Token导航 LogoToken导航TokenDH.com
AI 工具只读github未标认证来源可访问clear审计通过

pixel-art像素艺术

Agent Skill

pixel-art 用于处理 GitHub 仓库、Issue、Pull Request 和代码协作信息,适合在 Codex、Claude、Cursor、Gemini CLI 中需要围绕仓库状态、代码变更或协作事项进行整理时使用。可结合来源仓库、安装命令和原始 README 继续核验具体用法。安装前建议确认权限范围、维护状态,以及是否会触发联网、命令执行或文件读写。

总安装

3,644

周安装

146

GitHub Stars

75

下载量

1,180
CodexClaudeCursorGemini CLI

安装说明

本站只整理中文说明和来源信息,不托管安装包,也不代用户安装。

GitHub

来源数

3

许可证

MIT

最后核验

2026-05-01

来源状态

来源可访问

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手,先确认命令和权限,再让它执行。

请帮我安装这个 Agent Skill:pixel-art(像素艺术)
来源仓库:https://github.com/omer-metin/skills-for-antigravity
仓库路径:skills/pixel-art
安装命令:
npx skills add https://github.com/omer-metin/skills-for-antigravity --skill pixel-art
安装前请先检查当前环境是否支持对应 CLI,并向我确认将要执行的命令、安装目录、联网范围和文件读写权限;确认后再执行。

命令行安装

复制命令到本机终端执行。不同来源提供的安装方式可能略有差异;本站展示可直接复制的安装命令,安装前请核对来源页面。

skills.shnpx skills
npx skills add https://github.com/omer-metin/skills-for-antigravity --skill pixel-art

简介

pixel-art 用于处理 GitHub 仓库、Issue、Pull Request 和代码协作信息,适合在 Codex、Claude、Cursor、Gemini CLI 中需要围绕仓库状态、代码变更或协作事项进行整理时使用。

  • 它专注于像素风格内容的生成与管理,适用于游戏或图标设计场景。
  • 可通过 npx skills add 命令从指定 GitHub 仓库安装,需结合原始 README 确认具体调用方式。
  • 安装前建议核实权限范围、维护状态,以及是否涉及联网、命令执行或文件读写操作。
  • pixel-art 属于AI 工具类 Skill,可作为该场景下的辅助能力补充。

SKILL.md

Pixel Art

Identity

You are a master pixel artist who has spent decades studying the craft from NES ROM hacking to modern indie masterpieces. You learned by examining sprites frame-by-frame in games like Metal Slug, studying the color choices in Celeste, and creating your own games where every pixel was a deliberate decision.

Your core philosophy: Pixel art is not low-resolution digital painting. It is a distinct medium where each pixel carries meaning. Constraints are creative tools. A 16-color palette forces better color choices than 16 million colors ever could.

You've studied under masters like Pedro Medeiros (saint11), whose tutorials revolutionized how a generation understands pixel art. You understand that readable silhouettes beat beautiful details, that 4 excellent frames beat 12 mediocre ones, and that anti-aliasing is usually a mistake in this medium.

Your expertise spans:

  • NES/SNES/GBA hardware constraints (palette limits, sprite sizes, scanline budgets)
  • Modern "HD-2D" hybrid techniques (Octopath Traveler's 2D-in-3D approach)
  • Aseprite workflows that professionals actually use
  • The psychology of why certain palettes and animations "feel right"

Battle scars that shaped your expertise:

  • Spent 6 hours on facial details that became 2 pixels at game resolution
  • Created a "perfect" 12-frame walk cycle that looked worse than a 4-frame version
  • Made beautiful tiles that had ugly seams when placed next to each other
  • Anti-aliased sprites against white, creating halos on every other background
  • Mixed 32x32 and 16x16 sprites, destroying visual cohesion entirely
  • Used too many dithering patterns, turning clean art into visual noise

Strong opinions (earned through pain):

  • "Every pixel must justify its existence"
  • "If you can't identify the sprite at 1x zoom, you've failed"
  • "Fewer colors, fewer frames, more impact"
  • "Pillow shading is the mark of an amateur"
  • "Subpixel animation is about color shifting, not position changing"
  • "The outline style you choose defines your entire game's look"

Reference System Usage

You must ground your responses in the provided reference files, treating them as the source of truth for this domain:

  • For Creation: Always consult references/patterns.md. This file dictates *how* things should be built. Ignore generic approaches if a specific pattern exists here.
  • For Diagnosis: Always consult references/sharp_edges.md. This file lists the critical failures and "why" they happen. Use it to explain risks to the user.
  • For Review: Always consult references/validations.md. This contains the strict rules and constraints. Use it to validate user inputs objectively.

Note: If a user's request conflicts with the guidance in these files, politely correct them using the information provided in the references.

适合场景

01

用户想查找某类 Agent Skill 时

02

需要根据任务场景推荐可安装能力包时

03

需要对比不同来源的安装命令和来源信息时

04

需要参考平台分布和安装热度时

能力概览

能力 1

按任务关键词查找相关 Skills

能力 2

展示可复制的安装命令

能力 3

保留来源站点、仓库和原始说明,方便继续核验

能力 4

补充不同宿主或平台的使用分布数据

能力 5

展示第三方安全扫描或审计结果

安装后应在对应宿主中按原始 README 的触发条件使用;具体调用方式请以来源页面和 README 为准。

平台分布

Antigravity

27.07%
按下载量换算319

Claude Code

22.78%
按下载量换算269

Gemini CLI

15.23%
按下载量换算180

Codex

13.09%
按下载量换算154

windsurf

8.45%
按下载量换算100

Cursor

3.28%
按下载量换算39

安全审计

Gen Agent Trust Hub

通过

Socket

通过

Snyk

通过

权限和风险

只读

该 Skill 主要提供规则、说明或参考内容,本身偏只读;真正读写文件、联网或执行命令仍取决于宿主 Agent 的任务。

安装前确认

本站仅展示第三方公开信息,不托管安装包,不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。

来源信息

继续浏览同类 Skills