스킬 character-design-sheet
📦

character-design-sheet

콘텐츠 리비전 r1 중간 위험 ⚙️ 외부 명령어🌐 네트워크 접근

Crear hojas de diseño de personajes consistentes

Los generadores de imágenes con IA suelen cambiar un personaje entre imágenes. Esta habilidad guía a Claude, Codex y Claude Code mediante hojas de referencia, anclas de descripción y planificación de LoRA.

지원: Claude Codex Code(CC)
Maintain this Skill? Claim it ⚠️ 50 나쁨

내 에이전트로 설치

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

에이전트 요청
Review the Skillstore skill "character-design-sheet" from https://skillstore.io/skills/halt-catch-fire-character-design-sheet.md and its manifest at https://skillstore.io/api/skills/halt-catch-fire-character-design-sheet/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.

테스트해 보기

"character-design-sheet" 사용 중입니다. I need a recurring fantasy merchant for a game prototype.

예상 결과:

  • Un ancla visual reutilizable de 50 palabras para el mercader.
  • Un plan de turnaround de cuatro vistas con ropa y proporciones fijas.
  • Un registro de paleta para piel, cabello, tela, ribetes y accesorios.

"character-design-sheet" 사용 중입니다. My comic character changes face shape between images.

예상 결과:

  • Un diagnóstico de desviación centrado en pistas vagas sobre edad, cabello, ojos y rostro.
  • Una estructura de prompt más sólida que repite primero los detalles de identidad.
  • Un plan de hoja de expresiones para vistas neutra, feliz, enojada, triste, sorprendida y pensativa.

"character-design-sheet" 사용 중입니다. I want to use a LoRA for a long visual novel project.

예상 결과:

  • Una lista de verificación de cobertura de imágenes de referencia para poses, iluminación, atuendos y primeros planos.
  • Una recomendación de palabra de activación y escala para una recuperación consistente del personaje.
  • Un plan de validación que compare las escenas generadas con la hoja de referencia.

보안 감사

중간 위험
v4 • 2026. 7. 6. 버전별 보고서 열기

The skill is not malicious, but it depends on broad belt CLI access and third-party inference services. Real command and network findings were confirmed, while markdown diagrams, templates, and the line 207 reconnaissance hit were dismissed as false positives. Publication should require clear user confirmation for login, installs, remote app runs, and possible service costs.

1
스캔된 파일
282
분석된 줄 수
9
검토 항목
0
오탐 무시됨

확인된 보안 우려 사항 (1)

중간
Overbroad Belt CLI Permission
The skill allows Bash(belt *) and then asks users to log in and run remote inference commands. This grants broad access to belt subcommands beyond the listed image examples.
The allowed-tools declaration permits every belt subcommand, and the quick start uses account login and app execution. No malicious intent appears, but the permission scope is broader than needed.
기능 검토 항목 (9)

이 스킬에 대해 예상될 수 있는 실제 로컬 기능이므로 검토가 필요하지만, 확인된 악의적 동작으로는 집계되지 않습니다.

중간
Ruby/shell backtick execution
> **Install the belt CLI skill:** `npx skills add belt-sh/cli`
Line 7 gives an npx command to install another CLI skill, which is real external command execution. It is transparent setup guidance, but it still asks users to run code from an external package source.
중간
Ruby/shell backtick execution
```bash
The quick start runs belt login and belt app run against a remote image model. This is intended behavior, but it executes an external CLI and may send prompt data to a third-party service.
중간
Ruby/shell backtick execution
```bash
This bash block runs several belt app run commands and a stitch-images job. The commands are fixed examples, but they still invoke external processing through the belt CLI.
중간
Ruby/shell backtick execution
```bash
The expression sheet example contains belt app run commands for remote image generation. There is no command injection evidence, but the external CLI execution risk is real.
중간
Ruby/shell backtick execution
```bash
The LoRA example invokes belt app run with a local LoRA path and remote model. This can transmit prompt and file reference data to an external inference workflow.
중간
Ruby/shell backtick execution
```bash
The related skills block provides npx skills add commands for additional external skill installs. They are optional documentation, but they remain shell commands that fetch external content.
중간
Ruby/shell backtick execution
```
The range includes the belt app store command, which uses the permitted external CLI to browse remote apps. The risk is low in intent but still involves external command and network use.
낮음
Hardcoded URL
Create consistent characters across multiple AI-generated images via [inference.sh](https://inferenc
Line 11 identifies inference.sh as the external service used for image generation. This is disclosed, but it confirms the skill depends on third-party network processing.
낮음
Hardcoded URL
> Requires inference.sh CLI (`belt`). [Install instructions](https://raw.githubusercontent.com/infer
Line 15 links to GitHub-hosted install instructions for the required CLI. This is transparent setup documentation, but it is still a hardcoded external dependency.
감사자: codex 감사 이력 보기 →
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
보안 평가

보고서 링크 복사

https://skillstore.io/skills/halt-catch-fire-character-design-sheet/audits/4?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_report

Markdown 배지

[![Skillstore security assessment](https://skillstore.io/badges/skills/halt-catch-fire-character-design-sheet/security.svg)](https://skillstore.io/skills/halt-catch-fire-character-design-sheet?utm_source=security_passport_badge)

HTML 배지

<a href="https://skillstore.io/skills/halt-catch-fire-character-design-sheet?utm_source=security_passport_badge"><img src="https://skillstore.io/badges/skills/halt-catch-fire-character-design-sheet/security.svg" alt="Skillstore security assessment" loading="lazy"></a>

임베드 카드

<iframe src="https://skillstore.io/embed/skills/halt-catch-fire-character-design-sheet.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

halt-catch-fire. (2026). character-design-sheet security audit report (audit version 4) [Author version unspecified]. Skillstore. https://skillstore.io/skills/halt-catch-fire-character-design-sheet/audits/4

BibTeX 인용

@techreport{halt-catch-fire-halt-catch-fire-character-design-sheet-2026, author = {halt-catch-fire}, title = {character-design-sheet security audit report (audit version 4)}, institution = {Skillstore}, year = {2026}, number = {4}, url = {https://skillstore.io/skills/halt-catch-fire-character-design-sheet/audits/4}, 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: "character-design-sheet security audit report (audit version 4)" version: "unspecified" type: report authors: - name: "halt-catch-fire" date-released: "2026-07-06" url: "https://skillstore.io/skills/halt-catch-fire-character-design-sheet/audits/4" identifiers: - type: other value: "skillstore:halt-catch-fire-character-design-sheet:audit:4" description: "Skillstore immutable audit report identifier"

변형 비교

설치 가능한 변형 2개

각 작성자의 스킬은 별도의 설치 항목으로 유지됩니다. 추천 변형은 Skillstore 근거로 순위가 정해집니다.

이 변형이 1위인 이유

Skillstore 점수가 가장 높음
101-skills 권장

101-skills-character-design-sheet

Skillstore 점수 77
증거 신뢰도 중간
Skillstore 사용량 27
업데이트됨

2026-10-12

halt-catch-fire-character-design-sheet

Skillstore 점수 50
증거 신뢰도 중간
Skillstore 사용량 44
업데이트됨

2026-09-09

Skillstore 점수

이 점수의 이유 증거 신뢰도: 중간
55
아키텍처
85
유지보수성
87
콘텐츠
67
커뮤니티
83
사양 준수

만들 수 있는 것

Preparar referencias de personajes para juegos

Crea referencias frontales, laterales, posteriores, de atuendos y de color antes de producir arte para juegos.

Planificar hojas de expresiones para cómics

Crea un conjunto repetible de rostros y emociones para personajes recurrentes de cómic o novela visual.

Estandarizar la dirección artística con IA

Documenta anclas, paletas y notas de LoRA para que un equipo pueda generar escenas consistentes.

이 프롬프트를 사용해 보세요

Iniciar una hoja de personaje
Create a character design sheet plan for [character idea]. Include a description anchor, turnaround views, expressions, palette notes, and missing questions.
Crear un conjunto de prompts de turnaround
Turn this character description into matching front, three-quarter, side, and back view prompts. Keep the identity details unchanged.
Diagnosticar desviaciones de consistencia
Review my character prompts for consistency drift. Identify weak visual anchors, missing color details, and changes that may alter the character.
Planificar un flujo de trabajo de personaje con LoRA
Design a LoRA preparation plan for this character. Specify reference image coverage, trigger wording, scale guidance, sheet outputs, and validation checks.

모범 사례

  • Escribe un ancla de descripción detallada y reutilízala exactamente.
  • Registra colores exactos, proporciones, ropa y marcas distintivas.
  • Genera vistas de referencia y expresiones antes de imágenes de escenas complejas.

피하기

  • Empezar la generación de escenas antes de definir una hoja de referencia.
  • Usar rasgos vagos como joven, atuendo genial o cabello rojo.
  • Cambiar detalles de identidad o el orden del prompt entre generaciones.

자주 묻는 질문

¿Esta habilidad genera imágenes directamente?
Proporciona orientación y ejemplos de comandos. La generación directa requiere la belt CLI y un servicio de inferencia compatible.
¿Puede garantizar personajes idénticos?
No. Mejora la consistencia mediante anclas, hojas y planificación de LoRA, pero el resultado del modelo aún puede variar.
¿Qué es un ancla de descripción?
Es un párrafo de identidad detallado que se reutiliza en cada prompt para que el modelo vea detalles estables del personaje.
¿Cuándo debería usar LoRA?
Usa LoRA cuando un proyecto necesite muchas imágenes del mismo personaje en distintas escenas, poses o atuendos.
¿Esto es útil sin la belt CLI?
Sí. Los métodos de hojas de referencia y la estructura de prompts pueden usarse con otras herramientas de generación de imágenes.
¿Qué datos pueden salir de mi máquina?
El texto de los prompts, las referencias de imágenes y las rutas de LoRA pueden enviarse cuando ejecutas comandos de inferencia remota.

개발자 세부 정보

작성자

halt-catch-fire

라이선스

MIT

Skillstore 리비전

r1

버전 안내

작성자가 버전을 선언하지 않았습니다.

참조

a06681402992ceae98ba04d54cfd4ab004862696

유지보수 최신성

2026. 7. 18.

사용량

3 다운로드 · 0 조회

파일 구조

📄 SKILL.md

halt-catch-fire의 다른 스킬

전체 보기
전체 보기