[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M77RSQSCV21KTYDSMBXJFSKH":3,"skill-same:01M77RSQSCV21KTYDSMBXJFSKH":77},{"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":54,"commitSha":55,"skillDirectory":56,"forksCount":57,"repositoryHtmlUrl":58,"repositoryHomepageUrl":59,"ownerHtmlUrl":60,"ownerBlogUrl":6,"ownerDescription":61,"updatedAt":62,"install":63,"resources":76},"01M77RSQSCV21KTYDSMBXJFSKH","pollinations",null,"Pollinations.ai API for AI generation and analysis - text, images, videos, audio, vision, and transcription. Use when user requests AI-powered content (text completion, image generation\u002Fediting, video generation, audio\u002FTTS, image\u002Fvideo analysis, audio transcription) or mentions Pollinations. Supports 25+ models with OpenAI-compatible endpoints.","Lord1Egypt\u002Fawesome-skill-forge","Lord1Egypt","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F99746359?v=4","01M7592YDNT0XK9WJ0T2MQVPDN","Mohamed Mounir Ali AL Keshita","01M75GRFNHC8VZNWEB8DKDE433",3,"MIT","https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge\u002Fblob\u002Fmaster\u002Fcommunity\u002Fclawhub\u002Fp\u002Fpollinations\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: pollinations\nversion: 1.0.2\ndescription: \"Pollinations.ai API for AI generation and analysis - text, images, videos, audio, vision, and transcription. Use when user requests AI-powered content (text completion, image generation\u002Fediting, video generation, audio\u002FTTS, image\u002Fvideo analysis, audio transcription) or mentions Pollinations. Supports 25+ models with OpenAI-compatible endpoints.\"\nmetadata: {\"openclaw\":{\"emoji\":\"🧬\",\"homepage\":\"https:\u002F\u002Fpollinations.ai\",\"os\":[\"darwin\",\"linux\",\"win32\"],\"requires\":{\"bins\":[\"curl\",\"jq\",\"base64\"],\"env\":[\"POLLINATIONS_API_KEY\"]},\"primaryEnv\":\"POLLINATIONS_API_KEY\",\"install\":[{\"id\":\"jq-brew\",\"kind\":\"brew\",\"formula\":\"jq\",\"bins\":[\"jq\"],\"label\":\"Install jq via Homebrew\",\"os\":[\"darwin\"]},{\"id\":\"jq-apt\",\"kind\":\"shell\",\"command\":\"sudo apt-get install -y jq\",\"bins\":[\"jq\"],\"label\":\"Install jq via apt\",\"os\":[\"linux\"]}]}}\n---\n\n# Pollinations v1.0.2\n\nUnified AI platform for generating and analyzing text, images, videos, and audio with 25+ models.\n\n## API Key\n\nGet free or paid keys at https:\u002F\u002Fenter.pollinations.ai\n- Secret Keys (`sk_`): Server-side, no rate limits (recommended)\n- Optional for many operations (free tier available)\n\n### Runtime Requirements\n\n| Type | Name | Required |\n|------|------|----------|\n| Env | `POLLINATIONS_API_KEY` | Optional (free tier works without) |\n| Bin | `curl` | Yes |\n| Bin | `jq` | Yes |\n| Bin | `base64` | Yes |\n\n## Operations & Scripts\n\n### 1. Text\u002FChat Generation (`scripts\u002Fchat.sh`)\n\nGenerate text using 25+ LLM models with OpenAI-compatible API.\n\n**Usage:**\n```bash\nscripts\u002Fchat.sh \"your message\"\nscripts\u002Fchat.sh \"your message\" --model claude --temp 0.7\nscripts\u002Fchat.sh \"explain quantum physics\" --model openai --max-tokens 500\nscripts\u002Fchat.sh \"list 3 colors\" --json --model openai\nscripts\u002Fchat.sh \"solve this step by step\" --model o3 --reasoning-effort high\nscripts\u002Fchat.sh \"translate to French\" --system \"You are a translator\" --model gemini\n```\n\n**Options:**\n- `--model MODEL` — Model name (default: openai)\n- `--temp N` — Temperature 0-2 (default: 1)\n- `--max-tokens N` — Max response length\n- `--top-p N` — Nucleus sampling 0-1\n- `--seed N` — Reproducibility (-1 = random)\n- `--system \"PROMPT\"` — System prompt\n- `--json` — Force structured JSON response\n- `--reasoning-effort LVL` — For o1\u002Fo3\u002FR1 models: high\u002Fmedium\u002Flow\u002Fminimal\u002Fnone\n- `--thinking-budget N` — Token budget for reasoning models\n\n**Models:** openai, claude, gemini, gemini-large, gemini-search, mistral, deepseek, grok, qwen, perplexity, o1, o3, gpt-4, and 15+ more. Use `scripts\u002Fmodels.sh text` to list all.\n\n**Simple text (no script needed):**\n```bash\ncurl \"https:\u002F\u002Fgen.pollinations.ai\u002Ftext\u002FHello%20world\"\n```\n\n### 2. Image Generation (`scripts\u002Fimage.sh`)\n\nGenerate images from text prompts with multiple models and options.\n\n**Usage:**\n```bash\nscripts\u002Fimage.sh \"a sunset over mountains\"\nscripts\u002Fimage.sh \"a portrait\" --model flux --width 1024 --height 1024\nscripts\u002Fimage.sh \"logo design\" --model gptimage --quality hd --transparent\nscripts\u002Fimage.sh \"photo\" --enhance --nologo --private\nscripts\u002Fimage.sh \"art\" --negative \"blurry, low quality\" --seed 42\n```\n\n**Options:**\n- `--model MODEL` — Model (default: flux)\n- `--width N` — Width 16-2048px (default: 1024)\n- `--height N` — Height 16-2048px (default: 1024)\n- `--seed N` — Reproducibility\n- `--output FILE` — Output filename\n- `--enhance` — AI prompt improvement\n- `--negative \"TEXT\"` — Negative prompt (what to avoid)\n- `--nologo` — Remove watermark\n- `--private` — Private generation\n- `--safe` — Enable NSFW filter\n- `--quality LEVEL` — low\u002Fmedium\u002Fhigh\u002Fhd (gptimage only)\n- `--transparent` — Transparent background PNG (gptimage only)\n- `--image-url URL` — Source image for image-to-image\n\n**Models:** flux (default), turbo, gptimage, kontext, seedream, nanobanana, nanobanana-pro. Use `scripts\u002Fmodels.sh image` to list all.\n\n### 3. Image Editing \u002F Image-to-Image (`scripts\u002Fimage-edit.sh`)\n\nTransform or edit existing images using AI.\n\n**Usage:**\n```bash\nscripts\u002Fimage-edit.sh \"make it blue\" --source \"https:\u002F\u002Fexample.com\u002Fphoto.jpg\"\nscripts\u002Fimage-edit.sh \"add sunglasses\" --source photo.jpg --model kontext\nscripts\u002Fimage-edit.sh \"convert to watercolor\" --source input.png --output watercolor.jpg\n```\n\n**Options:**\n- `--source URL\u002FFILE` — Source image (URL or local file, required)\n- `--model MODEL` — Model (default: kontext)\n- `--seed N` — Reproducibility\n- `--negative \"TEXT\"` — Negative prompt\n- `--output FILE` — Output filename\n\n### 4. Video Generation (`scripts\u002Fimage.sh` with video models)\n\nGenerate videos from text prompts or images.\n\n**Usage:**\n```bash\nscripts\u002Fimage.sh \"a cat playing piano\" --model veo --duration 6\nscripts\u002Fimage.sh \"ocean waves\" --model seedance --duration 8 --aspect-ratio 16:9\nscripts\u002Fimage.sh \"timelapse\" --model veo --duration 4 --audio\nscripts\u002Fimage.sh \"animate this\" --model seedance --image-url \"https:\u002F\u002Fexample.com\u002Fphoto.jpg\"\n```\n\n**Options (in addition to image options):**\n- `--model veo|seedance` — Video model (required)\n- `--duration N` — Length in seconds (veo: 4\u002F6\u002F8, seedance: 2-10)\n- `--aspect-ratio RATIO` — 16:9 or 9:16\n- `--audio` — Enable audio generation (veo only)\n- `--image-url URL` — Source image for image-to-video\n\n**Frame interpolation (veo):** Pass two images for first\u002Flast frame interpolation using the API directly:\n```\nhttps:\u002F\u002Fgen.pollinations.ai\u002Fimage\u002Fprompt?model=veo&image[0]=first_frame_url&image[1]=last_frame_url\n```\n\n**Models:** veo (4-8s, audio support, frame interpolation), seedance (2-10s, image-to-video)\n\n### 5. Text-to-Speech \u002F Audio (`scripts\u002Ftts.sh`)\n\nConvert text to speech with multiple voices and formats.\n\n**Usage:**\n```bash\nscripts\u002Ftts.sh \"Hello world\"\nscripts\u002Ftts.sh \"Bonjour le monde\" --voice nova --format mp3\nscripts\u002Ftts.sh \"Welcome\" --voice coral --format wav --output welcome.wav\n```\n\n**Options:**\n- `--voice VOICE` — Voice selection (default: nova)\n- `--format FORMAT` — Output format (default: mp3)\n- `--model MODEL` — Model (default: openai-audio)\n- `--output FILE` — Output filename\n\n**Voices (13):** alloy, amuch, ash, ballad, coral, dan, echo, fable, nova, onyx, sage, shimmer, verse\n\n**Formats (5):** mp3, wav, flac, opus, pcm16\n\n### 6. Image Analysis \u002F Vision (`scripts\u002Fanalyze-image.sh`)\n\nAnalyze and describe images using vision-capable AI models.\n\n**Usage:**\n```bash\nscripts\u002Fanalyze-image.sh \"https:\u002F\u002Fexample.com\u002Fphoto.jpg\"\nscripts\u002Fanalyze-image.sh photo.jpg --prompt \"What objects are in this image?\"\nscripts\u002Fanalyze-image.sh image.png --model claude --prompt \"Extract all text from this image\"\n```\n\n**Options:**\n- `--prompt \"TEXT\"` — Analysis question (default: \"Describe this image in detail\")\n- `--model MODEL` — Vision model (default: gemini)\n\n**Input:** URL or local file (jpg, png, gif, webp)\n\n**Models:** gemini, gemini-large, claude, openai, and other vision-capable models. Use `scripts\u002Fmodels.sh vision` to list all.\n\n### 7. Video Analysis (`scripts\u002Fanalyze-video.sh`)\n\nAnalyze video content using AI vision models.\n\n**Usage:**\n```bash\nscripts\u002Fanalyze-video.sh \"https:\u002F\u002Fexample.com\u002Fvideo.mp4\"\nscripts\u002Fanalyze-video.sh recording.mp4 --prompt \"Summarize the key moments\"\nscripts\u002Fanalyze-video.sh clip.mov --model gemini-large --prompt \"Count the people\"\n```\n\n**Options:**\n- `--prompt \"TEXT\"` — Analysis question (default: \"Describe this video in detail\")\n- `--model MODEL` — Video-capable model (default: gemini)\n\n**Input:** URL or local file (mp4, mov, avi)\n\n**Models:** gemini, gemini-large, claude, openai (video-capable models)\n\n### 8. Audio Transcription (`scripts\u002Ftranscribe.sh`)\n\nTranscribe audio files to text.\n\n**Usage:**\n```bash\nscripts\u002Ftranscribe.sh recording.mp3\nscripts\u002Ftranscribe.sh podcast.wav --model gemini-large\nscripts\u002Ftranscribe.sh \"https:\u002F\u002Fexample.com\u002Faudio.mp3\" --prompt \"Transcribe in French\"\n```\n\n**Options:**\n- `--prompt \"TEXT\"` — Transcription instructions (default: accurate transcription)\n- `--model MODEL` — Audio-capable model (default: gemini)\n\n**Input:** Local file or URL (mp3, wav, flac, ogg, m4a)\n\n**Models:** gemini, gemini-large, gemini-legacy, openai-audio\n\n### 9. List Available Models (`scripts\u002Fmodels.sh`)\n\nDynamically list all available models from the API.\n\n**Usage:**\n```bash\nscripts\u002Fmodels.sh              # List all models\nscripts\u002Fmodels.sh text         # Text\u002Fchat models only\nscripts\u002Fmodels.sh image        # Image generation models\nscripts\u002Fmodels.sh video        # Video generation models\nscripts\u002Fmodels.sh vision       # Vision\u002Fanalysis models\nscripts\u002Fmodels.sh audio        # Audio\u002FTTS models\n```\n\n## API Endpoints Reference\n\n| Operation | Endpoint | Method |\n|-----------|----------|--------|\n| Simple Text | `\u002Ftext\u002F{prompt}` | GET |\n| Chat Completion | `\u002Fv1\u002Fchat\u002Fcompletions` | POST |\n| Image Generation | `\u002Fimage\u002F{prompt}?{params}` | GET |\n| Image-to-Image | `\u002Fimage\u002F{prompt}?image={url}&{params}` | GET |\n| Video Generation | `\u002Fimage\u002F{prompt}?model=veo&{params}` | GET |\n| Image Analysis | `\u002Fv1\u002Fchat\u002Fcompletions` (with image_url) | POST |\n| Video Analysis | `\u002Fv1\u002Fchat\u002Fcompletions` (with video_url) | POST |\n| Audio\u002FTTS | `\u002Fv1\u002Fchat\u002Fcompletions` (openai-audio) | POST |\n| Audio Transcription | `\u002Fv1\u002Fchat\u002Fcompletions` (with input_audio) | POST |\n| List Text Models | `\u002Fv1\u002Fmodels` | GET |\n| List Image Models | `\u002Fimage\u002Fmodels` | GET |\n| List Vision Models | `\u002Ftext\u002Fmodels` | GET |\n\n## Tips\n\n1. **Free tier available**: Many operations work without an API key (rate limited)\n2. **OpenAI-compatible**: Chat endpoint works with existing OpenAI integrations\n3. **Reproducibility**: Use `seed` parameter for consistent outputs across all operations\n4. **Image enhancement**: Use `--enhance` for AI-improved prompts on image generation\n5. **JSON mode**: Use `--json` flag on chat for structured data extraction\n6. **Reasoning models**: Use `--reasoning-effort` with o1\u002Fo3\u002FR1 for controlled thinking depth\n7. **Video from images**: Use `--image-url` with seedance for image-to-video, or veo frame interpolation\n8. **Audio on video**: Use `--audio` with veo model for videos with sound\n9. **Local files**: Analysis scripts (image, video, transcription) accept both URLs and local files\n10. **Private mode**: Use `--private` to keep generations off public feed\n\n## API Documentation\n\nFull docs: https:\u002F\u002Fenter.pollinations.ai\u002Fapi\u002Fdocs\n","# Pollinations v1.0.2\n\nUnified AI platform for generating and analyzing text, images, videos, and audio with 25+ models.\n\n## API Key\n\nGet free or paid keys at https:\u002F\u002Fenter.pollinations.ai\n- Secret Keys (`sk_`): Server-side, no rate limits (recommended)\n- Optional for many operations (free tier available)\n\n### Runtime Requirements\n\n| Type | Name | Required |\n|------|------|----------|\n| Env | `POLLINATIONS_API_KEY` | Optional (free tier works without) |\n| Bin | `curl` | Yes |\n| Bin | `jq` | Yes |\n| Bin | `base64` | Yes |\n\n## Operations & Scripts\n\n### 1. Text\u002FChat Generation (`scripts\u002Fchat.sh`)\n\nGenerate text using 25+ LLM models with OpenAI-compatible API.\n\n**Usage:**\n```bash\nscripts\u002Fchat.sh \"your message\"\nscripts\u002Fchat.sh \"your message\" --model claude --temp 0.7\nscripts\u002Fchat.sh \"explain quantum physics\" --model openai --max-tokens 500\nscripts\u002Fchat.sh \"list 3 colors\" --json --model openai\nscripts\u002Fchat.sh \"solve this step by step\" --model o3 --reasoning-effort high\nscripts\u002Fchat.sh \"translate to French\" --system \"You are a translator\" --model gemini\n```\n\n**Options:**\n- `--model MODEL` — Model name (default: openai)\n- `--temp N` — Temperature 0-2 (default: 1)\n- `--max-tokens N` — Max response length\n- `--top-p N` — Nucleus sampling 0-1\n- `--seed N` — Reproducibility (-1 = random)\n- `--system \"PROMPT\"` — System prompt\n- `--json` — Force structured JSON response\n- `--reasoning-effort LVL` — For o1\u002Fo3\u002FR1 models: high\u002Fmedium\u002Flow\u002Fminimal\u002Fnone\n- `--thinking-budget N` — Token budget for reasoning models\n\n**Models:** openai, claude, gemini, gemini-large, gemini-search, mistral, deepseek, grok, qwen, perplexity, o1, o3, gpt-4, and 15+ more. Use `scripts\u002Fmodels.sh text` to list all.\n\n**Simple text (no script needed):**\n```bash\ncurl \"https:\u002F\u002Fgen.pollinations.ai\u002Ftext\u002FHello%20world\"\n```\n\n### 2. Image Generation (`scripts\u002Fimage.sh`)\n\nGenerate images from text prompts with multiple models and options.\n\n**Usage:**\n```bash\nscripts\u002Fimage.sh \"a sunset over mountains\"\nscripts\u002Fimage.sh \"a portrait\" --model flux --width 1024 --height 1024\nscripts\u002Fimage.sh \"logo design\" --model gptimage --quality hd --transparent\nscripts\u002Fimage.sh \"photo\" --enhance --nologo --private\nscripts\u002Fimage.sh \"art\" --negative \"blurry, low quality\" --seed 42\n```\n\n**Options:**\n- `--model MODEL` — Model (default: flux)\n- `--width N` — Width 16-2048px (default: 1024)\n- `--height N` — Height 16-2048px (default: 1024)\n- `--seed N` — Reproducibility\n- `--output FILE` — Output filename\n- `--enhance` — AI prompt improvement\n- `--negative \"TEXT\"` — Negative prompt (what to avoid)\n- `--nologo` — Remove watermark\n- `--private` — Private generation\n- `--safe` — Enable NSFW filter\n- `--quality LEVEL` — low\u002Fmedium\u002Fhigh\u002Fhd (gptimage only)\n- `--transparent` — Transparent background PNG (gptimage only)\n- `--image-url URL` — Source image for image-to-image\n\n**Models:** flux (default), turbo, gptimage, kontext, seedream, nanobanana, nanobanana-pro. Use `scripts\u002Fmodels.sh image` to list all.\n\n### 3. Image Editing \u002F Image-to-Image (`scripts\u002Fimage-edit.sh`)\n\nTransform or edit existing images using AI.\n\n**Usage:**\n```bash\nscripts\u002Fimage-edit.sh \"make it blue\" --source \"https:\u002F\u002Fexample.com\u002Fphoto.jpg\"\nscripts\u002Fimage-edit.sh \"add sunglasses\" --source photo.jpg --model kontext\nscripts\u002Fimage-edit.sh \"convert to watercolor\" --source input.png --output watercolor.jpg\n```\n\n**Options:**\n- `--source URL\u002FFILE` — Source image (URL or local file, required)\n- `--model MODEL` — Model (default: kontext)\n- `--seed N` — Reproducibility\n- `--negative \"TEXT\"` — Negative prompt\n- `--output FILE` — Output filename\n\n### 4. Video Generation (`scripts\u002Fimage.sh` with video models)\n\nGenerate videos from text prompts or images.\n\n**Usage:**\n```bash\nscripts\u002Fimage.sh \"a cat playing piano\" --model veo --duration 6\nscripts\u002Fimage.sh \"ocean waves\" --model seedance --duration 8 --aspect-ratio 16:9\nscripts\u002Fimage.sh \"timelapse\" --model veo --duration 4 --audio\nscripts\u002Fimage.sh \"animate this\" --model seedance --image-url \"https:\u002F\u002Fexample.com\u002Fphoto.jpg\"\n```\n\n**Options (in addition to image options):**\n- `--model veo|seedance` — Video model (required)\n- `--duration N` — Length in seconds (veo: 4\u002F6\u002F8, seedance: 2-10)\n- `--aspect-ratio RATIO` — 16:9 or 9:16\n- `--audio` — Enable audio generation (veo only)\n- `--image-url URL` — Source image for image-to-video\n\n**Frame interpolation (veo):** Pass two images for first\u002Flast frame interpolation using the API directly:\n```\nhttps:\u002F\u002Fgen.pollinations.ai\u002Fimage\u002Fprompt?model=veo&image[0]=first_frame_url&image[1]=last_frame_url\n```\n\n**Models:** veo (4-8s, audio support, frame interpolation), seedance (2-10s, image-to-video)\n\n### 5. Text-to-Speech \u002F Audio (`scripts\u002Ftts.sh`)\n\nConvert text to speech with multiple voices and formats.\n\n**Usage:**\n```bash\nscripts\u002Ftts.sh \"Hello world\"\nscripts\u002Ftts.sh \"Bonjour le monde\" --voice nova --format mp3\nscripts\u002Ftts.sh \"Welcome\" --voice coral --format wav --output welcome.wav\n```\n\n**Options:**\n- `--voice VOICE` — Voice selection (default: nova)\n- `--format FORMAT` — Output format (default: mp3)\n- `--model MODEL` — Model (default: openai-audio)\n- `--output FILE` — Output filename\n\n**Voices (13):** alloy, amuch, ash, ballad, coral, dan, echo, fable, nova, onyx, sage, shimmer, verse\n\n**Formats (5):** mp3, wav, flac, opus, pcm16\n\n### 6. Image Analysis \u002F Vision (`scripts\u002Fanalyze-image.sh`)\n\nAnalyze and describe images using vision-capable AI models.\n\n**Usage:**\n```bash\nscripts\u002Fanalyze-image.sh \"https:\u002F\u002Fexample.com\u002Fphoto.jpg\"\nscripts\u002Fanalyze-image.sh photo.jpg --prompt \"What objects are in this image?\"\nscripts\u002Fanalyze-image.sh image.png --model claude --prompt \"Extract all text from this image\"\n```\n\n**Options:**\n- `--prompt \"TEXT\"` — Analysis question (default: \"Describe this image in detail\")\n- `--model MODEL` — Vision model (default: gemini)\n\n**Input:** URL or local file (jpg, png, gif, webp)\n\n**Models:** gemini, gemini-large, claude, openai, and other vision-capable models. Use `scripts\u002Fmodels.sh vision` to list all.\n\n### 7. Video Analysis (`scripts\u002Fanalyze-video.sh`)\n\nAnalyze video content using AI vision models.\n\n**Usage:**\n```bash\nscripts\u002Fanalyze-video.sh \"https:\u002F\u002Fexample.com\u002Fvideo.mp4\"\nscripts\u002Fanalyze-video.sh recording.mp4 --prompt \"Summarize the key moments\"\nscripts\u002Fanalyze-video.sh clip.mov --model gemini-large --prompt \"Count the people\"\n```\n\n**Options:**\n- `--prompt \"TEXT\"` — Analysis question (default: \"Describe this video in detail\")\n- `--model MODEL` — Video-capable model (default: gemini)\n\n**Input:** URL or local file (mp4, mov, avi)\n\n**Models:** gemini, gemini-large, claude, openai (video-capable models)\n\n### 8. Audio Transcription (`scripts\u002Ftranscribe.sh`)\n\nTranscribe audio files to text.\n\n**Usage:**\n```bash\nscripts\u002Ftranscribe.sh recording.mp3\nscripts\u002Ftranscribe.sh podcast.wav --model gemini-large\nscripts\u002Ftranscribe.sh \"https:\u002F\u002Fexample.com\u002Faudio.mp3\" --prompt \"Transcribe in French\"\n```\n\n**Options:**\n- `--prompt \"TEXT\"` — Transcription instructions (default: accurate transcription)\n- `--model MODEL` — Audio-capable model (default: gemini)\n\n**Input:** Local file or URL (mp3, wav, flac, ogg, m4a)\n\n**Models:** gemini, gemini-large, gemini-legacy, openai-audio\n\n### 9. List Available Models (`scripts\u002Fmodels.sh`)\n\nDynamically list all available models from the API.\n\n**Usage:**\n```bash\nscripts\u002Fmodels.sh              # List all models\nscripts\u002Fmodels.sh text         # Text\u002Fchat models only\nscripts\u002Fmodels.sh image        # Image generation models\nscripts\u002Fmodels.sh video        # Video generation models\nscripts\u002Fmodels.sh vision       # Vision\u002Fanalysis models\nscripts\u002Fmodels.sh audio        # Audio\u002FTTS models\n```\n\n## API Endpoints Reference\n\n| Operation | Endpoint | Method |\n|-----------|----------|--------|\n| Simple Text | `\u002Ftext\u002F{prompt}` | GET |\n| Chat Completion | `\u002Fv1\u002Fchat\u002Fcompletions` | POST |\n| Image Generation | `\u002Fimage\u002F{prompt}?{params}` | GET |\n| Image-to-Image | `\u002Fimage\u002F{prompt}?image={url}&{params}` | GET |\n| Video Generation | `\u002Fimage\u002F{prompt}?model=veo&{params}` | GET |\n| Image Analysis | `\u002Fv1\u002Fchat\u002Fcompletions` (with image_url) | POST |\n| Video Analysis | `\u002Fv1\u002Fchat\u002Fcompletions` (with video_url) | POST |\n| Audio\u002FTTS | `\u002Fv1\u002Fchat\u002Fcompletions` (openai-audio) | POST |\n| Audio Transcription | `\u002Fv1\u002Fchat\u002Fcompletions` (with input_audio) | POST |\n| List Text Models | `\u002Fv1\u002Fmodels` | GET |\n| List Image Models | `\u002Fimage\u002Fmodels` | GET |\n| List Vision Models | `\u002Ftext\u002Fmodels` | GET |\n\n## Tips\n\n1. **Free tier available**: Many operations work without an API key (rate limited)\n2. **OpenAI-compatible**: Chat endpoint works with existing OpenAI integrations\n3. **Reproducibility**: Use `seed` parameter for consistent outputs across all operations\n4. **Image enhancement**: Use `--enhance` for AI-improved prompts on image generation\n5. **JSON mode**: Use `--json` flag on chat for structured data extraction\n6. **Reasoning models**: Use `--reasoning-effort` with o1\u002Fo3\u002FR1 for controlled thinking depth\n7. **Video from images**: Use `--image-url` with seedance for image-to-video, or veo frame interpolation\n8. **Audio on video**: Use `--audio` with veo model for videos with sound\n9. **Local files**: Analysis scripts (image, video, transcription) accept both URLs and local files\n10. **Private mode**: Use `--private` to keep generations off public feed\n\n## API Documentation\n\nFull docs: https:\u002F\u002Fenter.pollinations.ai\u002Fapi\u002Fdocs\n",{"name":5,"version":24,"metadata":25,"description":7},"1.0.2",{"openclaw":26},{"os":27,"emoji":31,"install":32,"homepage":47,"requires":48,"primaryEnv":50},[28,29,30],"darwin","linux","win32","🧬",[33,40],{"id":34,"os":35,"bins":36,"kind":38,"label":39,"formula":37},"jq-brew",[28],[37],"jq","brew","Install jq via Homebrew",{"id":41,"os":42,"bins":43,"kind":44,"label":45,"command":46},"jq-apt",[29],[37],"shell","Install jq via apt","sudo apt-get install -y jq","https:\u002F\u002Fpollinations.ai",{"env":49,"bins":51},[50],"POLLINATIONS_API_KEY",[52,37,53],"curl","base64","master","4aa004da461d820f4ea5499e58eb8d196cf99016","community\u002Fclawhub\u002Fp\u002Fpollinations",0,"https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge","https:\u002F\u002Fskill-explorer-rho.vercel.app","https:\u002F\u002Fgithub.com\u002FLord1Egypt","Unbreakable. Unstoppable. Unmatched⚡.\r\n Speaker of machine tongues 🤖  | World-builder of decentralized dreams 🌐 | Defender of the digital realm🛡️.","2026-06-10 08:21:01",{"source":8,"skillName":5,"commands":64,"prompt":74,"zipAvailable":75},[65,68,71],{"tool":66,"command":67},"npx","npx skills add Lord1Egypt\u002Fawesome-skill-forge --skill pollinations",{"tool":69,"command":70},"bunx","bunx skills add Lord1Egypt\u002Fawesome-skill-forge --skill pollinations",{"tool":72,"command":73},"pnpm","pnpm dlx skills add Lord1Egypt\u002Fawesome-skill-forge --skill pollinations","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge\u002Fblob\u002Fmaster\u002Fcommunity\u002Fclawhub\u002Fp\u002Fpollinations\u002FSKILL.md",true,[],[78,85,92,99,106,113],{"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":19},"01M785WKJB99G3STR1NF9NRTJW","youtube-content","YouTube transcripts to summaries, threads, blogs.","https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge\u002Fblob\u002Fmaster\u002Fskills\u002Fyoutube-content\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":19},"01M785WEFHB0G2S9YA6EPR3H0E","xurl","X\u002FTwitter via xurl CLI: post, search, DM, media, v2 API.","https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge\u002Fblob\u002Fmaster\u002Fskills\u002Fxurl\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":19},"01M785W98EDN4EFJXJPMQEHCRC","touchdesigner-mcp","Control a running TouchDesigner instance via twozero MCP — create operators, set parameters, wire connections, execute Python, build real-time visuals. 36 native tools.","https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge\u002Fblob\u002Fmaster\u002Fskills\u002Ftouchdesigner-mcp\u002FSKILL.md",[],[],{"skillNo":100,"name":101,"nameZh":6,"description":102,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":103,"categories":104,"keywords":105,"publishedAt":19},"01M785W5S9FP3QBH2V191E025P","test-driven-development","TDD: enforce RED-GREEN-REFACTOR, tests before code.","https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge\u002Fblob\u002Fmaster\u002Fskills\u002Ftest-driven-development\u002FSKILL.md",[],[],{"skillNo":107,"name":108,"nameZh":6,"description":109,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":110,"categories":111,"keywords":112,"publishedAt":19},"01M785W2AS08NSSH9YATCV6FJB","teams-meeting-pipeline","Operate the Teams meeting summary pipeline via Hermes CLI — summarize meetings, inspect pipeline status, replay jobs, manage Microsoft Graph subscriptions.","https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge\u002Fblob\u002Fmaster\u002Fskills\u002Fteams-meeting-pipeline\u002FSKILL.md",[],[],{"skillNo":114,"name":115,"nameZh":6,"description":116,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":117,"categories":118,"keywords":119,"publishedAt":19},"01M785VXKW4T34BTP1SCHW1R7F","systematic-debugging","4-phase root cause debugging: understand bugs before fixing.","https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge\u002Fblob\u002Fmaster\u002Fskills\u002Fsystematic-debugging\u002FSKILL.md",[],[]]