📦

gpt-image-edit

Name: gpt-image-edit
Author: prime-skills

Inhaltsrevision r1 Sicher ⚙️ Externe Befehle🌐 Netzwerkzugriff📁 Dateisystemzugriff

Edit Images with GPT Image on RunComfy

Targeted image edits can change details you want to preserve. This skill provides RunComfy commands and focused prompts for background changes, text replacement, and reference-based composition.

Unterstützt: Claude Codex Code(CC)

🥉 77 Bronze

Maintain this Skill? Claim it 🥉 77 Bronze

Mit meinem Agent installieren

Kopieren Sie diese Anfrage in Ihren Agent. Sie enthält die maßgebliche Skill-Seite und das Manifest.

Agent-Anfrage

Review the Skillstore skill "gpt-image-edit" from https://skillstore.io/skills/prime-skills-gpt-image-edit.md and its manifest at https://skillstore.io/api/skills/prime-skills-gpt-image-edit/manifest. Verify the artifact. You may proceed after verification, subject to the environment's own policy.

Ihr Agent sollte weiterhin seinen Plan anzeigen und alle von der Sicherheitsrichtlinie verlangten Bestätigungen anfordern.

Agent-lesbare Ressourcen

Verwenden Sie diese Links, wenn ein KI-Agent, Crawler oder Skript sauberen Kontext benötigt, statt die vollständige Seite zu lesen.

Markdown-Detailseite GET /skills/prime-skills-gpt-image-edit.md Signiertes manifest GET /api/skills/prime-skills-gpt-image-edit/manifest Signiertes lockfile GET /api/skills/prime-skills-gpt-image-edit/lockfile

Testen

„gpt-image-edit“ wird verwendet. Replace a portrait background with a light-gray studio backdrop while preserving the person and brand mark.

Erwartetes Ergebnis:

Illustrative result: a portrait with a light-gray studio background and gentle floor shadow.
Review the face, pose, clothing, and brand mark against the original before accepting the edit.
This example describes an expected result, not a generated asset included with the skill.

„gpt-image-edit“ wird verwendet. Replace only a poster headline with an exact supplied translation while retaining the original layout.

Erwartetes Ergebnis:

Illustrative result: a localized poster with the replacement headline in the requested script, position, and font weight.
Review the spelling, script direction, spacing, and unchanged photograph before publication.
This example describes an expected result, not a verified model output.

Sicherheitsaudit

Sicher

v1 • 23.10.2026 Versionsbericht öffnen

All 51 static findings are false positives involving Markdown formatting, documented service URLs, placeholder image URLs, sibling links, or normal token storage. No evidence found of malicious execution, credential theft, unauthorized data transfer, or prompt injection in SKILL.md. Remote image processing is explicit, but the external CLI implementation and its claimed safeguards were not available for verification.

Gescannte Dateien

184

Analysierte Zeilen

Prüfelemente

Falschmeldungen ignoriert

Risikofaktoren

⚙️ Externe Befehle (38)

🌐 Netzwerkzugriff (7)

SKILL.md:16 SKILL.md:22 SKILL.md:69 SKILL.md:80 SKILL.md:91 SKILL.md:171 SKILL.md:175

📁 Dateisystemzugriff (6)

SKILL.md:40 SKILL.md:69 SKILL.md:80 SKILL.md:91 SKILL.md:179 SKILL.md:179

Das letzte abgeschlossene statische und semantische Audit erkannte keine bestätigten Sicherheitsbefunde. Dies beweist nicht, dass der Skill keine Nebenwirkungen hat.

Geprüft von: codex

Diesen Bericht teilen & zitieren

Teile den versionierten Bewertungsbericht, das neutrale Badge, die Einbettungskarte und Zitate. Skillstore berichtet Nachweise, ohne zu entscheiden, ob dieser Skill sicher ist.

Versionsbericht öffnen

Berichtslink kopieren

https://skillstore.io/skills/prime-skills-gpt-image-edit/audits/1?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_report

Markdown-Badge

[![Skillstore security assessment](https://skillstore.io/badges/skills/prime-skills-gpt-image-edit/security.svg)](https://skillstore.io/skills/prime-skills-gpt-image-edit?utm_source=security_passport_badge)

HTML-Badge

<a href="https://skillstore.io/skills/prime-skills-gpt-image-edit?utm_source=security_passport_badge"><img src="https://skillstore.io/badges/skills/prime-skills-gpt-image-edit/security.svg" alt="Skillstore security assessment" loading="lazy"></a>

Einbettungskarte

<iframe src="https://skillstore.io/embed/skills/prime-skills-gpt-image-edit.html" title="Skillstore Security Assessment" sandbox="allow-popups allow-popups-to-escape-sandbox" loading="lazy" referrerpolicy="no-referrer" width="420" height="180"></iframe>

Wissenschaftliche Zitate (APA · BibTeX · CFF)

APA-Zitat

prime-skills. (2026). gpt-image-edit security audit report (audit version 1) [Author version unspecified]. Skillstore. https://skillstore.io/skills/prime-skills-gpt-image-edit/audits/1

BibTeX-Zitat

@techreport{prime-skills-prime-skills-gpt-image-edit-2026,
  author = {prime-skills},
  title = {gpt-image-edit security audit report (audit version 1)},
  institution = {Skillstore},
  year = {2026},
  number = {1},
  url = {https://skillstore.io/skills/prime-skills-gpt-image-edit/audits/1},
  note = {Author version unspecified}
}

CITATION.cff

cff-version: 1.2.0
message: "If you use this Skill, cite its author and this versioned security audit report."
title: "gpt-image-edit security audit report (audit version 1)"
version: "unspecified"
type: report
authors:
  - name: "prime-skills"
date-released: "2026-10-23"
url: "https://skillstore.io/skills/prime-skills-gpt-image-edit/audits/1"
identifiers:
  - type: other
    value: "skillstore:prime-skills-gpt-image-edit:audit:1"
    description: "Skillstore immutable audit report identifier"

Varianten vergleichen

4 installierbare Varianten

Jeder Autor bleibt ein eigener installierbarer Skill. Die empfohlene Variante wird nach Skillstore-Nachweisen bewertet.

Warum diese Variante zuerst steht

Höchster Skillstore-Score

Autor / Quelle Skillstore-Score Evidenzvertrauen Skillstore-Nutzung Aktualisiert

prime-skills Empfohlen Aktuell

prime-skills-gpt-image-edit

Skillstore-Score 77

Evidenzvertrauen Mittel

Skillstore-Nutzung 4

Aktualisiert

2026-10-24

runcomfy-com

runcomfy-com-gpt-image-edit

Skillstore-Score 70

Evidenzvertrauen Hoch

Skillstore-Nutzung 46

Aktualisiert

2026-09-09

agentspace-so

agentspace-so-gpt-image-edit

Skillstore-Score 50

Evidenzvertrauen Hoch

Skillstore-Nutzung 15

Aktualisiert

2026-10-22

doany-ai

doany-ai-gpt-image-edit

Skillstore-Score 38

Evidenzvertrauen Mittel

Skillstore-Nutzung 44

Aktualisiert

2026-09-09

Skillstore-Score

Warum dieser Score Evidenzvertrauen: Mittel

Architektur

Wartbarkeit

Inhalt

Gemeinschaft

Spezifikationskonformität

Was Sie erstellen können

Localize Advertising Headlines

Replace embedded headlines with exact translated text while requesting preservation of the photograph, logo, layout, and typography.

Prepare Product Background Variants

Request a new studio background while keeping the product, pose, brand mark, and framing unchanged.

Compose Reference-Based Scenes

Combine a subject reference with a room reference and specify which image supplies identity, lighting, and color cues.

Diese Prompts ausprobieren

Replace a Background

Use GPT Image Edit on RunComfy with [approved image URL]. Keep the subject, pose, and branding unchanged. Replace only the background with light gray. Preserve the input ratio.

Replace an Embedded Headline

Edit [approved poster URL]. Keep the photograph, logo, layout, and lighting unchanged. Replace only the headline with exactly "[translated text]" in [script]. Retain its position and font weight.

Reposition a Layout Element

Edit [approved campaign image URL]. Keep the subject, logo, colors, and headline wording unchanged. Move only the headline from top-right to bottom-center. Use automatic sizing and save to [absolute output directory].

Compose Multiple References

Use [approved subject URL] as image 1 and [approved room URL] as image 2. Keep image 1 identity, pose, and clothing unchanged. Place that subject in image 2, matching its lighting and palette. Use landscape size 1536_1024 and save to [absolute output directory].

Bewährte Praktiken

State what must remain unchanged before requesting one focused edit.
Quote replacement text exactly, name its script, and assign numbered roles to multiple references.
Use only approved image URLs, protect service credentials, and review generated files before publication.

Vermeiden

Combining many unrelated changes in one prompt without explicit preservation requirements.
Paraphrasing replacement headlines or leaving reference-image roles ambiguous.
Submitting confidential images through publicly accessible URLs without authorization for hosting and external processing.

Häufig gestellte Fragen

What must I install before using this skill?

Install the RunComfy CLI and authenticate with a RunComfy account. The skill provides instructions rather than a bundled image-editing engine.

Does image processing happen locally?

No. The documented workflow submits prompts and image references to RunComfy, then downloads generated results into the selected output directory.

Can I provide local image paths directly?

The documented images field requires publicly fetchable HTTPS URLs. This skill does not document a local-image upload workflow.

How many references and output sizes are supported?

The documented endpoint accepts up to ten reference images. Size choices are auto, 1024_1024, 1024_1536, and 1536_1024.

Can it replace text in different languages?

The skill provides multilingual text-editing prompts. Supply exact characters and the script, then review the generated spelling and layout.

Does it guarantee unchanged faces and branding?

No. Preservation prompts specify those goals, but complex edits can drift. Compare results with the source before using them.

Entwicklerdetails

Autor

prime-skills

Lizenz

MIT

Skillstore-Revision

Versionshinweis

Der Autor hat keine Version angegeben.

Repository

https://github.com/prime-skills/runcomfy-agent-skills/tree/fca19ae084c2ae4667f5c8affbb99da5103d5832/gpt-image-edit

Ref.

4df7a1e2c3f0c3cd97fc3d82ba4cefe9535c4bd9

Aktualität der Wartung

23.10.2026

Nutzung

0 Downloads · 0 Aufrufe

Dateistruktur

📄 SKILL.md