skills.rest
byteplus-sa
byteplus-saOFFICIAL
Explore all skills by this author →
GitHub

polym-eval-prompt-optimizer

Rewrite user prompts into structured templates for image and video generation models.

8|Updated May 13, 2026
Search Tags:#image generation#prompt optimization#LLM#video generation#Seedream#Seedance#scenario templates
One-click install
npx skills add https://github.com/byteplus-sa/polym --skill polym-eval-prompt-optimizer
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: polym-eval-prompt-optimizer
Source: https://github.com/byteplus-sa/polym/tree/main/skills/polym-eval-prompt-optimizer
Command: npx skills add https://github.com/byteplus-sa/polym --skill polym-eval-prompt-optimizer

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires openai, and includes scripts (resource) components.

What problem does it solve?

This Skill removes the guesswork of writing high-quality prompts by transforming a user's rough text into structured, model-optimized prompts for image and video generation.

Core Features & Use Cases

  • Prompt Optimization for Multiple Models: Produces optimized prompts tailored to Seedream, Seedance, Gemini/Imagen, Sora, and Veo.
  • Scenario-Specific Prompt Formulas: Applies different prompt structures for ecommerce, advertising, portrait, logo, and try-on use cases.
  • Model-Appropriate Output Format: Outputs an English optimized prompt, a Chinese translation when applicable, and clear improvements and suggestions.

Quick Start

Ask it to optimize your prompt for the target model and scenario, for example: Optimize this prompt for Seedream ecommerce image generation.

Frequently Asked Questions about polym-eval-prompt-optimizer

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I optimize prompts for image and video generation models like Seedream and Sora?▼

Prompt optimization rewrites rough text into structured, model-ready templates for image and video generation. This process tailors your input for specific models like Seedream, Seedance, Sora, and Veo to improve output quality.

Can I generate optimized prompts for specific scenarios like ecommerce and advertising?▼

Yes, prompt optimization applies scenario-specific formulas for ecommerce, advertising, portrait, logo, and try-on use cases. This ensures the generated image or video prompts follow structured templates tailored to your specific creative context.

What do I need to set up before using an LLM for prompt optimization?▼

You need an OpenAI-compatible API setup using a BYTEPLUS_API_KEY and a configured OPTIMIZER_MODEL_ID. You can also optionally specify a BYTEPLUS_BASE_URL to route the prompt optimization requests correctly.

Does the prompt optimizer output both English and Chinese translations?▼

Yes, the prompt optimizer returns structured JSON containing an English optimized prompt and a Chinese translation when applicable. It also includes specific improvements and suggestions to help you understand the prompt enhancements.

What is the best way to structure a rough prompt for video generation?▼

The best way to structure a rough prompt for video generation is to let an LLM rewrite it into a model-appropriate output format. This applies structured prompt formulas tailored to your target scenario and video model.

Related Skills

Explore More Design & Creative Skills→
ovachieverovachiever
52

sglang

Serve LLMs with RadixAttention prefix caching and constrained JSON/regex outputs.

Community
Advanced
bluewaves-creationsbluewaves-creations

media-generation

Generate images and videos via fal.ai models through Cloudflare AI Gateway.

Official
Intermediate
abagamesabagames
11

generating-dot-assets

Convert images into transparent pixel art assets with adjustable color palettes.

Community
Intermediate
PhucMPhamPhucMPham

ai-artist

Craft optimized prompts for LLMs, image generators, and video tools.

Community
Advanced