Image to Three.js Model
img2threejs/img2threejs
Rebuilds the object in a reference image as a procedural, animation-ready Three.js model written entirely in code, using staged sculpting with quality checks.
Hot reload applies method-body edits and can add new methods and fields (added members are visible to edited code in the same reload within the same assembly); it can also change signatures: a…
$ npx skills add CyberAgentGameEntertainment/NovaShader --skill uloop-hot-reload -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install CyberAgentGameEntertainment/NovaShader uloop-hot-reload --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/CyberAgentGameEntertainment/NovaShader.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/uloop-hot-reload .claude/skills/uloop-hot-reload && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "uloop-hot-reload" agent skill from https://github.com/CyberAgentGameEntertainment/NovaShader/tree/main/.claude/skills/uloop-hot-reload into .claude/skills/uloop-hot-reload/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "uloop-hot-reload", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/CyberAgentGameEntertainment/NovaShader/tree/main/.claude/skills/uloop-hot-reloadType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add CyberAgentGameEntertainment/NovaShader --skill uloop-hot-reload -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install CyberAgentGameEntertainment/NovaShader uloop-hot-reload --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/CyberAgentGameEntertainment/NovaShader.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.claude/skills/uloop-hot-reload .agents/skills/uloop-hot-reload && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "uloop-hot-reload" agent skill from https://github.com/CyberAgentGameEntertainment/NovaShader/tree/main/.claude/skills/uloop-hot-reload into .agents/skills/uloop-hot-reload/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "uloop-hot-reload", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add CyberAgentGameEntertainment/NovaShader --skill uloop-hot-reload -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install CyberAgentGameEntertainment/NovaShader uloop-hot-reload --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/CyberAgentGameEntertainment/NovaShader.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.claude/skills/uloop-hot-reload .cursor/skills/uloop-hot-reload && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "uloop-hot-reload" agent skill from https://github.com/CyberAgentGameEntertainment/NovaShader/tree/main/.claude/skills/uloop-hot-reload into .cursor/skills/uloop-hot-reload/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "uloop-hot-reload", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/CyberAgentGameEntertainment/NovaShader.git --path .claude/skills/uloop-hot-reload--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add CyberAgentGameEntertainment/NovaShader --skill uloop-hot-reload -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install CyberAgentGameEntertainment/NovaShader uloop-hot-reload --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/CyberAgentGameEntertainment/NovaShader.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.claude/skills/uloop-hot-reload .gemini/skills/uloop-hot-reload && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "uloop-hot-reload" agent skill from https://github.com/CyberAgentGameEntertainment/NovaShader/tree/main/.claude/skills/uloop-hot-reload into .gemini/skills/uloop-hot-reload/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "uloop-hot-reload", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install CyberAgentGameEntertainment/NovaShader uloop-hot-reloadInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add CyberAgentGameEntertainment/NovaShader --skill uloop-hot-reload -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/CyberAgentGameEntertainment/NovaShader.git skills-src && mkdir -p .github/skills && cp -r skills-src/.claude/skills/uloop-hot-reload .github/skills/uloop-hot-reload && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "uloop-hot-reload" agent skill from https://github.com/CyberAgentGameEntertainment/NovaShader/tree/main/.claude/skills/uloop-hot-reload into .github/skills/uloop-hot-reload/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "uloop-hot-reload", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add CyberAgentGameEntertainment/NovaShader --skill uloop-hot-reload -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install CyberAgentGameEntertainment/NovaShader uloop-hot-reload --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/CyberAgentGameEntertainment/NovaShader.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.claude/skills/uloop-hot-reload .opencode/skills/uloop-hot-reload && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "uloop-hot-reload" agent skill from https://github.com/CyberAgentGameEntertainment/NovaShader/tree/main/.claude/skills/uloop-hot-reload into .opencode/skills/uloop-hot-reload/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "uloop-hot-reload", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
uloop-hot-reloadHot reload applies method-body edits and can add new methods and fields (added members are visible to edited code in the same reload within the same assembly); it can also change signatures: a…
Uloop Hot Reload is an agent skill from CyberAgentGameEntertainment/NovaShader. Hot reload applies method-body edits and can add new methods and fields (added members are visible to edited code in the same reload within the same assembly); it can also change signatures: a return-type change applies only when the same reload (or an earlier one) covers the old signature's compiled callers, while a rename or parameter change applies as an added method and warns about compiled callers it leaves on the old signature. New types, or members referenced from other assemblies or from files that are…
Its SKILL.md is about 2k tokens, which your agent loads only when the skill is triggered. The skill folder holds 6 other files, including reference files (for example `references/mechanism-and-lifecycle.md`, `references/output.md` and `references/pause-point-interaction.md`).
It sits in Game Development. The repository describes itself as: Multi-functional shader for the Particle System that supports Universal Render Pipeline (URP) of Unity. The licence is MIT.
Read from SKILL.md and the folder at commit 7f0a400. It shows what the files ask for, not the result of running them.
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
No scripts in the folder and no shell commands in SKILL.md (its code samples are bash).
From the folder's file list and the shell code blocks in SKILL.md.
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Uloop Hot Reload loads about 2k tokens when it runs, and up to ~12k if it reads all its reference files. Until then it costs about 153 tokens; SKILL.md has 996 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
The full file from CyberAgentGameEntertainment/NovaShader at commit 7f0a400, republished under its MIT licence (© CyberAgentGameEntertainment). 996 words, ~1,968 tokens.
.claude/skills/uloop-hot-reload/SKILL.md (or your agent's skills folder). This skill also uses 5 other files; get the full folder from GitHub.Replaces method bodies in the running Editor (EditMode or PlayMode) directly from edited
project source files — no domain reload, no attributes, no source markers. Private/internal
member access, static methods, return values, async methods, and iterators all work within
the limits below — including private access inside async, iterator, lambda, local-function,
and LINQ-query bodies. Methods that cannot be patched are reported per method as Skipped
or Failed; one unpatchable method never aborts the rest of the run.
uloop hot-reload --files Assets/Scripts/Enemy.cs
uloop hot-reload --files Assets/Scripts/Enemy.cs,Assets/Scripts/Boss.cs
uloop hot-reload
uloop hot-reload --revert-allMultiple files are passed as one comma-separated value (or a JSON array); array options consume exactly one value token.
A brand-new script — or any script under a brand-new .asmdef — cannot be hot-reloaded
before its first import: Unity has not compiled it into any assembly yet. Run
uloop compile once to import new files, then iterate on them with hot reload.
| Parameter | Type | Default | Description |
|---|---|---|---|
--files | array | - | Project-relative .cs paths whose method bodies should be hot-reloaded. When omitted or empty on apply, selects the .cs sources whose bytes changed since the last compile snapshot, capped at 50 changed files per assembly with a warning when the cap trims the list; run uloop compile first when no snapshot exists, or pass explicit paths when no changed source is found |
--revert-all | flag | - | Remove every active hot-reload patch and clear the patch ledger. When set, --files is ignored |
--status | flag | - | Lists the currently active changes (patched methods and added members) without applying or reverting anything. |
When --files is omitted or empty, a source is selected only when its compilation assembly has a
snapshot directory and that source has its own snapshot file. A missing per-file snapshot is
left out rather than guessed as changed, so pass the file explicitly or run uloop compile
to establish a complete baseline.
uloop hot-reload --status lists the currently active changes without applying or
reverting anything; it cannot be combined with --files or --revert-all. Patches are
static Editor state, so after a domain reload it authoritatively reports zero. Each
Active row's InvocationCount counts calls into the patched body since the patch was
applied — read it as a reachability signal only while the code is actually being driven;
interpretation rules are in references/troubleshooting.md.
The edited files are grouped by the compiled assembly they belong to. Per group, every
editable method body is rewritten into a static shim by an out-of-process Roslyn worker
(private/internal access becomes accessor delegates where needed), the shims of the whole
group compile into one shim assembly against publicized reference copies and load into the
Editor domain, and each original method is patched with a Harmony transpiler (ID
io.github.hatayama.uloop.hot-reload). Because a group shares one shim assembly, a body
edited in one file can call a method or field added in another edited file of the same
assembly. Re-running after a real edit
replaces the patch; an unchanged file after a fully applied reload reports
AlreadyActive rows and changes nothing, unless another edited file of the same
assembly is in the reload — then it is re-applied with that group, and other
files of the assembly that hold active patches and are unchanged since they were
applied are re-applied too, so every active patch binds to the newest shim. With a compile-time source baseline, only
methods whose bodies actually changed are patched (UnchangedTotal counts the rest),
and a patched body that matches the baseline again is unpatched on that run.
Added rows
(see the scope reference for the property shapes still skipped), visible to edited code in the same reload
within the same assembly (pass the declaring file and its callers together), and vanish
on any compile or domain reload (an Editor-session illusion). New types, references
from other assemblies or from files that are neither passed to the reload nor
already hot-reloaded, reflection, serialization,
and Unity message discovery need uloop compile.Skipped unless the same reload — or an earlier one —
has patched every live compiled caller of the old signature. A rename or parameter-list
change is not gated: it follows the delete rules — the old signature is reported removed,
and a Warnings entry names each compiled call site left on the old behavior until
uloop compile.Skipped; finalizers and interface members are silently not applied. const and
other outside-body edits never change runtime behavior (drift is warned where
detectable).Failed method leaves that file
unapplied; patches in other files still apply, except bodies that call an added method
whose own shim failed to compile — those are Skipped until it compiles.Full rules and the Skipped/Failed condition tables: references/scope-and-limits.md.
Treat hot reload as the exploration phase and uloop compile as the landing phase:
keep edits inside the edited files, collect structural changes, and compile once —
every compile drops all patches and pause points and resets the PlayMode session (the compile response's Warning states how many were live).
While patches are active, AutoRefreshHeld is true so returning focus does not
recompile; uloop compile or --revert-all releases the hold.
One-shot methods (Awake, Start, initialization helpers) patch successfully but show
no effect on the call that already ran; the response marks them with LifecycleNote.
For values you expect to tune while playing, expose a static property getter instead of
a const.
All files live in references/ beside this skill; read the one whose trigger matches:
references/scope-and-limits.md — full scope rules: added members, signature changes, Skipped/Failed tables, source baselines, one-shot code, tunable getters.references/mechanism-and-lifecycle.md — patch mechanism, convergence, what survives which reload, Editor-code iteration without PlayMode.references/troubleshooting.md — Patched but no behavior change, JIT inlining, reading --status and InvocationCount.references/pause-point-interaction.md — how patches re-target or suppress armed pause points; one-way reachability checks.references/output.md — every response field: ErrorCode, NextActions, Methods rows, Warnings, totals.© CyberAgentGameEntertainment, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
SKILL.md and 5 other files (references) in .claude/skills/uloop-hot-reload of CyberAgentGameEntertainment/NovaShader.
Open the folder on GitHubat commit 7f0a400
Uloop Hot Reload next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Uloop Hot Reload this skillCyberAgentGameEntertainment/NovaShader | 1.6k | — | ~2k | Automated safety check: Pass | MIT | |
| Image to Three.js Modelimg2threejs/img2threejs | 18k | 1 repos | ~8.2k | Automated safety check: Pass | Apache-2.0 | |
| Web CloneJane-xiaoer/claude-skill-web-clone | 1k | 1 repos | ~2.7k | Automated safety check: Pass | MIT | |
| Threejs Game Directormajidmanzarpour/threejs-game-skills | 2.5k | — | ~2.2k | Automated safety check: Pass | MIT | |
| Game Asset Generatorhtdt/godogen | 7.1k | — | ~2.8k | Automated safety check: Pass | MIT | |
| Threejs Gameplay Systemsvalkor-ai/loom | 1.2k | 1 repos | ~1.4k | Automated safety check: Pass | Apache-2.0 |
img2threejs/img2threejs
Rebuilds the object in a reference image as a procedural, animation-ready Three.js model written entirely in code, using staged sculpting with quality checks.
Jane-xiaoer/claude-skill-web-clone
网站复刻 / 克隆方法论。USE WHEN 用户说 复刻网站、克隆网站、clone website、抄个站、仿站、 照着这个站做一个、reproduce site、还原某个网页效果、把这个站搬下来改成我的、 复刻某个交互/WebGL/Canvas/Three.js 效果。提供「先拿真源码 → 判路径 → 逆向拆解 → 搭工程 → 替换内容」的可移植决策树,覆盖静态站 /…
majidmanzarpour/threejs-game-skills
Entrypoint for building, upgrading, and finishing Three.js browser games.
htdt/godogen
Generates game art from text prompts: PNG images, GLB 3D models, rigged characters, animations and sprites, with background removal.
valkor-ai/loom
Build and iterate playable Three.js game systems: starter scaffold, architecture, design briefs, core loops, level and encounter design, entities, input, camera, collision and physics, scoring…
0x0funky/agent-sprite-forge
Draws 2D game art from code with no image model: pixel sprites, SVG props and icons, rigged characters, FX, autotiles and layouts, only when explicitly asked for.
CyberAgentGameEntertainment/NovaShader
Execute C with Unity APIs when existing uloop tools cannot inspect or edit enough.
CyberAgentGameEntertainment/NovaShader
Simulate keyboard input in PlayMode through Unity Input System.
CyberAgentGameEntertainment/NovaShader
Simulate Mouse.current input in PlayMode through Unity Input System.
CyberAgentGameEntertainment/NovaShader
Control Unity Editor Play Mode. An agent skill from CyberAgentGameEntertainment/NovaShader.
CyberAgentGameEntertainment/NovaShader
Pauses Unity playback at any source file:line without editing code or recompiling, and returns a snapshot of the locals, parameters, and instance fields at that exact frame.
CyberAgentGameEntertainment/NovaShader
Launch or restart Unity Editor. An agent skill from CyberAgentGameEntertainment/NovaShader.
Categories
Hot reload applies method-body edits and can add new methods and fields (added members are visible to edited code in the same reload within the same assembly); it can also change signatures: a…. Uloop Hot Reload is an agent skill from CyberAgentGameEntertainment/NovaShader. Hot reload applies method-body edits and can add new methods and fields (added members are visible to edited code in the same reload within the same assembly); it can also change signatures: a return-type change applies only when the same reload (or an earlier one) covers the old signature's compiled callers, while a rename or parameter change applies as an added method and warns about compiled callers it leaves on the old signature.
Uloop Hot Reload fits situations like: game Development work in your project.
Run `npx skills add CyberAgentGameEntertainment/NovaShader --skill uloop-hot-reload -a claude-code`. Or copy the skill folder (.claude/skills/uloop-hot-reload in CyberAgentGameEntertainment/NovaShader) into .claude/skills/uloop-hot-reload in your project. Claude Code loads it when a task matches its description.
Run `npx skills add CyberAgentGameEntertainment/NovaShader --skill uloop-hot-reload -a codex`. Or copy the skill folder (.claude/skills/uloop-hot-reload in CyberAgentGameEntertainment/NovaShader) into .agents/skills/uloop-hot-reload in your project. Codex loads it when a task matches its description.
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add CyberAgentGameEntertainment/NovaShader --skill uloop-hot-reload -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/uloop-hot-reload, .gemini/skills/uloop-hot-reload, .github/skills/uloop-hot-reload and .opencode/skills/uloop-hot-reload in your project.
SKILL.md names no scripts, command-line tools or credentials: Uloop Hot Reload is instructions for the agent only.
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
Uloop Hot Reload is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
About 2k tokens (SKILL.md is roughly 7.9k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 10k tokens, read only when the agent opens those files.
Skills that share tags, products or a category with Uloop Hot Reload: Image to Three.js Model (img2threejs/img2threejs, 18k stars), Web Clone (Jane-xiaoer/claude-skill-web-clone, 1k stars), Threejs Game Director (majidmanzarpour/threejs-game-skills, 2.5k stars) and Game Asset Generator (htdt/godogen, 7.1k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
CyberAgentGameEntertainment (a GitHub organization) maintains it in CyberAgentGameEntertainment/NovaShader, which has 1,622 GitHub stars. The repository holds 10 skills in this directory. The repository was last updated on October 7, 2026.
Source: CyberAgentGameEntertainment/NovaShader on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.