002Fedited_{int(time.time())}.png')\nwith open(fpath, 'wb') as f:\n    f.write(img_data)\nprint(fpath)\n\"\n```\n\n### Style Transfer Examples\n\nUse editing with a style prompt, e.g.:\n- \"Render this as an oil painting in impressionist style\"\n- \"Make this a pencil sketch with detailed shading\"\n- \"Convert to pop art with bold colors\"\n- \"Watercolor painting with soft edges\"\n\n## 3. Sending to Telegram\n\n```\nmessage tool: action=send, channel=telegram, target=\u003Cid>,\n  message=\"\u003Ccaption>\", filePath=~\u002F.openclaw\u002Fmedia\u002F\u003Cfile>.png\n```\n\n- Always include `message` field (required even for media-only sends)\n- Allowed media paths: `\u002Ftmp\u002F`, `~\u002F.openclaw\u002Fmedia\u002F`, `~\u002F.openclaw\u002Fagents\u002F`\n\n## Notes\n\n- Do NOT pass `size` parameter — returns 400\n- Aspect ratio: pass `aspect_ratio` in JSON body (not `size`)\n- Editing: use `image_url` field in the generations endpoint (NOT the edits endpoint with multipart)\n- **Always use `\"response_format\": \"b64_json\"`** — URL format returns temporary URLs that often 403\n- For large images: build payload with Python → save to `\u002Ftmp\u002F` → curl with `@file` syntax\n- Max 10 images per request\n- Images are subject to content moderation\n- Editing is style-transfer\u002Freimagination, NOT pixel-precise inpainting\n","# Grok Imagine Image Pro\n\nAPI Key: `$XAI_API_KEY` (already configured)\nSave dir: `~\u002F.openclaw\u002Fmedia\u002F` (resolves to `\u002Fdata\u002F.openclaw\u002Fmedia\u002F` — allowed for Telegram sending)\n\n## Available Models\n\n- `grok-imagine-image` — standard quality, faster\n- `grok-imagine-image-pro` — higher quality (default for generation)\n\n## 1. Image Generation\n\n```bash\ncurl -s https:\u002F\u002Fapi.x.ai\u002Fv1\u002Fimages\u002Fgenerations \\\n  -H \"Authorization: Bearer $XAI_API_KEY\" \\\n  -H \"Content-Type: application\u002Fjson\" \\\n  --data '{\n    \"model\": \"grok-imagine-image-pro\",\n    \"prompt\": \"\u003CPROMPT>\",\n    \"n\": 1,\n    \"response_format\": \"b64_json\"\n  }' | python3 -c \"\nimport json, sys, base64, os, time\nos.makedirs(os.path.expanduser('~\u002F.openclaw\u002Fmedia'), exist_ok=True)\nr = json.load(sys.stdin)\nts = int(time.time())\nfor i, img in enumerate(r['data']):\n    img_data = base64.b64decode(img['b64_json'])\n    fpath = os.path.expanduser(f'~\u002F.openclaw\u002Fmedia\u002Fgenerated_{ts}_{i}.png')\n    with open(fpath, 'wb') as f:\n        f.write(img_data)\n    print(fpath)\n\"\n```\n\n### Aspect Ratios\n\nAdd `\"aspect_ratio\": \"\u003Cratio>\"` to the JSON body. Supported values:\n\n| Ratio | Use case |\n|-------|----------|\n| `1:1` | Social media, thumbnails |\n| `16:9` \u002F `9:16` | Widescreen, mobile stories |\n| `4:3` \u002F `3:4` | Presentations, portraits |\n| `3:2` \u002F `2:3` | Photography |\n| `2:1` \u002F `1:2` | Banners, headers |\n| `auto` | Model picks best ratio (default) |\n\n### Batch Generation\n\nSet `\"n\": \u003Ccount>` (1-10) to generate multiple images in one request.\n\n## 2. Image Editing \u002F Style Transfer\n\nEdit an existing image by providing a source image plus an edit prompt.\nUses the same `\u002Fv1\u002Fimages\u002Fgenerations` endpoint with an added `image_url` field.\n\n**Do NOT use `\u002Fv1\u002Fimages\u002Fedits` with multipart — xAI requires JSON.**\n\n**IMPORTANT:** For local files, use Python to build the payload JSON file, then curl with `@file`.\nInline base64 in curl args causes \"Argument list too long\" for images >~100KB.\n\n**NOTE:** This is NOT true image editing — the API generates a new image inspired by the source.\nIt cannot make pixel-precise edits (e.g. changing only a car's color while keeping everything else identical).\n\n### Edit from local file (recommended approach):\n\n```bash\npython3 -c \"\nimport json, base64\nwith open('\u003CSOURCE_PATH>', 'rb') as f:\n    b64 = base64.b64encode(f.read()).decode()\npayload = {\n    'model': 'grok-imagine-image',\n    'prompt': '\u003CEDIT_PROMPT>',\n    'image_url': f'data:image\u002Fpng;base64,{b64}',\n    'n': 1,\n    'response_format': 'b64_json'\n}\nwith open('\u002Ftmp\u002Fimg_edit_payload.json', 'w') as f:\n    json.dump(payload, f)\nprint('Payload ready')\n\" && \\\ncurl -s https:\u002F\u002Fapi.x.ai\u002Fv1\u002Fimages\u002Fgenerations \\\n  -H \"Authorization: Bearer $XAI_API_KEY\" \\\n  -H \"Content-Type: application\u002Fjson\" \\\n  -d @\u002Ftmp\u002Fimg_edit_payload.json | python3 -c \"\nimport json, sys, base64, os, time\nos.makedirs(os.path.expanduser('~\u002F.openclaw\u002Fmedia'), exist_ok=True)\nr = json.load(sys.stdin)\nimg_data = base64.b64decode(r['data'][0]['b64_json'])\nfpath = os.path.expanduser(f'~\u002F.openclaw\u002Fmedia\u002Fedited_{int(time.time())}.png')\nwith open(fpath, 'wb') as f:\n    f.write(img_data)\nprint(fpath)\n\"\n```\n\n### Edit from URL:\n\n```bash\ncurl -s https:\u002F\u002Fapi.x.ai\u002Fv1\u002Fimages\u002Fgenerations \\\n  -H \"Authorization: Bearer $XAI_API_KEY\" \\\n  -H \"Content-Type: application\u002Fjson\" \\\n  --data '{\n    \"model\": \"grok-imagine-image\",\n    \"prompt\": \"\u003CEDIT_PROMPT>\",\n    \"image_url\": \"\u003CPUBLIC_IMAGE_URL>\",\n    \"n\": 1,\n    \"response_format\": \"b64_json\"\n  }' | python3 -c \"\nimport json, sys, base64, os, time\nos.makedirs(os.path.expanduser('~\u002F.openclaw\u002Fmedia'), exist_ok=True)\nr = json.load(sys.stdin)\nimg_data = base64.b64decode(r['data'][0]['b64_json'])\nfpath = os.path.expanduser(f'~\u002F.openclaw\u002Fmedia\u002Fedited_{int(time.time())}.png')\nwith open(fpath, 'wb') as f:\n    f.write(img_data)\nprint(fpath)\n\"\n```\n\n### Style Transfer Examples\n\nUse editing with a style prompt, e.g.:\n- \"Render this as an oil painting in impressionist style\"\n- \"Make this a pencil sketch with detailed shading\"\n- \"Convert to pop art with bold colors\"\n- \"Watercolor painting with soft edges\"\n\n## 3. Sending to Telegram\n\n```\nmessage tool: action=send, channel=telegram, target=\u003Cid>,\n  message=\"\u003Ccaption>\", filePath=~\u002F.openclaw\u002Fmedia\u002F\u003Cfile>.png\n```\n\n- Always include `message` field (required even for media-only sends)\n- Allowed media paths: `\u002Ftmp\u002F`, `~\u002F.openclaw\u002Fmedia\u002F`, `~\u002F.openclaw\u002Fagents\u002F`\n\n## Notes\n\n- Do NOT pass `size` parameter — returns 400\n- Aspect ratio: pass `aspect_ratio` in JSON body (not `size`)\n- Editing: use `image_url` field in the generations endpoint (NOT the edits endpoint with multipart)\n- **Always use `\"response_format\": \"b64_json\"`** — URL format returns temporary URLs that often 403\n- For large images: build payload with Python → save to `\u002Ftmp\u002F` → curl with `@file` syntax\n- Max 10 images per request\n- Images are subject to content moderation\n- Editing is style-transfer\u002Freimagination, NOT pixel-precise inpainting\n",{"name":5,"metadata":24,"description":7},{"openclaw":25},{"requires":26},{"env":27,"bins":29},[28],"XAI_API_KEY",[30,31],"curl","python3","main","f9d3fe7cf9ac8f1ea63a0d96e98e1f510a3814db","skills\u002Fnixeifoit\u002Fgrok-imagine-image-pro",1,"https:\u002F\u002Fgithub.com\u002Fjavimosch\u002Fopen-claw-skills","https:\u002F\u002Fgithub.com\u002Fjavimosch","intrane.fr","Building robust, open-source infrastructure for the commons. AI-leveraged, self-hosted, built to last.","2026-06-07 03:34:58",{"source":8,"skillName":5,"commands":42,"prompt":52,"zipAvailable":53},[43,46,49],{"tool":44,"command":45},"npx","npx skills add javimosch\u002Fopen-claw-skills --skill grok-imagine-image-pro",{"tool":47,"command":48},"bunx","bunx skills add javimosch\u002Fopen-claw-skills --skill grok-imagine-image-pro",{"tool":50,"command":51},"pnpm","pnpm dlx skills add javimosch\u002Fopen-claw-skills --skill grok-imagine-image-pro","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fjavimosch\u002Fopen-claw-skills\u002Fblob\u002Fmain\u002Fskills\u002Fnixeifoit\u002Fgrok-imagine-image-pro\u002FSKILL.md",true,[],[56,64,71,78,85,92],{"skillNo":57,"name":58,"nameZh":6,"description":59,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":60,"categories":61,"keywords":62,"publishedAt":63},"01M778GGXG2VQ0YF31W2MKGMQZ","crowd-prompting","A marketplace where AI agents improve prompts, system instructions, tool descriptions, and other text-based content with domain expertise from real-world operations — and earn tokens for valuable contributions.","https:\u002F\u002Fgithub.com\u002Fjavimosch\u002Fopen-claw-skills\u002Fblob\u002Fmain\u002Fskills\u002Fzzadrian\u002Fcrowd-prompting\u002FSKILL.md",[],[],"2026-11-15 14:19:17",{"skillNo":65,"name":66,"nameZh":6,"description":67,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":68,"categories":69,"keywords":70,"publishedAt":63},"01M778G7BH8SBJ9FJ6C3G7CB1K","ceaser","Interact with the Ceaser privacy protocol on Base L2 using the ceaser-mcp MCP tools. This skill uses the ceaser-mcp npm package for ALL operations -- shield, unshield, note management, and protocol queries. All ceaser tool calls use CLI subcommands (npx -y ceaser-mcp \u003Csubcommand>). Ceaser is a privacy-preserving ETH wrapper using Noir\u002FUltraHonk zero-knowledge proofs on Base L2 (chain ID 8453).","https:\u002F\u002Fgithub.com\u002Fjavimosch\u002Fopen-claw-skills\u002Fblob\u002Fmain\u002Fskills\u002Fzyra-v21\u002Fceaser\u002FSKILL.md",[],[],{"skillNo":72,"name":73,"nameZh":6,"description":74,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":75,"categories":76,"keywords":77,"publishedAt":63},"01M778FYCJQZWFKKX5FYMK3S47","ceaser-send","Fully automated private ETH transfer via Ceaser Protocol on Base L2 using the ceaser-mcp MCP tools. This skill uses the ceaser-mcp npm package for ALL operations -- all ceaser tool calls use CLI subcommands (npx -y ceaser-mcp \u003Csubcommand>). WARNING -- creates observable on-chain links between user wallet and hot wallet (see Privacy Warning). Generates an ephemeral hot wallet with BIP-39 mnemonic recovery, user funds it, agent signs and broadcasts the Shield TX automatically. Exactly one manual step required (funding the hot wallet with ETH). Uses Noir\u002FUltraHonk zero-knowledge proofs.","https:\u002F\u002Fgithub.com\u002Fjavimosch\u002Fopen-claw-skills\u002Fblob\u002Fmain\u002Fskills\u002Fzyra-v21\u002Fceaser-send\u002FSKILL.md",[],[],{"skillNo":79,"name":80,"nameZh":6,"description":81,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":82,"categories":83,"keywords":84,"publishedAt":63},"01M778FQQNSEYA3HJKZBPQ4M9Z","dilemm-ai","Compete in DilemmAI, the prisoner's dilemma AI arena at dilemm.ai. Use when an OpenClaw agent wants to create an account, design and submit strategy prompts for their bot, enter matchmaking, analyze historical matches and leaderboards, and iterate on bot strategy. Requires headless browser automation (no API available yet).","https:\u002F\u002Fgithub.com\u002Fjavimosch\u002Fopen-claw-skills\u002Fblob\u002Fmain\u002Fskills\u002Fzyori\u002Fdilemm-ai\u002FSKILL.md",[],[],{"skillNo":86,"name":87,"nameZh":6,"description":88,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":89,"categories":90,"keywords":91,"publishedAt":63},"01M778FGVZX7QA2TF9BFMM37FY","moldium","Post and manage content on the Moldium blog platform. Triggered by \"post to Moldium\", \"write a blog post\", \"publish an article\", etc.","https:\u002F\u002Fgithub.com\u002Fjavimosch\u002Fopen-claw-skills\u002Fblob\u002Fmain\u002Fskills\u002Fzyom45\u002Fmoldium\u002FSKILL.md",[],[],{"skillNo":93,"name":94,"nameZh":6,"description":95,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":96,"categories":97,"keywords":98,"publishedAt":63},"01M778F88D8PQ9MQ0KNW2TJ8ZH","arxiv-paper-reviews","Interact with arXiv Crawler API to fetch papers, read reviews, submit comments, search papers, and import papers. Use when working with arXiv papers, fetching paper lists by date\u002Fcategory\u002Finterest, viewing paper details with comments, submitting paper reviews, searching papers by title, or importing papers from arXiv URLs via API at http:\u002F\u002Fweakaccept.top:8000\u002F.","https:\u002F\u002Fgithub.com\u002Fjavimosch\u002Fopen-claw-skills\u002Fblob\u002Fmain\u002Fskills\u002Fzxrys\u002Farxiv-paper-reviews\u002FSKILL.md",[],[]]