Godot Agent Vision logo

Godot Agent Vision

Community
thedivergentai
godot-agent-vision

Agentic eyes for Godot work: cross-platform screenshot CLI (asset/region/window/screen) to budgeted WebP, TEMP editor viewport bridge under .gdskills/, and Taste Receptor Atlas v2 (~237 micro-receptors × 0–2: hierarchy, contrast, typography×41, affordance, space, color, icon, composition, light/FX, motion-tells, anti-slop, originality, identity). Use when agents must see UI, assets, or the editor — not for in-game screenshot Autoloads. Keywords: agent vision, screenshot, WebP, visual QA, taste receptors, typography, UI review, asset sheet, editor viewport, anti-slop.

Overview

Publisherthedivergentai
RepositoryGD-Agentic-Skills
Skill namegodot-agent-vision
Stars
727
Forks
43
Bundled files
24
LicenseLGPL-3.0
Links
  • 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.

  • 24 bundled files

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

  • Open source

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

Installation

Install the Godot Agent Vision 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.
  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/thedivergentai/GD-Agentic-Skills.git /tmp/GD-Agentic-Skills
mkdir -p .claude/skills
cp -r /tmp/GD-Agentic-Skills/skills/godot-agent-vision .claude/skills/godot-agent-vision
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Godot Agent Vision 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 Godot Agent Vision 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 Godot Agent Vision 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.

Godot Agent Vision

Host-side eyes for coding agents building Godot projects: capture → budgeted WebP → scored visual review. Not a game Autoload, not an exportable screenshot API.

Do NOT Load every reference for one task. Load the MANDATORY file for the active mode, then only the rubric axes you are scoring.

NEVER Do

  • NEVER ship the editor bridge as an Autoload or leave addons/_gdskills_agent_vision/ committed — stage, capture, teardown.
  • NEVER leave --keep-bridge on after debugging — skips teardown and dirties the consumer project.
  • NEVER dump uncompressed PNG walls into model context — WebP only; default short-edge 512; --detail only when pixels fail (especially type).
  • NEVER replace scored taste with binary PASS/FAIL or vibes — score applicable rows in taste-receptors.md (Atlas v2, 237 receptors × 0–2); V1–V8 /120 in vision-review-rubric.md is rollup only.
  • NEVER invent taste without loading Family deep refs when those pixels are present: TYPE → typography-sight.md; HIER/CTRST → hier-contrast-receptors.md; SPACE/AFF → space-affordance-receptors.md; COLOR/ICON → color-icon-receptors.md; COMP/LIGHT/MOT → composition-fx-receptors.md; plus anti-slop-sight.md / ui-taste-sight.md.
  • NEVER treat purple-gradient / glow-card / cream-serif AI defaults as “good UI” unless the capture owns that identity with legible critical info and type discipline (SLOP-STACK / TYPE-DISPLAY-HUD-SPLIT).
  • NEVER put ornate display faces on ammo/HP/timersTYPE-DISPLAY-HUD-SPLIT ship blocker; data type is boring on purpose.
  • NEVER promise silent window-by-title on Wayland — region, grim, X11, or editor bridge.
  • NEVER trust black fullscreen BitBlt/mss frames — exclusive fullscreen / some GPU paths return empty; windowed, region, DXGI-only if justified, or editor bridge.
  • NEVER commit .gdskills/vision/** — ensure .gdskills/ is gitignored first.

When to use

NeedModeMANDATORY loads
Asset files / sheetsassetcapture-modes.md, webp-budgets.md, rubric V6–V8 + originality-sight.md
Desktop rectangleregioncapture-modes + budgets + rubric axes in frame
Godot/editor/game windowwindow --titlecapture-modes (OS limits!)
Full monitorscreenlast resort (secret chrome)
Editor 2D/3D pixelseditoreditor-bridge-lifecycle.md

After capture: Read WebP(s) → score Taste Receptor Atlas (not vibes) → zero-list + ordered fixes keyed to receptor IDs. If any TYPE-* / micro-seam ≤1 for illegibility at 512 short-edge, re-capture --detail or text crop before locking.

Setup (agent host)

text
pip install -r skills/godot-agent-vision/requirements-vision.txt
# optional macOS window titles:
# pip install pyobjc-framework-Quartz

Requires a display session. Use repo/project venv Python.

Available Scripts

Do NOT Load every script. Call only what the mode needs.

capture.py

Main CLI: doctor, list-windows, screen, region, window, asset, editor. Prints wrote=, bytes=, budget=short-edge:N|long-edge:N.

webp_encode.py

Default fit short-edge 512; --detail / --max-edge switches to long-edge cap (1568). Never upscales. Soft re-encode if >1MB.

asset_sheet.py

Single asset or ≤2×2 contact sheet with labels; res:// resolution against --project-root.

ensure_gitignore.py

Appends .gdskills/ so vision scratch never stages.

stage_editor_bridge.py

Stages TEMP addon, optional --godot launch, handshake wait, WebP encode, teardown + project.godot plugin strip.

Editor bridge templates

Capture CLI (golden path)

text
python skills/godot-agent-vision/scripts/capture.py doctor
python skills/godot-agent-vision/scripts/capture.py window --project-root . --title Godot
python skills/godot-agent-vision/scripts/capture.py asset --project-root . --paths res://ui/icons --sheet
python skills/godot-agent-vision/scripts/capture.py editor --project-root . --editor-mode 3d --godot "%GODOT_PATH%"
# typography / OCR / dense layout only:
python skills/godot-agent-vision/scripts/capture.py window --project-root . --title Godot --detail

Default out: {project}/.gdskills/vision/YYYYMMDD-HHMMSS-<mode>[-label].webp

MANDATORY platform landmines: capture-modes.md. MANDATORY budgets: webp-budgets.md.

Editor bridge (TEMP)

Stages templates → addons/_gdskills_agent_vision/.gdskills/vision/{request,raw,done} → WebP → delete addon + restore enabled=.

MANDATORY: editor-bridge-lifecycle.md. Prefer EditorPlugin over EditorScript (await across RefCounted is unsafe).

Structured review (Taste Receptor Atlas → optional /120)

MANDATORY primary: taste-receptors.md237 micro-receptors across 13 families (HIER, CTRST, TYPE×41, AFF, SPACE, COLOR, ICON, COMP, LIGHT, MOT, SLOP, ORIG, ID), each 0/1/2, grade by % of applicable, hard gates. Routing + V-rollup: vision-review-rubric.md.

When scoring…Load
Any reviewMANDATORY taste-receptors.md
TYPE-* / HUD numerals / menusMANDATORY typography-sight.md
HIER-* / CTRST-*hier-contrast-receptors.md
SPACE-* / AFF-*space-affordance-receptors.md
COLOR-* / ICON-*color-icon-receptors.md
COMP-* / LIGHT-* / MOT-*composition-fx-receptors.md
SLOP-* / UI cross-checkanti-slop-sight.md, ui-taste-sight.md
ORIG-*originality-sight.md
ID-*identity-sight.md

Expert Knowledge Delta

Capture / OS

  • Windows: Per-Monitor DPI V2 before geometry; mss before DPI-clobbering imports; monitors[0] virtual union can be negative-origin; longest title match for Godot’s path-in-title windows.
  • Windows black frames: minimized / exclusive fullscreen / GPU-protected content — not “empty UI.” Prefer windowed + region or editor bridge; DXGI is optional weight, not default.
  • macOS: Screen Recording attaches to responsible binary; wallpaper-only = hard fail; screencapture CLI attribution breaks under agents — prefer in-process Quartz/mss.
  • macOS Retina: pick logical points (automation) vs backing pixels (OCR) and do not mix without scale metadata.
  • Linux: Wayland → skip mss; grim on wlroots; no silent title grab; portal paths are interactive.
  • Asset res:// resolves against --project-root; missing paths must error loudly — never invent files.

WebP / context

  • Vision tokens track pixel area; request size tracks codec. Default short-edge 512 for identity/overview/anti-slop; escalate long-edge 1568 only for glyphs, seams, dense full-layout.
  • Contact sheets ≤2×2 with gutters — 3×3+ makes panel text sub-pixel after model downscale.
  • Never upscale tiny icons to fill 512/1568 — wastes tokens without information.

Editor bridge

  • EditorPlugin (Node) can await RenderingServer.frame_post_draw safely; EditorScript is RefCounted and can free mid-await.
  • Capture: EditorInterface.get_editor_viewport_2d/3dget_texture().get_image() after ≥1–2 frame waits; set main screen 2D/3D first or texture is stale/empty.
  • Empty get_image() ⇒ missing await or wrong main screen — not proof the GPU is fine.
  • Handshake: write PNG under raw/, then done flag; Python waits for size-stable PNG.
  • Teardown must strip res://addons/_gdskills_agent_vision/plugin.cfg from [editor_plugins] enabled= and delete the addon — underscore name signals private/temp.
  • Control crops: full editor image + get_global_rectImage.get_region, clamped to bounds.

Sight / taste (why the atlas is heavy)

  • Score receptors, not vibes: hierarchy is composite size×contrast×motion×sat (HIER-WEIGHT-MATH); peripheral HUD must read as shape (HIER-PERIPH-READ); contrast is worst-case on plates (CTRST-GRAD-WORST, CTRST-BODY-45).
  • Agents default to AI UI centroids (purple wash, neon glow cards, cream+serif, Lucide soup). T≥3 without ownership ⇒ SLOP-STACK=0 / overall F.
  • Typography is ship-blocking (41 TYPE receptors): TYPE-DISPLAY-HUD-SPLIT, TYPE-OPSZ-MATCH, TYPE-NUM-TABULAR/TIMER-STABLE, TYPE-GLYPH-INTEGRITY, TYPE-FACE-CAP — display cuts at HUD size and tabular wobble are zeroes, not “style.”
  • Color/icon: 4–6 semantic roles + accent budget ~5–15%; silhouette test on icon sets; CVD shape backup (COLOR-ONLY / ICON-SIL).
  • Composition/FX/motion: power-point vs HUD conflict (COMP-POWER-CONFLICT); bloom/particles must not replace hierarchy or occlude UI; freeze-frames leak shake/tween artifacts (MOT-*) — sequence capture when peak ambiguous.
  • Originality: filter scènes à faire first; fail franchise silhouette/mark matches and stacked construction tells.
  • Identity: palette roles + edge grammar + motif recurrence (2–4) + type pairing + icon grid + HUD↔menu↔key-art DNA — gradient-alone is not a brand.

Decision tree

  1. Files on disk? → asset (± sheet) → Read → score COLOR/ICON/ORIG/ID/SLOP (+ TYPE if labels) → fixes.
  2. Known window? → window (else region) → Read → score all applicable atlas families → fixes.
  3. Editor viewport fidelity? → editor → teardown → score → fixes.
  4. Else screen (last resort).
  5. TYPE/CTRST illegible at 512? → --detail or text crop → re-score those receptors.
  6. MOT/hit-peak ambiguous? → 2–8 frame sequence → re-score MOT/LIGHT hit receptors.

Reference

Progressive disclosure: open Official Documentation only for a specific API; load Related Skills when routing to a peer domain — do not preload the whole lattice.

Official Documentation

Related Skills

Prerequisites
Complements
Downstream / consumers
  • Genre and UI skills that ship screens — route here when agents must see results, not guess.
Master
  • godot-master — Decision matrix row Agent Eyes / Visual QA.

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 Godot Agent Vision AI skill do?

Agentic eyes for Godot work: cross-platform screenshot CLI (asset/region/window/screen) to budgeted WebP, TEMP editor viewport bridge under .gdskills/, and Taste Receptor Atlas v2 (~237 micro-receptors × 0–2: hierarchy, contrast, typography×41, affordance, space, color, icon, composition, light/FX, motion-tells, anti-slop, originality, identity). Use when agents must see UI, assets, or the editor — not for in-game screenshot Autoloads. Keywords: agent vision, screenshot, WebP, visual QA, taste receptors, typography, UI review, asset sheet, editor viewport, anti-slop.

Why use Godot Agent Vision on TypingMind?

Because you install it once and use it with any model. Godot Agent Vision 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 Godot Agent Vision in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/thedivergentai/GD-Agentic-Skills/tree/main/skills/godot-agent-vision. 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 Godot Agent Vision?

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 Godot Agent Vision?

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

Is the Godot Agent Vision AI skill free?

Yes. It is published on GitHub by thedivergentai under the LGPL-3.0 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.

View all

Set up your own AI workspace now

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