스킬 generating-images

📦

generating-images

Name: generating-images
Author: supercmohq

v0.1.0 콘텐츠 리비전 r1 안전 ⚙️ 외부 명령어

Generate Better Images From Any Creative Brief

Image requests often fail because prompts and model choices do not match the intended result. This skill routes each brief and builds a model-specific prompt.

지원: Claude Codex Code(CC)

🥉 78 브론즈

Maintain this Skill? Claim it 🥉 78 브론즈

내 에이전트로 설치

이 요청을 에이전트에 복사하세요. 공식 Skill 페이지와 매니페스트가 포함되어 있습니다.

에이전트 요청

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

에이전트는 계속해서 계획을 표시하고 보안 정책에서 요구하는 확인을 요청해야 합니다.

에이전트가 읽기 쉬운 리소스

AI 에이전트, 크롤러, 스크립트가 전체 페이지 대신 정리된 컨텍스트만 필요할 때 이 링크를 사용하세요.

Markdown 상세 GET /skills/supercmohq-generating-images.md 서명된 manifest GET /api/skills/supercmohq-generating-images/manifest 서명된 lockfile GET /api/skills/supercmohq-generating-images/lockfile

테스트해 보기

"generating-images" 사용 중입니다. Create a square launch poster with the headline NIGHT RUN and a runner beneath neon city lights.

예상 결과:

A square poster with exact headline placement, high-contrast typography, a centered runner, neon lighting, restrained copy, and fixed layout constraints.

"generating-images" 사용 중입니다. Edit my portrait into a cinematic rainy street while keeping my face and jacket recognizable.

예상 결과:

A reference-guided portrait edit preserving facial identity and clothing, with wet pavement, controlled lens depth, directional rain, and a cool cinematic grade.

"generating-images" 사용 중입니다. Generate three matching editorial images of one chef in different kitchen scenes.

예상 결과:

Three coordinated images with repeated subject and wardrobe details, consistent lighting and palette, and distinct framing for each kitchen scene.

보안 감사

안전

v1 • 2026. 8. 13. 버전별 보고서 열기

All 40 static findings are false positives caused by Markdown code spans or ordinary image-generation guidance. The skill contains no shell execution, system reconnaissance, prompt injection, or other intent-level security issue.

스캔된 파일

430

분석된 줄 수

검토 항목

오탐 무시됨

가장 최근에 완료된 정적·의미론적 감사에서 확인된 보안 발견 사항이 감지되지 않았습니다. 이는 스킬에 부작용이 없음을 증명하지 않습니다.

감사자: codex

이 보고서 공유 및 인용

버전이 지정된 평가 보고서, 중립 배지, 임베드 카드 및 인용을 공유하세요. Skillstore는 근거를 보고하지만 이 Skill의 안전 여부를 판단하지 않습니다.

버전별 보고서 열기

보고서 링크 복사

https://skillstore.io/skills/supercmohq-generating-images/audits/1?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_report

Markdown 배지

[![Skillstore security assessment](https://skillstore.io/badges/skills/supercmohq-generating-images/security.svg)](https://skillstore.io/skills/supercmohq-generating-images?utm_source=security_passport_badge)

HTML 배지

<a href="https://skillstore.io/skills/supercmohq-generating-images?utm_source=security_passport_badge"><img src="https://skillstore.io/badges/skills/supercmohq-generating-images/security.svg" alt="Skillstore security assessment" loading="lazy"></a>

임베드 카드

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

학술 인용 (APA · BibTeX · CFF)

APA 인용

supercmohq. (2026). generating-images security audit report (audit version 1) [Author version 0.1.0]. Skillstore. https://skillstore.io/skills/supercmohq-generating-images/audits/1

BibTeX 인용

@techreport{supercmohq-supercmohq-generating-images-2026,
  author = {supercmohq},
  title = {generating-images security audit report (audit version 1)},
  institution = {Skillstore},
  year = {2026},
  number = {1},
  url = {https://skillstore.io/skills/supercmohq-generating-images/audits/1},
  note = {Author version 0.1.0}
}

CITATION.cff

cff-version: 1.2.0
message: "If you use this Skill, cite its author and this versioned security audit report."
title: "generating-images security audit report (audit version 1)"
version: "0.1.0"
type: report
authors:
  - name: "supercmohq"
date-released: "2026-08-13"
url: "https://skillstore.io/skills/supercmohq-generating-images/audits/1"
identifiers:
  - type: other
    value: "skillstore:supercmohq-generating-images:audit:1"
    description: "Skillstore immutable audit report identifier"

Skillstore 점수

이 점수의 이유 증거 신뢰도: 중간

아키텍처

100

유지보수성

콘텐츠

커뮤니티

사양 준수

만들 수 있는 것

Create Campaign Graphics

Build posters, banners, thumbnails, and social graphics with controlled copy, hierarchy, palette, and layout.

Develop Consistent Portraits

Generate or edit portraits while preserving facial features, wardrobe, lighting, and visual style across a set.

Produce Cinematic Concepts

Turn scene briefs into cinematic stills with explicit framing, lenses, lighting, materials, grading, and factual constraints.

이 프롬프트를 사용해 보세요

Generate a Simple Image

Create an image of [subject] in [setting]. Use [style], [lighting], and a [aspect ratio] frame.

Design a Copy-Bearing Graphic

Design a [format] for [audience]. Show [subject]. Render "[exact text]" in [type style] at [placement]. Use [colors] and preserve [constraints].

Edit a Reference Image

Edit Image 1 by changing [target] to [new state]. Preserve [identity, geometry, palette, or text]. Match [reference role] from Image 2.

Build a Consistent Image Set

Generate [count] images of [fully repeated subject description]. Keep [wardrobe, palette, lighting, and style] identical. Vary only [shot, action, framing, or ratio].

모범 사례

Provide exact on-image text, required dimensions, and any details that must remain unchanged.
Label each reference image by role, such as subject, style, background, or preserved asset.
Repeat subject, wardrobe, lighting, and palette descriptions in every request for a consistent set.

피하기

Do not rely on vague quality words when concrete materials, lighting, framing, and style are available.
Do not resubmit a pending generation because that can create a second billed job.
Do not assume generated sets share identity when each request lacks the complete repeated description.