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.
Drive an ambitious goal past a real-world quality bar by splitting it into pieces, each looped through a builder and a fresh, harsh, blind critic until ours reaches the bar or the caller stops.
Install Gauntlet Loop
$ npx skills add DanMcInerney/orchflows --skill gauntlet-loop -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install DanMcInerney/orchflows gauntlet-loop --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/DanMcInerney/orchflows.git skills-src && mkdir -p .claude/skills && cp -r skills-src/example-workflows/gauntlet-loop/skills/gauntlet-loop .claude/skills/gauntlet-loop && 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 "gauntlet-loop" agent skill from https://github.com/DanMcInerney/orchflows/tree/main/example-workflows/gauntlet-loop/skills/gauntlet-loop into .claude/skills/gauntlet-loop/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "gauntlet-loop", 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/DanMcInerney/orchflows/tree/main/example-workflows/gauntlet-loop/skills/gauntlet-loopType 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 DanMcInerney/orchflows --skill gauntlet-loop -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install DanMcInerney/orchflows gauntlet-loop --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/DanMcInerney/orchflows.git skills-src && mkdir -p .agents/skills && cp -r skills-src/example-workflows/gauntlet-loop/skills/gauntlet-loop .agents/skills/gauntlet-loop && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "gauntlet-loop" agent skill from https://github.com/DanMcInerney/orchflows/tree/main/example-workflows/gauntlet-loop/skills/gauntlet-loop into .agents/skills/gauntlet-loop/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "gauntlet-loop", 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 DanMcInerney/orchflows --skill gauntlet-loop -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install DanMcInerney/orchflows gauntlet-loop --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/DanMcInerney/orchflows.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/example-workflows/gauntlet-loop/skills/gauntlet-loop .cursor/skills/gauntlet-loop && 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 "gauntlet-loop" agent skill from https://github.com/DanMcInerney/orchflows/tree/main/example-workflows/gauntlet-loop/skills/gauntlet-loop into .cursor/skills/gauntlet-loop/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "gauntlet-loop", 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/DanMcInerney/orchflows.git --path example-workflows/gauntlet-loop/skills/gauntlet-loop--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 DanMcInerney/orchflows --skill gauntlet-loop -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install DanMcInerney/orchflows gauntlet-loop --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/DanMcInerney/orchflows.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/example-workflows/gauntlet-loop/skills/gauntlet-loop .gemini/skills/gauntlet-loop && 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 "gauntlet-loop" agent skill from https://github.com/DanMcInerney/orchflows/tree/main/example-workflows/gauntlet-loop/skills/gauntlet-loop into .gemini/skills/gauntlet-loop/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "gauntlet-loop", 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 DanMcInerney/orchflows gauntlet-loopInstalls 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 DanMcInerney/orchflows --skill gauntlet-loop -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/DanMcInerney/orchflows.git skills-src && mkdir -p .github/skills && cp -r skills-src/example-workflows/gauntlet-loop/skills/gauntlet-loop .github/skills/gauntlet-loop && 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 "gauntlet-loop" agent skill from https://github.com/DanMcInerney/orchflows/tree/main/example-workflows/gauntlet-loop/skills/gauntlet-loop into .github/skills/gauntlet-loop/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "gauntlet-loop", 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 DanMcInerney/orchflows --skill gauntlet-loop -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install DanMcInerney/orchflows gauntlet-loop --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/DanMcInerney/orchflows.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/example-workflows/gauntlet-loop/skills/gauntlet-loop .opencode/skills/gauntlet-loop && 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 "gauntlet-loop" agent skill from https://github.com/DanMcInerney/orchflows/tree/main/example-workflows/gauntlet-loop/skills/gauntlet-loop into .opencode/skills/gauntlet-loop/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "gauntlet-loop", 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
gauntlet-loop- GitHub stars
- 117
- Token cost
- ~1.2k tokens
- SKILL.md length
- 696 words
- Files
- 2
- Skills in repo
- 12
- Repo updated
- First seen
- Licence
- MIT
At a glance
Drive an ambitious goal past a real-world quality bar by splitting it into pieces, each looped through a builder and a fresh, harsh, blind critic until ours reaches the bar or the caller stops.
- Works in 3 steps: Build. A builder makes or revises the… → Judge. Freeze the piece and apply… → Close the gap or confirm. When ours…
- Game Development work in your project
- SKILL.md covers Set the bar, Split the work, Run each piece through the… and Smooth clashing pieces, plus 2 more sections
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
Gauntlet Loop is an agent skill from DanMcInerney/orchflows. Drive an ambitious goal past a real-world quality bar by splitting it into pieces, each looped through a builder and a fresh, harsh, blind critic until ours reaches the bar or the caller stops.
Its SKILL.md is about 1.2k tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files (for example `agents/openai.yaml`).
It sits in Game Development. The repository describes itself as: 2 skills, composable into workflows, which can then be built into more complex workflows. The licence is MIT.
When your agent uses it
- Game Development work in your project
Example prompts
- “/gauntlet-loop”
Workflow steps
3 steps, taken from the first numbered list in SKILL.md.
- Build. A builder makes or revises the piece from the goal, its slice of the bar, the latest gap and applicable guidance, and may study the…
- Judge. Freeze the piece and apply shared:compare-candidates to ours and its reference. Supply the goal, bar, caller constraints and the…
- Close the gap or confirm. When ours falls short, map the gap back to ours; the next round starts from it. When ours reaches the bar…
What it can do on your machine
Read from SKILL.md and the folder at commit 8d16eb3. 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
No scripts in the folder and no shell commands in SKILL.md.
From the folder's file list and the shell code blocks in SKILL.md.
Network
Links to these hosts (documentation or services it may open):
github.com
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
Gauntlet Loop loads about 1.2k tokens when it runs. Until then it costs about 52 tokens; SKILL.md has 696 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 DanMcInerney/orchflows at commit 8d16eb3, republished under its MIT licence (© DanMcInerney). 696 words, ~1,162 tokens.
Download SKILL.mdSave it as
.claude/skills/gauntlet-loop/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.- name
- gauntlet-loop
- description
- Drive an ambitious goal past a real-world quality bar by splitting it into pieces, each looped through a builder and a fresh, harsh, blind critic until ours reaches the bar or the caller stops.
- disable-model-invocation
- true
Apply library context as the coordinator (the lead). Inputs: goal, optional bar or candidate references, workspace and output location, optional caller bounds (time, cost, rounds) and scoped settings. Treat the goal as the destination: choose the architecture, pieces and order, adding no scope the caller did not ask for.
Set the bar
The bar is a named, inspectable thing that ours can sit beside and lose to: reference artifacts for subjective quality, or tests, measurements and reference implementations for engineering. Use a supplied bar. Otherwise find the concrete comparison that plays the role real Call of Duty screenshots played for Claude of Duty; "better", "production-ready" or a self-written rubric is not a bar. The bar need not be reachable. Gather the reference material into the output location, record the bar with one sentence on why it fits, and continue without a permission round unless the caller asked to approve it.
Reaching the bar means beating a reference, or matching a threshold bar such as a test suite, a target or an explicit "as good as".
Split the work
Divide the goal into the smallest pieces that can be improved and judged separately, each mapped to the part of the bar it must reach. A piece the bar does not cover, such as sound when the bar is screenshots, gets its own bar. Keep coupled parts together where judging them apart would mislead. Run independent pieces concurrently within host limits; give shared files one owner. Add, merge or split pieces as the artifact teaches you.
Run each piece through the gauntlet
A round is one build and its judgment for one piece. Record it before the build starts; consumed rounds carry through smoothing, splits and merges. Caller round bounds apply per piece unless the caller says otherwise.
- Build. A builder makes or revises the piece from the goal, its slice of the bar, the latest gap and applicable guidance, and may study the bar. Continue a builder across rounds or replace it as useful.
- Judge. Freeze the piece and apply
shared:compare-candidatesto ours and its reference. Supply the goal, bar, caller constraints and the actual output to inspect: rendered, run, played or read. Never supply the builder's history, reasoning or summary. Blind the pair where possible, with anonymous labels and randomized order; for measurement bars the critic runs the measurement. Ask for the better side and the largest gap. - Close the gap or confirm. When ours falls short, map the gap back to ours; the next round starts from it. When ours reaches the bar, confirm the win where one verdict could reflect bias or noise, with another
shared:compare-candidatescall by a fresh critic, without the first verdict: reversed order for judged comparisons, a matched re-run for noisy measurements. Disagreement is a loss; any other win stands confirmed.
There is no fixed number of rounds. A piece that stops improving changes approach and shows the stall on the progress page; stalling is not completion.
Show full SKILL.md (200 more words)Show less
Smooth clashing pieces
When separately improved pieces start to clash, have one fresh maker, with the builders' guidance, inspect the whole result and reconcile conflicts without redesigning it. Pieces it changes lose their confirmations and re-enter the gauntlet.
Show progress
Maintain a live progress page in the output location, HTML or Markdown, showing the bar and each piece evolving: renders, drafts, test results, verdicts, stalls and remaining gaps, in whatever form suits the work. Update it as work lands so the caller can watch without interrupting. It and the run records must let a later session resume without redoing judged rounds.
Stop and return
Stop when every piece holds a confirmation for its current state, the caller stops the run, a caller bound is reached or every remaining piece is blocked. Missing rendering, inspection or independent review blocks the pieces that need it; builder claims never stand in for a critic's view of the output.
Return the artifact, the bar and why it was chosen, each piece's final verdict and largest remaining gap, rounds and observed cost, smoothing passes, the stop reason and the progress page. A run stopped while ours still falls short is an ordinary result; say where.
© DanMcInerney, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
SKILL.md and 1 other file in example-workflows/gauntlet-loop/skills/gauntlet-loop of DanMcInerney/orchflows.
- SKILL.md
- agents/openai.yaml
Open the folder on GitHubat commit 8d16eb3
Compare with similar skills
Gauntlet Loop 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 |
|---|---|---|---|---|---|---|
| Gauntlet Loop this skillDanMcInerney/orchflows | 117 | — | ~1.2k | 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 | 2.4k | — | ~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 DanMcInerney/orchflows
All 12 skills in this repoEvolve
DanMcInerney/orchflows
Iteratively improve any artifact and its improvement harness, inventing evaluation when needed; supports bounded runs, tournaments and continuous resumable search.
Benchmaker
DanMcInerney/orchflows
Build benchmarks of realistic, hard agent tasks, researched from real work, admitting only verified, shortcut-resistant, calibrated tasks and reporting how well the suite separates systems.
3D Browser Game
DanMcInerney/orchflows
Build a complete Three.js game or bounded production phase through mechanics experiments, Blender assets, QA and independent playtests.
Design Loop
DanMcInerney/orchflows
Develop a project endgoal through N bounded cycles of brainstorm and research, design, implementation, comparison testing and analysis.
Export Workflow
DanMcInerney/orchflows
Export an Orchflows workflow as a standalone native skill with a portability report and bounded trial.
Orchflows Review
DanMcInerney/orchflows
Review Orchflows against its purpose and design principles (architecture, workflow design, wording and bugs) and apply reviewed improvements on unmerged branches.
Related
Categories
Questions about Gauntlet Loop
What does Gauntlet Loop do?
Drive an ambitious goal past a real-world quality bar by splitting it into pieces, each looped through a builder and a fresh, harsh, blind critic until ours reaches the bar or the caller stops. Gauntlet Loop is an agent skill from DanMcInerney/orchflows. Drive an ambitious goal past a real-world quality bar by splitting it into pieces, each looped through a builder and a fresh, harsh, blind critic until ours reaches the bar or the caller stops.
When should I use Gauntlet Loop?
Gauntlet Loop fits situations like: game Development work in your project.
How do I install Gauntlet Loop in Claude Code?
Run `npx skills add DanMcInerney/orchflows --skill gauntlet-loop -a claude-code`. Or copy the skill folder (example-workflows/gauntlet-loop/skills/gauntlet-loop in DanMcInerney/orchflows) into .claude/skills/gauntlet-loop in your project. Claude Code loads it when a task matches its description.
How do I install Gauntlet Loop in Codex?
Run `npx skills add DanMcInerney/orchflows --skill gauntlet-loop -a codex`. Or copy the skill folder (example-workflows/gauntlet-loop/skills/gauntlet-loop in DanMcInerney/orchflows) into .agents/skills/gauntlet-loop in your project. Codex loads it when a task matches its description.
Can I use Gauntlet Loop 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 DanMcInerney/orchflows --skill gauntlet-loop -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/gauntlet-loop, .gemini/skills/gauntlet-loop, .github/skills/gauntlet-loop and .opencode/skills/gauntlet-loop in your project.
What does Gauntlet Loop need to run?
SKILL.md names no scripts, command-line tools or credentials: Gauntlet Loop is instructions for the agent only.
Does Gauntlet Loop access the network?
SKILL.md names 1 domain. As links in the text: github.com. This is read from the text; nothing was executed.
Is Gauntlet Loop 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 Gauntlet Loop use?
Gauntlet Loop 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 Gauntlet Loop use?
About 1.2k tokens (SKILL.md is roughly 4.6k 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 Gauntlet Loop?
Skills that share tags, products or a category with Gauntlet Loop: 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 Gauntlet Loop?
DanMcInerney (a GitHub user) maintains it in DanMcInerney/orchflows, which has 117 GitHub stars. The repository holds 12 skills in this directory. The repository was last updated on October 4, 2026.
Source: DanMcInerney/orchflows on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.