Gpt image 2 search
Skill Ryan-yang125/gpt-image-2-skills/skills/gpt-image-2-search
Use this skill whenever a user needs GPT Image 2 or ChatGPT image generation prompt ideas, Image2Studio prompt examples, visual references, style inspiration, reusable prompts, or examples for a subject, scene, product shot, poster, UI mockup, character, portrait, social media visual, composition, lighting setup, camera style, or aesthetic direction.From its SKILL.md
npx -y skills add Ryan-yang125/gpt-image-2-skills --skill gpt-image-2-searchAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
2 things to look at
- no licenseNo license file was found in the repository. Code published without one is not open source by default, so using it at work is a question for whoever answers licensing questions where you are.
- 3 stars3 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
SKILL.md
3.7 KB, 791 tokens by cl100k_base, as published. Nobody here has run it
GPT Image 2 Prompt Search
This skill helps you discover GPT Image 2 prompt and image examples from the public Image2Studio prompt library.
When to Use This Skill
Use this skill when the user:
- Asks for image generation prompt ideas or prompt inspiration
- Wants examples for a visual style, subject, composition, medium, or mood
- Needs reference images before writing or refining a prompt
- Asks for prompts for product shots, posters, characters, UI images, social media visuals, scenes, lighting, or camera styles
- Wants to improve, remix, or compare image-generation prompts
What is GPT Image 2 Prompt Search?
GPT Image 2 Prompt Search is a public Image2Studio search API for finding reusable ChatGPT image generation prompts and matching image references.
Key command:
node scripts/search.mjs --q "cinematic portrait" --limit 8
If the helper script is unavailable, read references/api.md and make the equivalent GET request directly.
How to Help Users Find Prompts
Step 1: Understand What They Need
When a user asks for prompt help, identify:
- The subject or object they want to generate
- The visual style, medium, mood, lighting, or camera language
- The intended output format, such as poster, product shot, portrait, icon, scene, or social media image
Step 2: Search the Prompt Library
Convert the user's request into 2-4 concise English visual keywords, then run:
node scripts/search.mjs --q "<keywords>" --limit 8
Examples:
- User asks for a premium perfume campaign prompt ->
node scripts/search.mjs --q "luxury perfume ad" --limit 8 - User asks for anime character references ->
node scripts/search.mjs --q "anime character sheet" --limit 8 - User asks for clean app icon ideas ->
node scripts/search.mjs --q "isometric app icon" --limit 8
If results are weak, retry once with broader or adjacent visual terms.
Step 3: Verify Relevance Before Recommending
Do not recommend results based only on title matches. Prefer results that align with:
- Subject and scene
- Visual style and medium
- Composition, lighting, camera style, or layout
- Aspect ratio and intended use
- Prompt quality and clarity
Step 4: Present Useful Results
When you find relevant prompts, present them with:
- The prompt title
- Why it matches the user's request
- The prompt or a concise prompt excerpt
- The
imageUrlfor visual reference - The
studioUrlfor opening the prompt in the web editor
Do not call useUrl unless the user explicitly chooses or uses that prompt.
Search Tips
Use specific visual keywords:
cinematic portraitminimal product posteranime character sheetluxury perfume adisometric app iconeditorial fashion photosurreal architecture
Try alternative terms when needed:
- If
posteris weak, trycampaign,editorial, oradvertisement - If
portraitis weak, tryheadshot,fashion photo, orcharacter - If
minimalis weak, tryclean,studio, ormodern
When No Prompts Are Found
If no relevant prompts are found:
- Say that the search did not find a strong match
- Try one broader query if useful
- Offer to write a new prompt directly from the user's request
Read references/api.md only when endpoint parameters, response fields, or error behavior matter.
What ships with it: 2 files
8.9 KB alongside SKILL.md, 1 of them executable
references/
- api.md2.5 KB
scripts/
- search.mjsruns6.3 KB