Skip to content
Get packs

AI Studio Image

Generates humanized, phone-style photos via Google AI Studio (Gemini/Imagen) from a text request.

Source Download skill
Repository
sickn33/agentic-awesome-skills
Stars
49,023
Licence
MIT
Files
8 files

What it does

Once installed, the agent can turn a plain request like a café scene into an image generation job on Google AI Studio. Before calling the image API, it rewrites the prompt with layers meant to make the result look like a casual smartphone photo, such as natural light, slight imperfections and realistic skin texture. It then runs bundled Python scripts that send the request to Google's Gemini or Imagen models and save the output to a local folder.

Great for

  • Social media creators who want lifestyle or influencer-style images without a photo shoot
  • Educators who need clean, readable visuals for course material or slides
  • Developers already set up with a Google AI Studio API key who want a scripted image pipeline

Skip it if

  • Anyone who needs to present images as real photographs of real people, since the skill is designed to make AI output look like an unedited phone photo and could be used to mislead
  • Users who cannot pay for image models: several listed models require --force-paid and cost $0.02 to $0.134 per image
  • Workflows that depend on the missing api-reference.md file, which the catalog copy does not include

Try asking

  • “Create a square Instagram image of a young woman drinking coffee in a café, influencer mode”
  • “Make a 9:16 stories visual for a educational tutorial about budgeting, educational mode”
  • “Generate a 16:9 YouTube thumbnail background with natural window light”
Step-by-step guide: how to use AI Studio ImageInstall, first run, examples, tips and FAQs

Install in 3 steps

  1. 1

    Download the skill

    The ZIP contains the 8 original files, the MIT licence and an attribution note.

    ai-studio-image.zip
  2. 2

    Add it to your agent

    Claude Code (all projects)

    mkdir -p ~/.claude/skills && unzip ai-studio-image.zip -d ~/.claude/skills/

    Claude Code / Agent SDK (this project only)

    mkdir -p .claude/skills && unzip ai-studio-image.zip -d .claude/skills/

    Claude apps (web/desktop): Settings → Capabilities → Skills → Upload skill, and choose the ZIP.

  3. 3

    Ask for the task

    No special command needed — the agent reads the skill's description and loads it when your request matches. Try one of the prompts above.

Get better results

  • Review the generated prompt and output before publishing, and do not present AI images as real photos of real people.
  • Start with the free-tier or cheapest model and check current pricing on Google's site, since the costs in SKILL.md may be out of date.
  • Keep API keys in a .env file outside shared folders and never commit it to version control.

What's inside

  • references/prompt-engineering.md
  • references/setup-guide.md
  • scripts/config.py
  • scripts/generate.py
  • scripts/prompt_engine.py
  • scripts/requirements.txt
  • scripts/templates.py
  • SKILL.md

Redistributed unmodified from sickn33/agentic-awesome-skills under the MIT licence. The assessment was drafted with AI from the skill's files on 2026-10-29. Skills can instruct your agent to run code — read SKILL.md and any scripts before installing.