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.
Persistent operation history and orchestration. An agent skill from Besty0728/Unity-Skills.
$ npx skills add Besty0728/Unity-Skills --skill unity-workflow -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install Besty0728/Unity-Skills unity-workflow --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/Besty0728/Unity-Skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/'SkillsForUnity/unity-skills~/skills/workflow' .claude/skills/unity-workflow && 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 "unity-workflow" agent skill from https://github.com/Besty0728/Unity-Skills/tree/main/SkillsForUnity/unity-skills~/skills/workflow into .claude/skills/unity-workflow/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "unity-workflow", 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/Besty0728/Unity-Skills/tree/main/SkillsForUnity/unity-skills~/skills/workflowType 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 Besty0728/Unity-Skills --skill unity-workflow -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install Besty0728/Unity-Skills unity-workflow --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Besty0728/Unity-Skills.git skills-src && mkdir -p .agents/skills && cp -r skills-src/'SkillsForUnity/unity-skills~/skills/workflow' .agents/skills/unity-workflow && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "unity-workflow" agent skill from https://github.com/Besty0728/Unity-Skills/tree/main/SkillsForUnity/unity-skills~/skills/workflow into .agents/skills/unity-workflow/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "unity-workflow", 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 Besty0728/Unity-Skills --skill unity-workflow -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install Besty0728/Unity-Skills unity-workflow --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Besty0728/Unity-Skills.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/'SkillsForUnity/unity-skills~/skills/workflow' .cursor/skills/unity-workflow && 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 "unity-workflow" agent skill from https://github.com/Besty0728/Unity-Skills/tree/main/SkillsForUnity/unity-skills~/skills/workflow into .cursor/skills/unity-workflow/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "unity-workflow", 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/Besty0728/Unity-Skills.git --path 'SkillsForUnity/unity-skills~/skills/workflow'--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 Besty0728/Unity-Skills --skill unity-workflow -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install Besty0728/Unity-Skills unity-workflow --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Besty0728/Unity-Skills.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/'SkillsForUnity/unity-skills~/skills/workflow' .gemini/skills/unity-workflow && 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 "unity-workflow" agent skill from https://github.com/Besty0728/Unity-Skills/tree/main/SkillsForUnity/unity-skills~/skills/workflow into .gemini/skills/unity-workflow/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "unity-workflow", 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 Besty0728/Unity-Skills unity-workflowInstalls 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 Besty0728/Unity-Skills --skill unity-workflow -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/Besty0728/Unity-Skills.git skills-src && mkdir -p .github/skills && cp -r skills-src/'SkillsForUnity/unity-skills~/skills/workflow' .github/skills/unity-workflow && 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 "unity-workflow" agent skill from https://github.com/Besty0728/Unity-Skills/tree/main/SkillsForUnity/unity-skills~/skills/workflow into .github/skills/unity-workflow/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "unity-workflow", 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 Besty0728/Unity-Skills --skill unity-workflow -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install Besty0728/Unity-Skills unity-workflow --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Besty0728/Unity-Skills.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/'SkillsForUnity/unity-skills~/skills/workflow' .opencode/skills/unity-workflow && 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 "unity-workflow" agent skill from https://github.com/Besty0728/Unity-Skills/tree/main/SkillsForUnity/unity-skills~/skills/workflow into .opencode/skills/unity-workflow/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "unity-workflow", 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.
unity-workflowPersistent operation history and orchestration. An agent skill from Besty0728/Unity-Skills.
Unity Workflow is an agent skill from Besty0728/Unity-Skills. Persistent operation history and orchestration
Its SKILL.md is about 4.1k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.
It sits in Game Development. The repository describes itself as: AI automation skills specifically designed for Unity. The licence is MIT.
Read from SKILL.md and the folder at commit 12a40e4. 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 python).
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.
Unity Workflow loads about 4.1k tokens when it runs. Until then it costs about 15 tokens; SKILL.md has 1,611 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 Besty0728/Unity-Skills at commit 12a40e4, republished under its MIT licence (© Besty0728). 1,611 words, ~4,128 tokens.
.claude/skills/unity-workflow/SKILL.md (or your agent's skills folder).Before calling any skill in this module: if you are about to call a skill with parameters guessed from its name or description, STOP — read this file (or fetch its schema via
GET /skills/recommend?includeSchema=true) first. If you already have the parameter definitions from recommend/schema, you may proceed straight to dryRun.
Persistent history and rollback system for AI operations ("Time Machine"). Allows tagging tasks, snapshotting objects before modification, and undoing specific tasks even after Editor restarts.
NEW: Session-level undo - Group all changes from a conversation and undo them together.
SkillMode.SemiAuto(bookmark / history / task / session 系列里的纯读查询 + workflow_plan,后者 ReadOnly=true 仅生成聚合计划),可直接执行。有副作用的 skill (bookmark_set / bookmark_goto / workflow_snapshot_object / workflow_snapshot_created / batch_retry_failed) 走默认 SkillMode.FullAuto,需 grant。bookmark_delete / workflow_delete_task(标 Operation.Delete,删除书签/任务记录)、workflow_clear_history(Operation.Delete + RiskLevel=high,清空全部历史+redo栈+文件存储,不可逆)。这些在 Approval/Auto 下返 MODE_FORBIDDEN,仅 Bypass 或 Allowlist 命中可调。注意:
workflow_undo_task/workflow_session_undo不是 Delete operation(标的是 Modify/Execute),它们能在 Approval/Auto 直接撤销已记录任务。
Surface profile: workflow_undo_task / workflow_redo_task / workflow_revert_task / workflow_session_undo inspect every snapshot the target task(s) would restore. If any snapshot would author a category the active profile withdraws — a scene GameObject, or a .unity / .mat asset — the whole call is refused with SURFACE_EXCLUDED (surfaceProfile/category/operation/manualDoc/userControlled/hint at the top level, not nested under details) rather than partially applied. Snapshots of scripts, prefabs, textures, ScriptableObjects, and Editor/project settings are unaffected — those stay undoable under every profile.
DO NOT (common hallucinations):
workflow_save does not exist → use workflow_task_end to end and save a taskworkflow_rollback does not exist → use workflow_undo_task (by taskId) or workflow_session_undo (by sessionId)workflow_create does not exist → use workflow_task_startworkflow_revert_task is deprecated → use workflow_undo_taskRouting:
editor_undo / editor_redo (editor module)history_undo with steps parameter (this module)workflow_session_undo (this module)bookmark_setSave current selection and scene view position as a bookmark.
| Parameter | Type | Required | Default | Description |
|---|---|---|---|---|
| bookmarkName | string | Yes | - | Name for the bookmark |
| note | string | No | null | Optional note for the bookmark |
Returns: { success, bookmark, selectedCount, hasSceneView, note }
bookmark_gotoRestore selection and scene view from a bookmark.
| Parameter | Type | Required | Default | Description |
|---|---|---|---|---|
| bookmarkName | string | Yes | - | Name of the bookmark to restore |
Returns: { success, bookmark, restoredSelection, note }
bookmark_listList all saved bookmarks.
No parameters.
Returns: { success, count, bookmarks: [{ name, selectedCount, hasSceneView, note, createdAt }] }
bookmark_deleteDelete a bookmark.
| Parameter | Type | Required | Default | Description |
|---|---|---|---|---|
| bookmarkName | string | Yes | - | Name of the bookmark to delete |
Returns: { success, deleted }
history_undoUndo the last operation (or multiple steps).
| Parameter | Type | Required | Default | Description |
|---|---|---|---|---|
| steps | int | No | 1 | Number of undo steps to perform |
Returns: { success, undoneSteps }
history_redoRedo the last undone operation (or multiple steps).
| Parameter | Type | Required | Default | Description |
|---|---|---|---|---|
| steps | int | No | 1 | Number of redo steps to perform |
Returns: { success, redoneSteps }
history_get_currentGet the name of the current undo group.
No parameters.
Returns: { success, currentGroup, groupIndex }
workflow_planGenerate a combined execution plan for multiple skills on the server side.
| Parameter | Type | Required | Default | Description |
|---|---|---|---|---|
skillsJson | string | Yes | - | JSON array of { "name": "...", "params": { ... } } entries |
Returns: { totalSteps, totalRisk, steps, dependencies, warnings, mayDisconnect }
batch_query_assetsQuery project assets with filters that are useful before batch cleanup or migration work.
| Parameter | Type | Required | Default | Description |
|---|---|---|---|---|
searchFilter | string | No | - | Extra AssetDatabase.FindAssets filter text |
folder | string | No | Assets | Search root |
typeFilter | string | No | - | Asset type filter such as t:Material or Prefab |
namePattern | string | No | - | Regex applied to file name without extension |
labelFilter | string | No | - | Asset label filter such as l:Addressable |
maxResults | int | No | 200 | Max assets returned |
Returns: { count, totalMatched, summary, assets }
batch_retry_failedRetry only the failed items from an earlier batch execution report. This now reuses the original operation context stored in the report.
| Parameter | Type | Required | Default | Description |
|---|---|---|---|---|
reportId | string | Yes | - | Source report ID from batch_report_get / batch_report_list |
runAsync | bool | No | true | Return a jobId immediately or wait for completion |
chunkSize | int | No | 100 | Chunk size for retry execution |
Returns: { status, jobId?, retryCount, originalReportId, reportId? }
workflow_session_startStart a new session (conversation-level). All changes will be tracked and can be undone together. Call this at the beginning of each conversation.
| Parameter | Type | Required | Default | Description |
|---|---|---|---|---|
| tag | string | No | null | Label for the session |
Returns: { success, sessionId, message }
workflow_session_endEnd the current session and save all tracked changes. Call this at the end of each conversation.
No parameters.
Returns: { success, sessionId, message }
workflow_session_undoUndo all changes made during a specific session (conversation-level undo).
| Parameter | Type | Required | Default | Description |
|---|---|---|---|---|
| sessionId | string | No | null | The UUID of the session to undo. If not provided, undoes the most recent session |
Returns: { success, sessionId, message }
workflow_session_listList all recorded sessions (conversation-level history).
No parameters.
Returns: { success, count, currentSessionId, sessions: [{ sessionId, taskCount, totalChanges, startTime, endTime, tags }] }
workflow_session_statusGet the current session status.
No parameters.
Returns: { success, hasActiveSession, currentSessionId, isRecording, currentTaskId, currentTaskTag, currentTaskDescription, snapshotCount }
workflow_task_startStart a new persistent workflow task to track changes for undo. Call workflow_task_end when done.
| Parameter | Type | Required | Default | Description |
|---|---|---|---|---|
| tag | string | Yes | - | Short label for the task (e.g., "Create NPC") |
| description | string | No | "" | Detailed description or prompt |
Returns: { success, taskId, message }
workflow_task_endEnd the current workflow task and save it. Requires an active task (call workflow_task_start first).
No parameters.
Returns: { success, taskId, snapshotCount, message }
workflow_snapshot_objectManually snapshot an object's state before modification. Requires an active task (call workflow_task_start first).
Call this BEFORE component_set_property, gameobject_set_transform, etc.
| Parameter | Type | Required | Default | Description |
|---|---|---|---|---|
| name | string | No | null | Name of the Game Object |
| instanceId | int | No | 0 | Instance ID of the object (preferred) |
Returns: { success, objectName, type }
workflow_snapshot_createdRecord a newly created object for undo tracking. Requires an active task (call workflow_task_start first).
Note: component_add and gameobject_create automatically record created objects, so you typically don't need to call this manually.
| Parameter | Type | Required | Default | Description |
|---|---|---|---|---|
| name | string | No | null | Name of the Game Object |
| instanceId | int | No | 0 | Instance ID of the object (preferred) |
Returns: { success, objectName, type }
workflow_listList persistent workflow history.
No parameters.
Returns: { success, count, history: [{ id, tag, description, time, changes }] }
workflow_undo_taskUndo changes from a specific task (restore to previous state). The undone task is saved and can be redone later.
| Parameter | Type | Required | Default | Description |
|---|---|---|---|---|
| taskId | string | Yes | - | The UUID of the task to undo |
Returns: { success, taskId }
workflow_redo_taskRedo a previously undone task (restore changes).
| Parameter | Type | Required | Default | Description |
|---|---|---|---|---|
| taskId | string | No | null | The UUID of the task to redo. If not provided, redoes the most recently undone task |
Returns: { success, taskId }
workflow_undone_listList all undone tasks that can be redone.
No parameters.
Returns: { success, count, undoneStack: [{ id, tag, description, time, changes }] }
workflow_revert_task(deprecated) Alias for workflow_undo_task. Use workflow_undo_task instead.
| Parameter | Type | Required | Default | Description |
|---|---|---|---|---|
| taskId | string | Yes | - | The UUID of the task to undo |
Returns: { success, taskId }
workflow_delete_taskDelete a task from history (does not revert changes, just removes the record).
| Parameter | Type | Required | Default | Description |
|---|---|---|---|---|
| taskId | string | Yes | - | The UUID of the task to delete |
Returns: { success, deletedId }
workflow_clear_historyPermanently clear ALL workflow history: every task, the redo (undone) stack, and every backed-up file blob in the content-addressed store. High-risk and irreversible.
This ONLY deletes tracking history — it does NOT undo or revert any change already applied to your project assets, scenes, or settings. To roll changes back, use workflow_undo_task / workflow_session_undo before clearing.
Marked SkillOperation.Delete + RiskLevel="high", so it is NeverInSemi (returns MODE_FORBIDDEN in Approval/Auto; only Bypass or an Allowlist hit can call it).
Parameters: None
Returns: { success, before, after, message } where before/after each report { tasks, undoneStack, historyFileBytes, fileStoreBytes }.
History is persisted to workflow_history.json (schemaVersion 5). Asset and .meta bytes are independently content-addressed in Library/UnitySkills/workflow_files/<sha1>; history keeps fileHash / metaFileHash references. Schema 2/3 histories are migrated atomically: legacy blobs are made durable before inline base64 is removed.
Snapshots are tiered by SnapshotType:
| Type | Trigger | What is stored | Undo behavior |
|---|---|---|---|
| Created | New asset/folder | path + GUID only | Delete the created asset/folder |
| Moved | asset_move | old + new path only | Move back to the old path |
| Deleted | asset_delete etc. | file + .meta moved into the store | Full restore, including .cs scripts (old implementation could not restore .cs) |
| Modified | material / SO / scene / uss / uxml / shadergraph … | content-addressed backup + lightweight originalJson | Restore the backed-up bytes |
| Setting | editor / project settings | handled via WorkflowSettingRestorerRegistry | Registry restores the previous value |
Undo/redo return per-snapshot detail (TaskUndoResult: total / succeeded / failed / details / error). Operations run in reverse order; on the first failure, failed and unprocessed snapshots stay on their source stack so they can be retried.
WorkflowAutoCleanConfig (EditorPrefs keys UnitySkills.Workflow.*) trims history and the file store after EndTask and after LoadHistory. Defaults: MaxTasks=200, MaxHistoryMB=32, MaxTaskAgeDays=30, MaxStoreMB=512, StoreMaxAgeDays=7. Store age/size pruning never removes a blob referenced by retained history. A value of 0 disables that individual limit.
Setting-class skills used to be one-way; they now register a restorer and can be rolled back: console_set_pause_on_error / console_set_collapse / console_set_clear_on_play, debug_set_defines, graphics_set_quality_level / graphics_set_default_render_pipeline / graphics_set_quality_render_pipeline / graphics_add_always_included_shader / graphics_remove_always_included_shader / graphics_set_shader_stripping, physics_set_gravity / physics_set_layer_collision, project_add_tag.
Cinemachine's 28 write skills now set TracksWorkflow=true (the snapshot code existed but never auto-triggered). scene_save / scene_create are now rollback-capable (scene_save over an existing scene backs up the old file as a Modified snapshot).
scene_save undo restores the on-disk .unity file; if the scene is currently open, you must Reload Scene for the restore to take effect.GlobalObjectId becomes invalid across an Editor restart, so undo will mark them as failed in the result detail.import unity_skills
# Session-level: wrap entire conversation for bulk undo
unity_skills.call_skill("workflow_session_start", tag="Build Player")
unity_skills.call_skill("gameobject_create", name="Player", primitiveType="Capsule")
unity_skills.call_skill("component_add", name="Player", componentType="Rigidbody")
unity_skills.call_skill("workflow_session_end")
# Later: undo entire session
sessions = unity_skills.call_skill("workflow_session_list")
unity_skills.call_skill("workflow_session_undo", sessionId=sessions["sessions"][0]["sessionId"])The following operations are automatically tracked for undo when a session/task is active:
gameobject_create / gameobject_create_batchgameobject_duplicate / gameobject_duplicate_batchcomponent_add / component_add_batchui_create_* (canvas, button, text, image, etc.)light_createprefab_instantiate / prefab_instantiate_batchmaterial_create / material_duplicateterrain_createcinemachine_create_vcamFor modification operations, the system auto-snapshots target objects before changes when possible.
Exact names, parameters, defaults, and returns are defined by GET /skills/schema or unity_skills.get_skill_schema(), not by this file.
© Besty0728, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Just SKILL.md in SkillsForUnity/unity-skills~/skills/workflow of Besty0728/Unity-Skills.
Open the folder on GitHubat commit 12a40e4
Unity Workflow 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 |
|---|---|---|---|---|---|---|
| Unity Workflow this skillBesty0728/Unity-Skills | 1.8k | — | ~4.1k | 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 | 2.4k | — | ~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…
CyberAgentGameEntertainment/NovaShader
Execute C with Unity APIs when existing uloop tools cannot inspect or edit enough.
Besty0728/Unity-Skills
Automate the Unity Editor through a local REST API — scripts, scenes, prefabs, assets, materials, lighting, tests and hundreds of other Editor operations.
Besty0728/Unity-Skills
Edit Unity Animator Controllers and drive runtime parameters
Besty0728/Unity-Skills
Advise on Unity gameplay and system architecture. An agent skill from Besty0728/Unity-Skills.
Besty0728/Unity-Skills
Unified batch and async-job orchestration. An agent skill from Besty0728/Unity-Skills.
Besty0728/Unity-Skills
Drive Unity Behavior behavior graphs and blackboard variables
Besty0728/Unity-Skills
Capture and query the Unity Editor console. An agent skill from Besty0728/Unity-Skills.
Categories
Persistent operation history and orchestration. An agent skill from Besty0728/Unity-Skills. Unity Workflow is an agent skill from Besty0728/Unity-Skills.
Unity Workflow fits situations like: game Development work in your project.
Run `npx skills add Besty0728/Unity-Skills --skill unity-workflow -a claude-code`. Or copy the skill folder (SkillsForUnity/unity-skills~/skills/workflow in Besty0728/Unity-Skills) into .claude/skills/unity-workflow in your project. Claude Code loads it when a task matches its description.
Run `npx skills add Besty0728/Unity-Skills --skill unity-workflow -a codex`. Or copy the skill folder (SkillsForUnity/unity-skills~/skills/workflow in Besty0728/Unity-Skills) into .agents/skills/unity-workflow 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 Besty0728/Unity-Skills --skill unity-workflow -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/unity-workflow, .gemini/skills/unity-workflow, .github/skills/unity-workflow and .opencode/skills/unity-workflow in your project.
SKILL.md names no scripts, command-line tools or credentials: Unity Workflow 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.
Unity Workflow is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
About 4.1k tokens (SKILL.md is roughly 17k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
Skills that share tags, products or a category with Unity Workflow: 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, 2.4k 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.
Besty0728 (a GitHub user) maintains it in Besty0728/Unity-Skills, which has 1,814 GitHub stars. The repository holds 82 skills in this directory. The repository was last updated on October 6, 2026.
Source: Besty0728/Unity-Skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.