All Prompts
50 prompts in the toolkit
Optimized prompts for OpenAI GPT-5.5 and GPT-5.5 Pro — native multimodality (text, vision, audio, speech), structured output, reasoning models, and function calling. Updated June 2026 for latest API capabilities.
Optimized prompts for Z.AI's GLM-5.2 — the #1 ranked open-weights model on Artificial Analysis. 753B MoE architecture, 1M context, MIT license. Outperforms GPT-5.5 on coding benchmarks at a fraction of the cost. Updated June 2026.
Optimized prompts for Anthropic Claude Fable 5 and Mythos 5 — the first public Mythos-class models. Long-context mastery, vision-native reasoning, software engineering, and scientific research. Updated June 2026.
Optimized prompts for NVIDIA Nemotron 3 Ultra — the first open-weight 550B hybrid Mamba-MoE model. 55B active parameters, 1M context window, 89.1 MMLU. Datacenter-scale agentic reasoning.
Optimized prompts for Ideogram 4.0 — the #2 image generation model with first-ever open weights. JSON-structured prompts with bounding boxes, color palettes, and precision text layouts. Excels at posters, UI mockups, and text-rich designs.
Optimized prompts for Google Gemma 4 12B — the encoder-free any-to-any multimodal model. Handles text, image, audio, and video with 256K context. Apache 2.0 open weights. Laptop-class deployment.
Optimized prompts for NVIDIA Cosmos3-Super — a 64B physical-AI omnimodel that couples action trajectories with video+audio generation. World-model architecture for physics-aware content creation.
Generate a 30-day social media content calendar with varied post types.
Create engaging newsletter templates with consistent structure and tone.