ue57-viewport-capture
Capture UE viewport screenshots (color, depth, normal buffers) and build AI analysis context.
Skill by IvanYangYangXi
Chalk Labs
Need help deploying ue57-viewport-capture?
Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/ivanyangyangxi-ue57-viewport-capture
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: design
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
- Runs as
- Python package
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/ue57-viewport-capture
What's inside
- Skill name
ue57-viewport-capture- Description
- Capture UE viewport screenshots (color, depth, normal buffers) and build AI analysis context. Use when AI needs to: (1) take a screenshot of the current viewport, (2) capture depth/normal maps alongside color, (3) analyze scene composition/lighting/performance visually, (4) get viewport image + camera transform for scene analysis. NOT for: runtime game screenshots, cinematic rendering, Sequencer captures.
- License
- MIT
- Instructions
- 158 lines in SKILL.md · view on GitHub
Before installing
- Ships executable scripts
Agent Skills spec issues
- name: "ue57-viewport-capture" does not match folder "ue57_viewport_capture"
- body: contains an absolute path from the author's machine
Files (3)
- SKILL.md
- __init__.py
- manifest.json
SKILL.md (first lines)
# UE 视口截图与场景分析
截取 UE 编辑器视口画面(支持颜色/深度/法线等多 Buffer),收集相机变换和场景元数据,构建 AI 视觉分析上下文。
## 调用方式
通过 `run_ue_python` 执行 Python 代码。所有函数在 `__init__.py` 中定义。
---
## 核心概念
### Buffer 类型
| Buffer | 说明 | 格式 | 用途 |
|--------|------|------|------|
| `color` | 最终渲染画面 (LDR) | JPG | 默认,通用分析 |
| `base_color` | 基础颜色(无光照) | JPG | 材质/贴图分析 |
| `depth` | 场景深度 | PNG | 空间关系、遮挡分析 |
| `normal` | 世界法线 | PNG | 几何质量、表面朝向 |
| `hdr` | HDR 颜色 | EXR | 曝光/色调分析 |
### 分析模式
| Mode | 说明 |
|------|------|
| `general` | 综合分析(内容、构图、光照、颜色、优化) |
| `composition` | 构图分析(三分法、视觉焦点、空间层次) |
| `lighting` | 光照分析(光源、阴影、GI、色温) |
| `performance` | 性能分析(过度绘制、LOD、光源数量) |
| `color` | 色彩分析(色调、配色、后处理) |
| `custom` | 自定义分析(需提供 custom_prompt) |
### 分辨率策略
- **截图分辨率** (`quick_capture`): 1920×1080,保证画面质量
- **分析分辨率** (`quick_analyze`): 1024×576,节省 token(颜色 JPG ~49KB,三 buffer 合计 ~233KB base64)
- 颜色类 buffer 用 JPG 压缩(quality=85),深度/法线用 PNG 保持精度
---
## 操作示例
### 模块导入(每次使用前)
```python
import importlib, sys
skill_path = r"C:\Users\yangjili\.openclaw\workspace\skills\ue57_viewport_capture"
if skill_path not in sys.path:
sys.path.insert(0, skill_path)
if "ue57_viewport_capture" in sys.modules:
importlib.reload(sys.modules["ue57_viewport_capture"])
from ue57_viewport_capture import quick_capture, quick_analyze, capture_viewport_scenecapture, cleanup_captures
```
### 1. 快速截图(全分辨率)
```python
from ue57_viewport_capture import quick_capture
result = quick_capture() # 仅颜色
result = quick_capture(buffers=["color", "depth", "normal"]) # 多 buffer
print(result["images"]) # {"color": "D:/.../capture_xxx_color.jpg"}
print(result["camera"]) # {"location": {...}, "rotation": {...}}
```
### 2. AI 分析截图(小分辨率,省 token)
```python
from ue57_viewport_capture import quick_analyze
# 综合分析
context = quick_analyze(mode="general")
# 光照分析(含深度)
context = quick_analyze(mode="lighting", buffers=["color", "depth"])
# 性能分析(全 buffer)
context = quick_analyze(mode="performance", buffers=["color", "depth", "normal"])
# 自定义分析
context = quick_analyze(
mode="custom",
buffers=["color"],
custom_prompt="请分析这个场景是否适合作为恐怖游戏的关卡。"
)
```
### 3. AI 拿到 context 后的使用方式
`quick_analyze` 返回的 context 包含:
```python
context = {
"images_base64": {"color": "base64...", "depth": "base64...", ...},
"camera": {"location": {"x":..., "y":..., "z":...}, "rotation": {...}},
"scene_stats": {"total_actors": 128, "lights": [...], "by_class": {...}},
"analysis_prompt": "预构建的分析指引文本",
"mode": "general",
"resolution": [1024, 576],
}
```
AI 应将 `images_base64` 中的图片作为视觉输入,结合 `analysis_prompt` 和 `scene_stats` 进行分析。
### 4. 自定义分辨率截图
```python
from ue57_viewport_capture import capture_viewport_scenecapture
result = capture_viewport_scenecapture(
resolution=(2560, 1440),
buffers=["color", "normal"],
filename_prefix="my_scene",
)
```
### 5. 清理旧截图From IvanYangYangXi/artclaw_bridge, MIT.
More from IvanYangYangXi/artclaw_bridge
- 0.504score
comfyui-node-installer
IvanYangYangXi
ComfyUI 缺失自定义节点自动检测与安装。 Use when AI needs to: (1) install missing custom nodes for a workflow, (2) check if required nodes are available, (3) search and…
SkillDFreshness: D★ 36Claude Code +9 - 0.504score
ue5-world-interaction
IvanYangYangXi
UE5.6/UE5.7 world interaction systems for pickups, spawners, overlap/trace checks, and visual feedback.
SkillDFreshness: D★ 36Claude Code +9 - 0.504score
ue5-architecture
IvanYangYangXi
UE5.6/UE5.7 architecture planning and module boundary design for Unreal projects.
SkillDFreshness: D★ 36Claude Code +9 - 0.504score
ue5-auto-assistant
IvanYangYangXi
UE5.6/UE5.7 automatic assistant entry for beginners.
SkillDFreshness: D★ 36Claude Code +9 - 0.504score
ue5-cpp-gameplay
IvanYangYangXi
UE5.6/UE5.7 gameplay C++ implementation for Actors, Components, DataAssets, and gameplay logic.
SkillDFreshness: D★ 36Claude Code +9 - 0.504score
ue5-debug-validation
IvanYangYangXi
UE5.6/UE5.7 debugging and validation workflow for logs, asset checks, and regression triage.
SkillDFreshness: D★ 36Claude Code +9 - 0.504score
scene-vision-analyzer
IvanYangYangXi
Analyze game scene concept art / screenshots into structured JSON for 3D reconstruction.
SkillDFreshness: D★ 36Claude Code +9 - 0.504score
ue5-pcg-building
IvanYangYangXi
UE5.6/UE5.7 PCG building generation workflow for modular buildings, blockouts, facade rules, and runtime generation.
SkillDFreshness: D★ 36Claude Code +9 - 0.504score
ue5-performance-packaging
IvanYangYangXi
UE5.6/UE5.7 performance and packaging readiness workflow.
SkillDFreshness: D★ 36Claude Code +9 - 0.504score
ue5-save-load-replication
IvanYangYangXi
UE5.6/UE5.7 save/load and multiplayer replication workflow for gameplay systems.
SkillDFreshness: D★ 36Claude Code +9 - 0.504score
ue5-ui-umg-slate
IvanYangYangXi
UE5.6/UE5.7 UI development workflow using UMG and Slate integration.
SkillDFreshness: D★ 36Claude Code +9 - 0.504score
sd-operation-rules
IvanYangYangXi
Substance Designer 操作通用规则。所有 SD 图操作前必读。 Use when AI needs to: (1) perform any SD graph modification, (2) check post-operation best practices, (3) understand…
SkillDFreshness: D★ 36Claude Code +9
Signals
- Stars
- 36
- Forks
- 7
- Open issues
- 1
- Last commit (this folder)
- Apr 25, 2026 (6 months ago)
- Last release
- Apr 15, 2026 (6 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/IvanYangYangXi/artclaw_bridge
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from IvanYangYangXi
- 0.504score
ue5-architecture
IvanYangYangXi
UE5.6/UE5.7 architecture planning and module boundary design for Unreal projects.
SkillDFreshness: D★ 36Claude Code +9 - 0.504score
ue5-debug-validation
IvanYangYangXi
UE5.6/UE5.7 debugging and validation workflow for logs, asset checks, and regression triage.
SkillDFreshness: D★ 36Claude Code +9 - 0.504score
scene-vision-analyzer
IvanYangYangXi
Analyze game scene concept art / screenshots into structured JSON for 3D reconstruction.
SkillDFreshness: D★ 36Claude Code +9 - 0.504score
ue5-auto-assistant
IvanYangYangXi
UE5.6/UE5.7 automatic assistant entry for beginners.
SkillDFreshness: D★ 36Claude Code +9 - 0.504score
ue5-cpp-gameplay
IvanYangYangXi
UE5.6/UE5.7 gameplay C++ implementation for Actors, Components, DataAssets, and gameplay logic.
SkillDFreshness: D★ 36Claude Code +9 - 0.504score
ue5-pcg-building
IvanYangYangXi
UE5.6/UE5.7 PCG building generation workflow for modular buildings, blockouts, facade rules, and runtime generation.
SkillDFreshness: D★ 36Claude Code +9
Done for you
Rather not set it up yourself?
Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.
See how we build AI agents →Read the case studies
Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.
- launches shipped
- 50+
- launches shipped
- media placements
- 500+
- media placements
- founders on every account
- 2
- founders on every account
Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block
Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.
Get ue57-viewport-capture running in your business
Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.
Cite this page
ue57-viewport-capture skill. Agent Mart. https://agentmart.dev/skills/ivanyangyangxi-ue57-viewport-capture (last updated 2026-10-24)