Content & Marketing · IN-DEPTH PROFILE

gpt-image-edit

GPT Image Edit is a RunComfy guide for OpenAI GPT Image 2's edit endpoint.

View listed source ↗Installation guide ↓
Best for

Designers localizing image assets

What you get

Rewrite embedded text + Compose multiple references

Main limitation

It supports a bounded set of output sizes and fewer inputs than the Nano Banana batch route.

First risk

Confidential references and false brand output. Up to ten external image URLs and the edit prompt are processed remotely, while output may alter trademarks, claims, or people. Use authorized assets, short-lived access, cost controls, and full-resolution human review.

EVIDENCE FRESHNESS

Three checks, kept separate

A recent source check is not a runtime test or security audit.

Upstream sourceChecked 2026-08-20

Pinned revision · fca19ae0

Open pinned commit ↗
SkillSignal profileSource-grounded

Updated 2026-08-20

Runtime & securityNot independently verified

Source review does not certify behavior or safety.

30-SECOND BRIEF

What it does—and when it fits

GPT Image Edit is a RunComfy guide for OpenAI GPT Image 2's edit endpoint. It emphasizes preservation-first instructions, multilingual embedded-text rewrites, layout-precise changes, and compositions using up to ten publicly fetchable references, with the first image treated as primary.

INSTALL BY AGENT

Choose your Agent

Paths come from official Agent docs or the universal installer behind skills.sh. Compatibility still follows this Skill's record.

Native

This Skill's current record explicitly names this Agent. Still inspect scripts, permissions, and external dependencies first.

Project scope.claude/skills/gpt-image-edit/
Personal scope~/.claude/skills/gpt-image-edit/

Use project scope for team sharing and personal scope across repositories. The installer defaults to project scope; add -g for personal scope.

Install command (project scope)npx skills add prime-skills/runcomfy-agent-skills --skill gpt-image-edit --agent claude-code
Official agent docs

Claude Code discovers custom Skill folders automatically at project or personal scope.

View path evidence ↗

TYPICAL WORKFLOW

A practical workflow

01

Rewrite embedded text

Replace visible copy in Latin, CJK, kana, Cyrillic, Arabic, and other scripts while retaining layout.

02

Compose multiple references

Assign subject, scene, palette, or layout roles across up to ten images.

03

Make layout-precise edits

Move headlines, swap calls to action, or preserve identity across localized variants.

THE TRADEOFFS

Advantages and tradeoffs

Notable strengths

  1. This profile is manually organized around the current upstream SKILL.md workflow.
  2. The capability boundary remains explicitly tied to prime-skills/runcomfy-agent-skills.
  3. Core uses, limitations, and risks are separated for pre-install review.

Limitations

  1. It supports a bounded set of output sizes and fewer inputs than the Nano Banana batch route.
  2. Text spelling, identity, logos, and exact pixel layout still require careful visual proofing.

COMPARE THE TRADEOFF

Consider these close alternatives

These are deterministic nearby candidates, not paid placements or a universal ranking. Open the full profile before choosing.

01

Same job family · native to Codex + Claude Code

ai-seo

Technical and editorial SEO workflows for product-led teams.
Tradeoff to check
Detailed package files are not fully catalogued.
First risk
Review before install · Medium
Source state
Editorial source
Open profile ↗
02

Same job family · native to Codex + Claude Code

copywriter

Product copy formulas for UX writing, launches and conversion moments.
Tradeoff to check
Detailed package files are not fully catalogued.
First risk
Review before install · Medium
Source state
Editorial source
Open profile ↗
03

Same job family · native to Codex + Claude Code

marketing-mode

A broad set of growth strategies organized for product teams.
Tradeoff to check
Detailed package files are not fully catalogued.
First risk
Review before install · Medium
Source state
Editorial source
Open profile ↗
Compare more in the directory →

BEST FIT

Who it is for

→

Designers localizing image assets

→

Teams composing multi-reference campaign visuals

BEFORE YOU USE IT

Risks to review before use

High

Confidential references and false brand output

Up to ten external image URLs and the edit prompt are processed remotely, while output may alter trademarks, claims, or people. Use authorized assets, short-lived access, cost controls, and full-resolution human review.

Medium

Upstream instruction drift

Behavior can change with upstream updates. Record the commit used for important workflows and review updates before adoption.

SECURITY

What the permission profile means

  • Declared access remains governed by the current upstream SKILL.md and runtime requests.
  • Treat repository files, web content, and tool output as untrusted input.
  • SkillSignal has not independently executed or security-audited this package; external skills.sh labels are not SkillSignal certification.

Not a security certification. External ratings are attributed references. SkillSignal has not independently executed or security-reviewed this Skill.

INSIDE THE PACKAGE

Indexed files

SKILL.mdUpstream Skill instructionsSource-linked

TAGS

image-editingmultilingual-textruncomfy

Manually expanded from the current upstream SKILL.md and linked source at prime-skills/runcomfy-agent-skills, checked 2026-08-20. This is an original summary, not an execution result or security certification.