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.
Build and verify a Babylon.js game progressively in OpenHarness's live Game Viewer.
Install Studio
$ npx skills add autonomous-ai/openharness --skill studio -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install autonomous-ai/openharness studio --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/autonomous-ai/openharness.git skills-src && mkdir -p .claude/skills && cp -r skills-src/store/agents/godogen/skills/studio .claude/skills/studio && 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 "studio" agent skill from https://github.com/autonomous-ai/openharness/tree/main/store/agents/godogen/skills/studio into .claude/skills/studio/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "studio", 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/autonomous-ai/openharness/tree/main/store/agents/godogen/skills/studioType 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 autonomous-ai/openharness --skill studio -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install autonomous-ai/openharness studio --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/autonomous-ai/openharness.git skills-src && mkdir -p .agents/skills && cp -r skills-src/store/agents/godogen/skills/studio .agents/skills/studio && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "studio" agent skill from https://github.com/autonomous-ai/openharness/tree/main/store/agents/godogen/skills/studio into .agents/skills/studio/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "studio", 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 autonomous-ai/openharness --skill studio -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install autonomous-ai/openharness studio --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/autonomous-ai/openharness.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/store/agents/godogen/skills/studio .cursor/skills/studio && 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 "studio" agent skill from https://github.com/autonomous-ai/openharness/tree/main/store/agents/godogen/skills/studio into .cursor/skills/studio/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "studio", 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/autonomous-ai/openharness.git --path store/agents/godogen/skills/studio--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 autonomous-ai/openharness --skill studio -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install autonomous-ai/openharness studio --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/autonomous-ai/openharness.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/store/agents/godogen/skills/studio .gemini/skills/studio && 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 "studio" agent skill from https://github.com/autonomous-ai/openharness/tree/main/store/agents/godogen/skills/studio into .gemini/skills/studio/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "studio", 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 autonomous-ai/openharness studioInstalls 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 autonomous-ai/openharness --skill studio -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/autonomous-ai/openharness.git skills-src && mkdir -p .github/skills && cp -r skills-src/store/agents/godogen/skills/studio .github/skills/studio && 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 "studio" agent skill from https://github.com/autonomous-ai/openharness/tree/main/store/agents/godogen/skills/studio into .github/skills/studio/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "studio", 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 autonomous-ai/openharness --skill studio -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install autonomous-ai/openharness studio --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/autonomous-ai/openharness.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/store/agents/godogen/skills/studio .opencode/skills/studio && 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 "studio" agent skill from https://github.com/autonomous-ai/openharness/tree/main/store/agents/godogen/skills/studio into .opencode/skills/studio/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "studio", 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.
Facts
- Skill name
studio- GitHub stars
- 1.1k
- Token cost
- ~1.1k tokens
- SKILL.md length
- 608 words
- Files
- 1
- Skills in repo
- 100
- Repo updated
- First seen
- Licence
- MIT
At a glance
Build and verify a Babylon.js game progressively in OpenHarness's live Game Viewer.
- Works in 4 steps: Update .harness/progress.json:… → Edit src/, public/, and index.html. The… → After every small milestone, npm run… → …
- Game Development work in your project
- SKILL.md covers Loop, Bridge, Rewind and playtest moments and Project facts, plus 1 more section
- Calls npm and node
What it does
Studio is an agent skill from autonomous-ai/openharness. Build and verify a Babylon.js game progressively in OpenHarness's live Game Viewer.
Its SKILL.md is about 1.1k 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: The ultimate harness for coding agents and beyond. All your agents. All your machines. One command center. Start with code, then follow your curiosity and build across… The licence is MIT.
When your agent uses it
- Game Development work in your project
Example prompts
- “/studio”
Workflow steps
4 steps, taken from the first numbered list in SKILL.md.
- Update .harness/progress.json: {"phase":"world","message":"Shaping the mountain"}.
- Edit src/, public/, and index.html. The viewer watches these files. Import generated assets
- After every small milestone, npm run check. Inspect the preview, then test the game.
- node "$GODOGEN_TOOLS/check.mjs" checks the actual viewer's current build/runtime state.
What it can do on your machine
Read from SKILL.md and the folder at commit 50da5db. It shows what the files ask for, not the result of running them.
Tool permissions
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.
Runs code
Shell commands in SKILL.md call:
npmnode
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md. Its commands use npm, which can reach the network depending on how they are called.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Studio loads about 1.1k tokens when it runs. Until then it costs about 23 tokens; SKILL.md has 608 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.
Safety
Auto-check passed
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.
SKILL.md
The full file from autonomous-ai/openharness at commit 50da5db, republished under its MIT licence (© autonomous-ai). 608 words, ~1,118 tokens.
Download SKILL.mdSave it as
.claude/skills/studio/SKILL.md (or your agent's skills folder).- name
- studio
- description
- Build and verify a Babylon.js game progressively in OpenHarness's live Game Viewer.
The live game studio
The viewer compiles saves into isolated versions. A broken edit cannot replace the last working game. While the user plays, a new version waits behind View update so it never resets their run.
Loop
- Update
.harness/progress.json:{"phase":"world","message":"Shaping the mountain"}. Phases areconcept,world,play,polish,check. Report real work, with no invented timings. - Edit
src/,public/, andindex.html. The viewer watches these files. Import generated assets using Vite URLs (import treeUrl from './assets/tree.glb?url'); avoid absolute/assets/paths. - After every small milestone,
npm run check. Inspect the preview, then test the game. node "$GODOGEN_TOOLS/check.mjs"checks the actual viewer's current build/runtime state. It requires an open viewer. Its success means the preview rendered without reported errors; it does not replace gameplay testing. Never fabricate a successful runtime report.
Bridge
Define window.harnessGame with setMode('explore'|'play'), setPaused(boolean), restart(),
and stats() returning real values. stats() may include fps, objects, score, distance.
The starter demonstrates all of these. After the first successful render, dispatch
new CustomEvent('harness:ready'). Game Viewer captures errors before that event and keeps the
previous version visible. Do not remove the error bridge or signal success before rendering.
Keyboard listeners should use event.code, release input on blur, and prevent arrow/space scroll
only when the game has focus. Progress must use elapsed seconds, not an assumed frame rate.
Respect pause, reduce motion, and audio muting. Use clear focus styles and readable contrast.
Rewind and playtest moments
The starter also exposes synchronous captureState() and restoreState(snapshot). Keep them
when changing the game. Capture a JSON object under 64 KiB with a schema identifier and all
state needed to continue: positions, velocities, collected items, score, elapsed time, random
state when used, and the camera. Validate the whole snapshot before mutating anything. Restore
meshes and HUD immediately, clear held keys, and leave pause and preview mode unchanged. The
studio stores preview mode separately with each moment. setPaused(true) freezes
the simulation and camera inertia. A replacement game must use its own schema and state shape.
The studio records five frames per second, keeping the latest 180. It pauses while the player
scrubs, then restores the live moment or resumes from the selected frame. Return game seconds
as stats().time; stats().running = false preserves the terminal frame without overwriting
the run with an idle finish screen. Dispatch harness:timeline-reset when an in-game restart
control begins a new run. Studio Restart already clears history.
Show full SKILL.md (212 more words)Show less
Pin moment writes out/playtests/<id>/moment.json, an optional screenshot.jpg of the game
canvas, and game/ containing that exact compiled version. Read these notes when responding
to playtest feedback. A Keep note is something to preserve; Change and Explore notes describe
the user's requests. Saved builds stay compatible with their own snapshots after source edits.
The current editable source remains in src/; never imply the archived build is the current
source. Do not delete or overwrite user moments. Revisit through Saved moments to inspect them.
Verify pause → capture → play → restore → resume, including an already-collected item and a moving/jumping character. Reject an incompatible snapshot without changing the world. Confirm the player can steer after resuming and that the saved state reopens with its original build.
Project facts
studio.json contains title, description, and controls (short text). Keep those accurate.
Put the current brief, completed features, remaining work, and asset attribution in README.md.
For external services, get the user's budget before the first paid generation and retain provenance.
Verification
Use browser capture on the running preview. Exercise Play, movement, restart, and a full game loop.
Check the canvas is nonblank, there are no runtime errors, and controls also work at a narrow size.
Finish by setting phase check with a factual message describing the checks that actually passed.
© autonomous-ai, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
Just SKILL.md in store/agents/godogen/skills/studio of autonomous-ai/openharness.
Open the folder on GitHubat commit 50da5db
Compare with similar skills
Studio 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 |
|---|---|---|---|---|---|---|
| Studio this skillautonomous-ai/openharness | 1.1k | — | ~1.1k | 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 | 2 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 |
Similar skills
Web Clone
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 /…
Threejs Game Director
majidmanzarpour/threejs-game-skills
Entrypoint for building, upgrading, and finishing Three.js browser games.
Game Asset Generator
htdt/godogen
Generates game art from text prompts: PNG images, GLB 3D models, rigged characters, animations and sprites, with background removal.
Threejs Gameplay Systems
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…
Uloop Execute Dynamic Code
CyberAgentGameEntertainment/NovaShader
Execute C with Unity APIs when existing uloop tools cannot inspect or edit enough.
More from autonomous-ai/openharness
All 100 skills in this repoG-code Slicer Tool
autonomous-ai/openharness
Slices 3D mesh files into printer-profiled plain G-code through real slicer CLIs, with backend discovery, input inspection, dry runs and static validation.
Home Assistant Automation Builder
autonomous-ai/openharness
Turns a home-automation request into standard, testable automations.yaml, run against Home Assistant Core's real triggers and verified with its own trace tool.
Score Music Composer
autonomous-ai/openharness
Turns a musical brief into LilyPond concert-pitch music, checked parts for each instrument and a playable practice pack.
OrcaSlicer 3MF and G-code Workflow
autonomous-ai/openharness
Turns an STL and explicit printer and material requirements into compared OrcaSlicer plans, an editable 3MF project, checked G-code and a portable handoff.
Sheets and Docs Report Builder
autonomous-ai/openharness
Builds an editable DOCX report, a formula-driven XLSX workbook and a fresh LibreOffice PDF preview from one structured source file, then checks them together.
Bambu Labs
autonomous-ai/openharness
Dry-run, upload, and cautiously initiate local Bambu Lab print jobs from validated plain .gcode, using Bambu LAN FTPS/MQTT handoffs.
Related
Categories
Questions about Studio
What does Studio do?
Build and verify a Babylon.js game progressively in OpenHarness's live Game Viewer. Studio is an agent skill from autonomous-ai/openharness.js game progressively in OpenHarness's live Game Viewer.
When should I use Studio?
Studio fits situations like: game Development work in your project.
How do I install Studio in Claude Code?
Run `npx skills add autonomous-ai/openharness --skill studio -a claude-code`. Or copy the skill folder (store/agents/godogen/skills/studio in autonomous-ai/openharness) into .claude/skills/studio in your project. Claude Code loads it when a task matches its description.
How do I install Studio in Codex?
Run `npx skills add autonomous-ai/openharness --skill studio -a codex`. Or copy the skill folder (store/agents/godogen/skills/studio in autonomous-ai/openharness) into .agents/skills/studio in your project. Codex loads it when a task matches its description.
Can I use Studio in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add autonomous-ai/openharness --skill studio -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/studio, .gemini/skills/studio, .github/skills/studio and .opencode/skills/studio in your project.
What does Studio need to run?
Going by SKILL.md and its folder, Studio needs the command-line tools its instructions call (npm and node).
Does Studio access the network?
SKILL.md contains no URLs. Its commands use npm, which can reach the network depending on how they are called. This is read from the text; nothing was executed.
Is Studio safe to install?
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.
What licence does Studio use?
Studio is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Studio use?
About 1.1k tokens (SKILL.md is roughly 4.5k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to Studio?
Skills that share tags, products or a category with Studio: 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.
Who maintains Studio?
autonomous-ai (a GitHub organization) maintains it in autonomous-ai/openharness, which has 1,149 GitHub stars. The repository holds 100 skills in this directory. The repository was last updated on October 8, 2026.
Source: autonomous-ai/openharness on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.