agentleFS
OpenLaborOpenLabor/openlabor/skills/image-generator/SKILL.md

Image Generator

Skill5 starsChanged 3 months agoMITView on GitHub

Generate images from text prompts using Flux, Imagen, and other AI models

  • Reads credentials

The file

We split this skill into the rules it gives an agent

6 rules. About 0 are common, 3 are distinctive, and 3 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈3

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 3

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Use the exec tool to run use.

    line 22
  2. Distinctive:

    Use "professional", "corporate", "clean" for business content

    line 90
  3. Very specific:

    Use flux-schnell for iteration, then flux-2-pro for the final version

    line 96
  4. Distinctive:

    Use 1:1 for social posts, 16:9 for headers/banners, 9:16 for stories

    line 100
  5. Very specific:

    Start with flux-schnell for speed, upgrade model for final versions

    line 101
  6. Distinctive:

    Never generate inappropriate, misleading, or offensive content

    line 102

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md
<!-- openlabor-connector: images, api_key={{INTERNAL_API_KEY}}, employee={{EMPLOYEE_ID}}, base={{API_BASE_URL}} -->

Image Generator

Generate images from text prompts using AI models (Flux, Imagen, and more).

You have access to image generation through the OpenLabor API.

How to Generate Images

Use the exec tool to run use. Credentials are loaded automatically from the workspace.

use images GENERATE '{"prompt":"your image description","model":"flux-schnell"}'

Parameters

ParameterTypeDefaultDescription
promptstringrequiredDetailed description of the image to generate
modelstring"flux-schnell"Which model to use (see models below)
aspect_ratiostring"1:1"Aspect ratio (1:1, 16:9, 9:16, 4:3, 3:4)
num_imagesstring"1"Number of images (1-4)
output_formatstring"webp"Output format (webp, png, jpg)

Available Models

Model IDSpeedQualityBest For
flux-schnellFast (~5s)GoodQuick drafts, iteration
flux-devMedium (~15s)HighBalanced quality/speed
flux-2-proSlow (~30s)HighestFinal/polished images
imagen-4-fastFast (~5s)GoodQuick Google-quality drafts
imagen-4Medium (~15s)HighBalanced Google quality
imagen-4-ultraSlow (~45s)HighestUltra-quality images

List Available Models

use images MODELS '{}'

Examples

# Social media post image
use images GENERATE '{"prompt":"Modern minimal workspace with laptop showing analytics dashboard, warm lighting, top-down view","model":"flux-schnell","aspect_ratio":"1:1"}'

# Twitter header
use images GENERATE '{"prompt":"Abstract gradient background in deep blue and purple, subtle geometric patterns","model":"flux-dev","aspect_ratio":"16:9"}'

# Instagram story
use images GENERATE '{"prompt":"Bold typographic quote card, white text on dark background, motivational","model":"flux-schnell","aspect_ratio":"9:16"}'

# High-quality brand image
use images GENERATE '{"prompt":"Professional product photo of a sleek SaaS dashboard on a MacBook, clean desk setup","model":"flux-2-pro","aspect_ratio":"16:9"}'

Response Format

Returns JSON with:

  • model — Model used
  • images — Array of image URLs (or base64 data URIs for Google models)
  • durationMs — Generation time in milliseconds

Prompt Writing Tips

For Social Media Images

  • Be specific about style: "minimal", "bold", "professional", "playful"
  • Include composition details: "top-down view", "close-up", "wide shot"
  • Mention lighting: "warm lighting", "natural light", "studio lighting"
  • Specify mood: "energetic", "calm", "professional", "casual"

For Brand Content

  • Reference your brand colors if relevant
  • Be specific about what should be in the image
  • Include "no text" if you want a clean image without text
  • Use "professional", "corporate", "clean" for business content

What Works Best

  • Detailed, specific prompts get better results
  • Include style references: "in the style of Apple product photography"
  • Specify what you DON'T want: "no people", "no text", "no watermark"
  • Use flux-schnell for iteration, then flux-2-pro for the final version

Guidelines

  • Generate images that are on-brand and professional
  • Use 1:1 for social posts, 16:9 for headers/banners, 9:16 for stories
  • Start with flux-schnell for speed, upgrade model for final versions
  • Never generate inappropriate, misleading, or offensive content
  • Credit AI generation when required by platform rules

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.