CtrlK
BlogDocsLog inGet started
Tessl Logo

imagegen

Use when the user asks to generate or edit images via the OpenAI Image API (for example: generate image, edit/inpaint/mask, background removal or replacement, transparent background, product shots, concept art, covers, or batch variants); run the bundled CLI (`scripts/image_gen.py`) and require `OPENAI_API_KEY` for live calls.

67

2.16x
Quality

92%

Does it follow best practices?

Impact

65%

2.16x

Average score across 11 eval scenarios

SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Evaluation results

0%

-80%

Background Replacement for Product Photo

edit-invariants-specification

Criteria
Baseline
With context

Uses edit command

0%

0%

Explicitly lists what to change

100%

0%

Explicitly lists invariants

100%

0%

0%

Game Asset Collection

batch-workflow-with-temp-cleanup

Criteria
Baseline
With context

Creates JSONL in tmp/imagegen/

0%

0%

Correct JSONL format

0%

0%

Uses generate-batch command

0%

0%

Cleans up temporary JSONL

0%

0%

30%

-40%

Landing Page Hero Background

augmentation-without-invention

Criteria
Baseline
With context

Adds layout constraints implied by use case

40%

0%

Does not invent new subjects

100%

100%

Stays focused on user request

100%

0%

100%

25%

Premium Brand Campaign Image

restraint-keywords-to-avoid-tacky-output

Criteria
Baseline
With context

Uses restraint keywords

100%

100%

Includes explicit Avoid: line

37%

100%

Avoids generic buzzwords

100%

100%

100%

100%

Product Cutout with Transparent Background

transparent-background-format-validation

Criteria
Baseline
With context

Requests transparent background

0%

100%

Sets compatible output format

0%

100%

Uses edit or generate appropriately

0%

100%

0%

-50%

Product Label Design

verbatim-text-rendering

Criteria
Baseline
With context

Quotes text verbatim

0%

0%

Specifies typography for main text

100%

0%

Specifies typography for subtitle

100%

0%

Requires exact rendering

0%

0%

95%

73%

Product Photography for E-commerce

structured-prompt-augmentation

Criteria
Baseline
With context

Uses taxonomy classification

0%

100%

Structured prompt format

0%

85%

Includes constraints to avoid tacky output

40%

100%

Does not invent new creative elements

80%

100%

100%

80%

Targeted Object Removal with Mask

mask-based-inpainting

Criteria
Baseline
With context

Uses edit command

0%

100%

Provides mask file

30%

100%

Provides input image

25%

100%

Specifies edit intent in prompt

0%

100%

100%

100%

Technical Infographic

quality-parameter-selection

Criteria
Baseline
With context

Uses quality flag

0%

100%

Selects quality=high

0%

100%

100%

80%

Virtual Clothing Try-On

input-fidelity-for-strict-edits

Criteria
Baseline
With context

Uses edit command

0%

100%

Sets input_fidelity=high

0%

100%

Specifies identity preservation in prompt

100%

100%

100%

100%

Website Hero Image

cli-first-approach

Criteria
Baseline
With context

Uses bundled CLI script

0%

100%

Does not create custom script

0%

100%

Repository
foryourhealth111-pixel/Vibe-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.