Menu

Not in the top 1,000 by GitHub stars

compiler-segfault/sketch-parallax-skill

Sketch Parallax · 手绘视界 — 将人物、动物与物件图片制作成透明彩铅手绘分层 HTML，支持电脑端 3D 混合穿梭与逐页独立手稿。Turn images into interactive pencil-sketch 3D spaces, with shared fly-throughs and independent sketch pages.

Engineering

History

Review weekly changes to SKILL.md before updating. Dates mark the weeks in which we observed each version; checks apply to the recorded commits.

View weekly changes

skills/sketch-parallax/SKILL.md

Week of Nov 2, 2026 · +0 / −0 lines

Before Local scripts → After Local scripts

d57446a73c4c → d57446a73c4c

Compare on GitHub

Week of Oct 26, 2026 · Line counts unavailable

Before Not checked yet → After Local scripts

First observation → d57446a73c4c

No earlier version was observed for comparison.

Compare on GitHub

View on GitHubAdd to my skills

Verified commit d57446a73c4c57e385442e10778decffeab68f74

10GitHub stars
0stars in 7 days
1skill in this repository
0commits in 30 days

Heat

0.3
  • Star growth, last 7 daysNot available
  • Star growth, last 24 hoursNot available
  • Rank movement, last 7 daysNot available
  • Commits, last 30 daysNot available
  • Accounts asking about it through MCP, last 7 daysNot available
  • Hot votes this weekNot available

Heat never changes the order by stars, and sponsorship never touches it. How heat works

Stars over time

Oct 25, 2026Oct 25, 202610

30-day change not yet available: not enough history.

Individual skills in this repository

How it works

sketch-parallax

When your agent uses it

把人物、动物或物件图片制作成电脑浏览的透明手绘分层 HTML，支持共享 3D 穿梭空间和逐页独立 3D 手稿。用于彩铅、石墨笔触拆开并从正面重组的交互效果。

What it loads into context

Frontmatter

72 tokens

Always available to the agent

SKILL.md

1,376 tokens

When the skill is activated

Reference documents

1,526 tokens

Loaded on request

Token counts are estimates. Scripts run separately; they are not counted as reference context.

The playbook

  1. 先确认能力，不假定工具存在
  2. 模式语义
  3. 素材流程
  4. 构建
  5. 验收
  6. 精简交付

Scripts executed separately

  • assets/engine.js
  • scripts/build.py
  • scripts/cutout.py
  • scripts/doctor.py
  • scripts/unpack.py
  • scripts/verify.py

Files

  • SKILL.mdcore5,150 bytes
  • SKILL.mdcore5,150 bytes
  • SKILL.mdcore5,150 bytes
  • agents/openai.yamlasset308 bytes
  • assets/engine.jsruns13,642 bytes
  • assets/style.cssasset8,089 bytes
  • assets/template.htmlasset3,000 bytes
  • references/artwork.mddoc1,697 bytes
  • references/capabilities.mddoc2,761 bytes
  • references/manifest.mddoc1,253 bytes
  • requirements-cutout.txtdoc42 bytes
  • requirements-test.txtdoc40 bytes
  • requirements.txtdoc15 bytes
  • scripts/build.pyruns4,541 bytes
  • scripts/cutout.pyruns5,026 bytes
  • scripts/doctor.pyruns675 bytes
  • scripts/unpack.pyruns1,694 bytes
  • scripts/verify.pyruns3,593 bytes
Read SKILL.md

# Sketch Parallax · 手绘视界

目标是电脑端交互 HTML，不默认做手机版、MP4 或真实身体建模。支持 1–8 个主体。每个主体先有可靠透明素材，再做可选手绘转换，最后用随包模板产生两种空间效果。

## 先确认能力，不假定工具存在

读取 [references/capabilities.md](references/capabilities.md)，运行 `python scripts/doctor.py`。确认可用的 Python、图像编辑工具和浏览器。

- 必需：Python + Pillow；可执行本地脚本；支持 WebGL2 的电脑浏览器。
- 抠图：已有透明图或用户蒙版不需要模型；不透明图可选本地 rembg。模型另下载，不在 skill 包里。动漫优先试 isnet-anime，照片/动物试 isnet-general-use，结果必须看图验收。
- 当前彩铅效果：需要图像编辑/生成工具，或用户直接提供透明手绘稿。没有编辑能力时可用透明原图展示空间分层，但要说明未做手绘转换，不能把普通滤镜宣称为同等效果。
- **不需要 AI 单目深度模型。** 模板生成 14 层局部笔触和轻微曲面深度，这属于人工设计的艺术空间；不是从图中恢复真实身体。用户要求真实深度、肢体运动或侧背面时，本模板不足，要说明并另选技术。
- 验证可选依赖：Playwright + Chromium。没有浏览器自动化时仍可构建，手动检查页面，并明确未自动验证。
- 音乐可选。没有授权音频就不放音乐，不从参考视频抽取音轨，不需要语音/音乐 API。
View the complete source on GitHub

Skills included

  • sketch-parallax

Repository facts

License
MIT
Created
Oct 3, 2026
Last pushed
Oct 5, 2026
Forks
2
Open issues
0
Project activity
Active

Before you install

Local scripts

Automated signals, not a guarantee

Checked Nov 6, 2026

Not fully analyzed: some files were too long, unreadable or missing. This never lowers the level.

Show 3 notes
  • skills/sketch-parallax/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
  • skills/sketch-parallax/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
  • skills/sketch-parallax/assets/style.css:1 Analysis incomplete: physical or joined line exceeds character limit
Show all 9 signals by file

skills/sketch-parallax/assets/engine.js

  • Executable scriptline 1
    Executable file

skills/sketch-parallax/assets/style.css

  • Network accessline 3
    :root{color-scheme:light;--bg:#eae4d6;--panel:#f1ecdf;--ink:#3c342b;--muted:#786e61;--accent:#bd713e}body{background:#eae4d6;color:#3c342b}.rail{background:#e4ddcd;border-color:#776a4b15}.brand{color:#3b3229}.brand-mark{color:#a36c41}.rail-

skills/sketch-parallax/scripts/build.py

  • Executable scriptline 1
    #!/usr/bin/env python3

skills/sketch-parallax/scripts/cutout.py

  • Executable scriptline 1
    #!/usr/bin/env python3

skills/sketch-parallax/scripts/doctor.py

  • Executable scriptline 1
    #!/usr/bin/env python3

skills/sketch-parallax/scripts/unpack.py

  • Executable scriptline 1
    #!/usr/bin/env python3
  • Possible obfuscationline 14
    (out/filename).write_bytes(base64.b64decode(body,validate=True));item={k:v for k,v in c.items() if k not in ('image','width','height')};item['image']=filename;data.append(item)
  • Possible obfuscationline 19
    (out/'music.mp3').write_bytes(base64.b64decode(body,validate=True));spec['audio']='music.mp3'

skills/sketch-parallax/scripts/verify.py

  • Executable scriptline 1
    #!/usr/bin/env python3

How the signals fit together

Facts from a static read of the files at the pinned commit. They describe what the code does, not why.

Some files could not be read; the facts below still hold.

Signal confidence: 8 facts

Works with

Agent compatibility, from the files in this repository
AgentStatusEvidenceInstall to
Claude CodeCompatibleStandard SKILL.md skills/sketch-parallax/SKILL.md.claude/skills/<skill-name>/
CodexCompatibleStandard SKILL.md skills/sketch-parallax/SKILL.md.agents/skills/<skill-name>/
CursorCompatibleStandard SKILL.md skills/sketch-parallax/SKILL.md.cursor/skills/<skill-name>/
Gemini CLICompatibleStandard SKILL.md skills/sketch-parallax/SKILL.md.gemini/skills/<skill-name>/
GitHub CopilotCompatibleStandard SKILL.md skills/sketch-parallax/SKILL.md.github/skills/<skill-name>/
OpenCodeCompatibleStandard SKILL.md skills/sketch-parallax/SKILL.md.opencode/skills/<skill-name>/
  • Native The repository ships a manifest, folder or frontmatter field for this agent.
  • Compatible A standard SKILL.md that this agent can read.
  • Unknown No evidence either way.

Derived automatically from paths, manifests and frontmatter. Not tested on each agent.

You might also use

Kayforkind/reimagine-it

Kayforkind Content-Derived Design CLI. HTML in, standalone HTML out from the source's own nouns, dates, numbers, and colors. Not the reimagineit.ai interview SaaS.

212GitHub stars

JamesonZGJ/layered-holo-card-skill

Turn a photo into a layered 2.5D holographic card with original-color subjects, safe parallax, dynamic shadows and a portable Agent workflow.

10GitHub stars

QingYunA/answer-me-with-html

Turns an answer into a one-page visual HTML explainer: the model writes a short Markdown draft and the bundled CLI builds one page. Use it proactively and liberally in replies to …

6kGitHub stars

oil-oil/oil-motion

把 AI 生成或已有的视频、序列帧变成随滚动、指针、拖动、触摸、设备方向、音频、数据或状态变化的网页动画：设计动作方向，生成关键帧与视频，整理成图集或视频，编译时间轴并接入运行时。用…

2.8kGitHub stars

DenisSergeevitch/agents-best-practices

Use this skill when designing, generating an MVP blueprint for, auditing, troubleshooting, refactoring, or explaining an agentic harness for any domain. Covers provider-neutral ag…

2.4kGitHub stars

HRuiCcc/RuiC-card-skill

全息闪卡通用 Agent Skill，不挑宿主、多模态模型都能用：一句话生成可拖转、会流光、带层次景深的 3D 闪卡网页，附可编辑 Blender 工程 · A host-agnostic Agent Skill: turn one sentence in…

644GitHub stars