Agent skill · creative production · sundial-org
pollinations
Pollinations.ai API for AI generation - text, images, videos, audio, and analysis. Use when user requests AI-powered generation (text completion, images, videos, audio, vision/analysis, transcription) or mentions Pollinations. Supports 25+ models (OpenAI, Claude, Gemini, Flux, Veo, etc.) with OpenAI-compatible chat endpoint and specialized generation endpoints.
Why this skill is useful
Adds executable scripts for text, image, and audio generation that provide capabilities not easily inferred from general knowledge.
What it needs
Requires curl installed locally. Requires pollinations account access. About 3k tokens when loaded. Last updated 2026-03-07. 639 stars on the source repository.
What this skill does
Pollinations 🧬 Unified AI platform for text, images, videos, and audio generation with 25+ models. API Key Get free or paid keys at https://enter.pollinations.ai Secret Keys (sk): Server-side, no rate limits (recommended) Optional for many operations (free tier available) Store key in environment variable: Quick Start Text Generation Simple text generation: Chat completions (OpenAI-compatible): Use script: scripts/chat.sh for easy chat completions Image Generation Use script: scripts/image.sh for image generation Audio Generation (TTS) Use script: scripts/tts.sh for text-to-speech API Endpoints Base URLs Chat/Text: https://gen.pollinations.ai/v1/chat/completions Simple Text: https://gen.pollinations.ai/text/{prompt} Image: https://gen.pollinations.ai/image/{prompt}?{params} Video: https://gen.pollinations.ai/image/{prompt}?{params} (generates video) Supported Operations 1. Text/Chat Generation Models: OpenAI, Claude, Gemini, Mistral, DeepSeek, Grok, Qwen Coder, Perplexity, and 20+ more Common models: openai, claude, gemini, mistral, deepseek, qwen, gpt-4, o1, o3 Parameters: model (string): Model name/ID messages (array): Chat messages with roles (system/user/assistant) temperature (number): 0-2, default 1 maxtokens (number): Max response length topp (number): Nucleus sampling, default 1 seed (number): Reproducibility (-1 for random) jsonMode (boolean): Force JSON response reasoningeffort (string): For o1/o3/R1 (high/medium/low/minimal/none) thinkingbudget (number): Tokens for reasoning (thinking models) Vision support: Include imageurl in message content for multi-modal: 2. …
How to use it
Reference it in AdaL, Claude Code, Cursor or any coding agent — nothing to install:
@skills sundial-org/pollinations