CtrlK
BlogDocsLog inGet started
Tessl Logo

gpt-image-1-5

Generate and edit images using OpenAI's GPT Image 1.5 model. Use when the user asks to generate, create, edit, modify, change, alter, or update images. Also use when user references an existing image file and asks to modify it in any way (e.g., "modify this image", "change the background", "replace X with Y"). Supports text-to-image generation and image editing with optional mask. DO NOT read the image file first - use this skill directly with the --input-image parameter.

87

2.29x
Quality

82%

Does it follow best practices?

Impact

94%

2.29x

Average score across 3 eval scenarios

SecuritybySnyk

Risky

Do not use without reviewing

SKILL.md
Quality
Evals
Security

Evaluation results

100%

67%

Marketing Banner Image Generation

Quality and size parameter mapping

Criteria
Without context
With context

Quality set to high

0%

100%

Size set to landscape

0%

100%

Absolute script path

0%

100%

uv run invocation

0%

100%

Filename timestamp format

0%

100%

Filename lowercase hyphens

0%

100%

Filename descriptive length

75%

100%

Prompt passed as-is

62%

100%

No image read-back

100%

100%

Three separate commands

83%

100%

90%

49%

Brand Asset Creation for App Launch

Transparent background and filename naming

Criteria
Without context
With context

Transparent background

0%

100%

Quality set to low

0%

100%

Absolute script path

0%

100%

uv run invocation

0%

100%

Filename timestamp prefix

0%

0%

Filename descriptive name

60%

100%

Filename ends in .png

100%

100%

Three asset commands

100%

100%

No image read-back

100%

100%

Filenames documented

100%

100%

92%

42%

Product Photo Retouching: Object Replacement

Masked inpainting workflow

Criteria
Without context
With context

Uses --input-image

0%

100%

Uses --mask parameter

0%

100%

Editing prompt format

100%

100%

Absolute script path

0%

100%

uv run invocation

0%

100%

Filename timestamp format

0%

0%

No pre-edit image read

100%

100%

Mask convention explained

100%

100%

No image read-back

100%

100%

Output filename documented

100%

100%

Repository
intellectronica/agent-skills
Evaluated
Agent
Claude Code
Model
Claude Sonnet 4.6

Table of Contents

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.