TypingMindTypingMindThe best frontend for AI
Uloop Screenshot logo

Uloop Screenshot

Community
hatayama
uloop-screenshot

Capture Unity Editor windows or Game View rendering as PNG. Use for visual checks, debugging, documentation, or annotated UI element coordinates.

Overview

Publisherhatayama
Repositoryunity-cli-loop
Skill nameuloop-screenshot
Stars
578
Forks
49
Bundled files
1
LicenseMIT
Links
Skill sourceRepository
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 1 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by hatayama on GitHub. Read the source before you install it.

Installation

Install the Uloop Screenshot AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/hatayama/unity-cli-loop/tree/main/.agents/skills/uloop-screenshot
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/hatayama/unity-cli-loop.git /tmp/unity-cli-loop
mkdir -p .claude/skills
cp -r /tmp/unity-cli-loop/.agents/skills/uloop-screenshot .claude/skills/uloop-screenshot
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Uloop Screenshot in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Uloop Screenshot on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Uloop Screenshot is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

uloop screenshot

Take a screenshot of any Unity EditorWindow by name and save as PNG.

Usage

bash
uloop screenshot [--window-name <name>] [--resolution-scale <scale>] [--match-mode <mode>] [--capture-mode <mode>] [--annotate-elements] [--annotate-raycast-grid] [--raycast-layer-mask <layers>] [--elements-only] [--output-directory <path>]

Parameters

ParameterTypeDefaultDescription
--window-namestringGameWindow name to capture (for example Game, Scene, Console, Inspector). Ignored when the resolved capture mode is rendering (auto during Play Mode resolves to rendering). When the Game tab is Device Simulator and the title is Simulator, default Game falls back to Simulator.
--resolution-scalenumber1.0Resolution scale (0.1 to 1.0)
--match-modeenumexactWindow name matching mode: exact, prefix, or contains. Ignored when the resolved capture mode is rendering (auto during Play Mode resolves to rendering).
--capture-modeenumautoauto - rendering in PlayMode and window otherwise, window - capture EditorWindow including toolbar, rendering - capture game rendering only (PlayMode required), GameView - alias for rendering. Rendering screenshots return ScreenshotToInputFormula for converting raw image pixels before calling simulate-mouse-input (including --dry-run) or simulate-mouse-ui.
--output-directorystring""Output directory path for saving screenshots. When empty, uses default path (.uloop/outputs/Screenshots/). Accepts absolute paths.
--annotate-elementsflag-Annotate interactive UI elements with index labels and interaction hints (A / CLICK, B / DRAG, ...). The response includes an AnnotatedElements array with element metadata sorted by SortingOrder then SiblingIndex (an approximation of z-order, not the guaranteed draw order). Only works when the resolved capture mode is rendering (auto during Play Mode resolves to rendering) in PlayMode.
--annotate-raycast-gridflag-Annotate clustered 3D physics collider candidates as PhysicsCollider entries in AnnotatedElements. Uses Camera.main visibility and the same top-left Game View coordinates as simulate-mouse-input. Only works when the resolved capture mode is rendering (auto during Play Mode resolves to rendering) in PlayMode.
--raycast-layer-maskstring""Comma-separated physics layer names to narrow which layers --annotate-raycast-grid clusters. Hits are limited to layers also visible to Camera.main.cullingMask. When omitted, clusters against Physics.DefaultRaycastLayers.
--elements-onlyflag-Return only annotated element JSON without capturing a screenshot image. Requires --annotate-elements or --annotate-raycast-grid, and the resolved capture mode to be rendering (auto during Play Mode resolves to rendering) in PlayMode.

Match Modes

ModeDescriptionExample
exactWindow name must match exactly (case-insensitive)"Project" matches "Project" only
prefixWindow name must start with the input"Project" matches "Project" and "Project Settings"
containsWindow name must contain the input anywhere"set" matches "Project Settings"

Window Name

The window name is the text displayed in the window's title bar (tab). Common names: Game, Simulator, Scene, Console, Inspector, Project, Hierarchy, Animation, Animator, Profiler. Custom EditorWindow titles are also supported.

Device Simulator

  • Prefer --capture-mode rendering for the annotate → click flow. It works with both the normal Game view and Device Simulator, and coordinates match simulate-mouse-ui / simulate-mouse-input (including --dry-run).
  • --capture-mode window captures Editor chrome (toolbar/borders). With Device Simulator as the play view, default --window-name Game falls back to Simulator when no Game tab exists; you can also pass --window-name Simulator.
  • Simulator Fit to Screen / Scale / Safe Area overlays are chrome-only and do not change rendering-mode input coordinates. After device rotation, re-run annotate before clicking: rotation changes the Game View size, so every earlier AnnotatedElements entry (bounds, SimX/SimY, probe and occlusion results) is stale.

Output

Returns JSON with:

  • ScreenshotCount: Number of windows captured
  • ResolvedCaptureMode: "window" or "rendering" — the mode actually used after resolving auto
  • Warning: Appears for window captures taken while Play Mode is running with at least one image, and for any image captured while Play Mode is paused (UGUI/canvas content may show the frame rendered before the pause; run uloop control-play-mode --action Step once and capture again to refresh it).
  • Screenshots: Array of screenshot info, each containing:
    • ImagePath: Absolute path to the saved PNG file. Empty ("") when --elements-only is used because no image file is written; FileSizeBytes, Width, and Height are then 0, while GameViewWidth/GameViewHeight and AnnotatedElements still carry real values. When it is non-empty, always open the file named here — the output directory accumulates every past capture, so guessing the newest file with directory listing (ls -t or similar) can silently pick a stale screenshot from an earlier run.
    • FileSizeBytes: Size of the saved file in bytes
    • Width: Captured image width in pixels
    • Height: Captured image height in pixels
    • ImageCoordinateSystem: "top-left-game-view" or "top-left-window"
    • ResolutionScale: Resolution scale used for capture
    • ImageToInputOffsetY: Y offset used for top-left-game-view coordinate conversion
    • GameViewWidth, GameViewHeight: Game View size in input coordinates at capture time — the basis for SimX/SimY and for the Y flip inside simulate-mouse-input. Populated for rendering captures, including --elements-only
    • ScreenshotToInputFormula: Formula converting raw image pixels to simulate-mouse input coordinates
    • AnnotatedElements: Array of annotated UI element metadata. Empty unless --annotate-elements or --annotate-raycast-grid is used.
    • RaycastLayerSummaries / RaycastLayerNamesChecked: Physics-layer diagnostics populated when --annotate-raycast-grid is used.

For AnnotatedElements / RaycastLayerSummaries fields and gameView coordinate conversion, read references/annotated-elements.md before using screenshot coordinates with mouse simulation tools.

When multiple windows match (e.g., multiple Inspector windows or when using contains mode), all matching windows are captured with numbered filenames (e.g., Inspector_1_*.png, Inspector_2_*.png).

Notes

  • Use uloop focus-window first if needed
  • Target window must be open in Unity Editor
  • Window name matching is always case-insensitive

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Uloop Screenshot AI skill do?

Capture Unity Editor windows or Game View rendering as PNG. Use for visual checks, debugging, documentation, or annotated UI element coordinates.

Why use Uloop Screenshot on TypingMind?

Because you install it once and use it with any model. Uloop Screenshot is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Uloop Screenshot in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/hatayama/unity-cli-loop/tree/main/.agents/skills/uloop-screenshot. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Uloop Screenshot?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Uloop Screenshot?

As many as you like. As long as a model supports skills, you can use Uloop Screenshot with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Uloop Screenshot AI skill free?

Yes. It is published on GitHub by hatayama under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

Related AI Skills

View all
openclaw logo

Release Openclaw Maintainer

openclaw
OrganizationPopular

Prepare, publish, recover, or verify OpenClaw beta, stable, and extended-stable releases, including approved backports.

82.2K
391K
11 files
View
openclaw logo

Release Openclaw Plugin Testing

openclaw
OrganizationPopular

Plan and run pre-release OpenClaw plugin validation across bundled plugins, package artifacts, lifecycle commands, doctor/fix, config round-trip, gateway startup, SDK compatibility, Docker E2E,…

82.2K
391K
1 files
View
openclaw logo

Solid

openclaw
OrganizationPopular

Write, port, review, or test Solid 2 UI in OpenClaw (Control UI, plugin views, Canvas hosts), including state ownership, Lit interop during the migration, native overlays, testing, performance, and…

82.4K
391.7K
9 files
View
openclaw logo

Auto Qa

openclaw
OrganizationPopular

Run OpenClaw-wide autonomous QA and live/stress campaigns across independent subsystem lanes, with verified fixes and a resumable evidence report.

82.2K
391K
5 files
View

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇