Every premium and members-only resource for $9.99/month, as a no-commitment subscription. See the plans

PalateKit

Sign in
Menu

Request a resource

Describe the resource you are missing in one sentence. We will email you when it is published.

0 / 280

A page, a video or an image online.

Unlock PalateKit

Unlock everything

Plan

Paying means accepting our terms of sale.

Secure payment by Stripe. Receipts and invoices sent by email.

Welcome back

Sign in to install, download or save this resource. A free account is enough for free resources.

Prompt specification for generated images v1.0.0

Use this resource to turn an image request into precise prompts and generate the visuals

New

  • 555 downloads
  • 151 likes
  • 176 saves

Free

Install with the CLI

In a terminal, from the folder you want:

npx --yes palatekit@latest install image-prompt-spec-generation

With no option, the skill goes to ~/.agents/skills/; add --agent claude-code (or codex, cursor…) to target an agent.

First time: connect the CLI with

npx --yes palatekit@latest login

The agent writes a spec per image (subject, style, composition, lighting, aspect ratio, negative constraints) for the fal-ai/nano-banana-pro model, then generates the files when automation is configured. You get reusable prompts and the images.

Mostly picked by

Updated November 2, 2026

Card for the “Prompt specification for generated images” skill

Details

Works in
Install guides
Generates with
Your agent's model
Licence
MIT

Similar resources

View all

What you get

  • SKILL.md: intake, prompt specification and quality check
  • references/automation.md: generation automation

Good fit for

  • You want an illustration or thumbnail for an article
  • Your generated images vary too much from one run to the next

Not for

    Tags

    • image
    • prompt
    • illustration
    • generation

    About

    You say

    “Generate a watercolour illustration of a craftsman's workshop at sunrise, 16:9.”

    Card for the “Prompt specification for generated images” skill

    Skill published by sanky369 under the MIT license, delivered in its original version.

    Show more

    How to use it

    1. Install the skill in your agent's skills folder
    2. Ask your agent to turn an image request into precise prompts and generate the visuals
    3. Review and adjust the result

    Content preview

    Files

    • LICENSE1 KB
    • NOTICE-PALATEKIT.md0.5 KB
    • references/automation.md5.2 KB
    • SKILL.md7.7 KB

    Origin and licence

    Listed unmodified

    Author
    sanky369
    Source
    github.com/sanky369/vibe-building-skills/tree/e9714d8decbc9a76eaab3bd85866117b8010e9bc/skills/creative/image-generation
    Licence
    MIT

    Notice

    « image-generation » (sanky369, MIT) livré dans sa version d'origine : fiche en français et en anglais par PalateKit.

    User reviews

    –

    No ratings yet

    Loading reviews…

    Delete your review?

    Your rating and comment will be removed from the page.