What it does
Turn any goal into a short prompt that makes your agent set a real quality bar, run builder and critic pairs, compare blind, and loop until it wins.
- Connects Instruction files the AI reads
- Account or key Not confirmed yet (README not read yet)
- Category 자동화와 에이전트
제작자용: README에 배지 달기
제작자라면 이 코드를 README에 붙여 넣으세요. 배지는 이 페이지로 연결됩니다.
[](https://mcp.popnx.com/en/skills/robonuggets-gauntlet-loop)비슷한 Skill
같은 종류의 작업, Skill 목록과 같은 순서
robonuggets의 Skill(지시 묶음) 1개, AI가 읽고 그대로 일해요 · MCP server가 아니에요
Skill과 MCP의 차이
MCP = 손
AI를 외부 서비스나 데이터에 연결합니다(예: Notion 읽기, 청구서 만들기). 프로그램이나 서버가 실행 중이어야 합니다.
Skill = 안내서
작업 방법을 AI에게 가르치는 텍스트 파일. 어떤 서비스에도 연결되지 않습니다.
겹치는 경우도 있습니다. 도구를 부르는 스크립트가 있는 Skill도, 지식만 보내는 MCP도 있습니다. 하려는 작업을 기준으로 고르세요.
쓸 수 있는 앱
Claude Code
제작자 README와 repo 폴더 기준
설치
Is it safe?
- Who made it
GitHub account robonuggets (person), 2 years old
- Use and upkeep
★ 1,254 stars · code last changed 2026년 8월 6일
- Any scripts?
No, plain text files the AI reads and follows
- Uses the internet?
No scripts, so it does not go online by itself
- Changes machine-wide settings?
No hooks or writes to machine settings found
Checked automatically from the repo files at commit 9b1975a (read only, nothing was run). Not a safety guarantee: read it and decide for yourself
먼저: 어떤 AI를 쓰시나요
쓰는 앱을 고르면 그 앱의 설치 방법만 보여 드립니다
Option 1Upload to claude.ai (web and app)
Uploading to claude.ai would fail: the description is over 200 characters (443). Use "Let the AI install it" instead
Option 1Claude Code에게 설치 맡기기
이 문장을 복사해 Claude Code 채팅에 붙여 넣으세요
For one project, paste it into a chat that is open in that project’s folder · The AI always shows you the path before installing
The AI tells you what it will do first and asks your permission at every step
Claude Code를 다시 열고 /gauntlet-loop를 입력하거나 관련 작업을 요청하면 Claude가 알아서 써요
Checked against official docs 2026년 11월 12일 · Source: code.claude.com
For Terminal users
Skill은 AI가 따르는 지시예요. 설치 전에 파일을 읽고, 믿을 수 있는 제작자 것만 설치하세요.
터미널 열기
Mac: Command+스페이스 후 Terminal 입력 · Windows: 아래 명령은 PowerShell에서 안 돼요. 위의 “AI에게 설치 맡기기”를 쓰세요
skill 폴더를 ~/.claude/skills에 복사
repo를 임시 폴더에 내려받고 SKILL.md가 있는 폴더만 복사해요
명령을 확인하는 중 · 확인을 통과하면 복사 버튼이 나타나요
Claude Code를 다시 열고 /gauntlet-loop를 입력하거나 관련 작업을 요청하면 Claude가 알아서 써요
ChatGPT 데스크톱 앱
ChatGPT 데스크톱 앱에는 Codex가 들어 있고, Codex는 ~/.agents/skills 폴더에서 Skill을 읽습니다
Option 1ChatGPT에게 설치 맡기기
ChatGPT 데스크톱 앱에서 Codex를 열고 이 문장을 채팅에 붙여 넣으세요
The AI always shows you the path before installing
The AI tells you what it will do first and asks your permission at every step
Option 2폴더를 직접 넣기
gauntlet-loop 폴더를 ~/.agents/skills/gauntlet-loop에 넣으세요
~는 홈 폴더($HOME)입니다
For Terminal users
Skill은 AI가 따르는 지시예요. 설치 전에 파일을 읽고, 믿을 수 있는 제작자 것만 설치하세요.
터미널 열기
Mac: Command+스페이스 후 Terminal 입력 · Windows: 아래 명령은 PowerShell에서 안 돼요. 위의 “AI에게 설치 맡기기”를 쓰세요
skill 폴더를 ~/.agents/skills에 복사
repo를 임시 폴더에 내려받고 SKILL.md가 있는 폴더만 복사해요
명령을 확인하는 중 · 확인을 통과하면 복사 버튼이 나타나요
설치한 뒤
- ChatGPT 데스크톱 앱: 사이드바에서 Skills를 열어 Skill이 보이는지 확인하세요
- 쓰는 법: ChatGPT에서는 @를 입력하고 Skill을 고르세요 · Codex CLI나 IDE 확장 프로그램에서는 /skills를 실행하거나 $ 뒤에 Skill 이름을 입력하세요
- Codex는 새로 설치한 Skill을 스스로 찾습니다. 보이지 않으면 Codex를 다시 시작하세요
Checked against official docs 2026년 11월 15일 · Source: learn.chatgpt.com
웹과 모바일의 ChatGPT
직접 설치한 Skill은 쓸 수 없고, 디렉터리의 플러그인에 들어 있는 Skill만 쓸 수 있습니다
이 Skill을 ChatGPT에서 쓰려면 위 방법대로 ChatGPT 데스크톱 앱을 쓰세요
Checked against official docs 2026년 11월 15일 · Source: learn.chatgpt.com
Option 1Codex에게 설치 맡기기
이 문장을 복사해 Codex 채팅에 붙여 넣으세요 · ChatGPT 데스크톱 앱 안의 Codex, Codex CLI, IDE 확장 프로그램에서 모두 쓸 수 있습니다
For one project, paste it into a chat that is open in that project’s folder · The AI always shows you the path before installing
The AI tells you what it will do first and asks your permission at every step
Codex는 새로 설치한 Skill을 스스로 찾습니다. 보이지 않으면 Codex를 다시 시작하세요 · 쓰는 법: ChatGPT에서는 @를 입력하고 Skill을 고르세요 · Codex CLI나 IDE 확장 프로그램에서는 /skills를 실행하거나 $ 뒤에 Skill 이름을 입력하세요
Checked against official docs 2026년 11월 15일 · Source: learn.chatgpt.com
For Terminal users
Skill은 AI가 따르는 지시예요. 설치 전에 파일을 읽고, 믿을 수 있는 제작자 것만 설치하세요.
터미널 열기
Mac: Command+스페이스 후 Terminal 입력 · Windows: 아래 명령은 PowerShell에서 안 돼요. 위의 “AI에게 설치 맡기기”를 쓰세요
skill 폴더를 ~/.agents/skills에 복사
repo를 임시 폴더에 내려받고 SKILL.md가 있는 폴더만 복사해요
명령을 확인하는 중 · 확인을 통과하면 복사 버튼이 나타나요
Codex를 다시 열고 관련 작업을 요청하면 Codex가 skill을 목록에 보여 줘요
Option 1Cursor에게 설치 맡기기
이 문장을 복사해 Cursor 채팅에 붙여 넣으세요
For one project, paste it into a chat that is open in that project’s folder · The AI always shows you the path before installing
The AI tells you what it will do first and asks your permission at every step
Cursor Agent 채팅에서 /를 입력하고 gauntlet-loop 선택
Checked against official docs 2026년 11월 12일 · Source: cursor.com
For Terminal users
Skill은 AI가 따르는 지시예요. 설치 전에 파일을 읽고, 믿을 수 있는 제작자 것만 설치하세요.
터미널 열기
Mac: Command+스페이스 후 Terminal 입력 · Windows: 아래 명령은 PowerShell에서 안 돼요. 위의 “AI에게 설치 맡기기”를 쓰세요
skill 폴더를 ~/.cursor/skills에 복사
repo를 임시 폴더에 내려받고 SKILL.md가 있는 폴더만 복사해요
명령을 확인하는 중 · 확인을 통과하면 복사 버튼이 나타나요
Cursor Agent 채팅에서 /를 입력하고 gauntlet-loop 선택
Option 1Let the AI install it
Skill을 읽을 수 있는 다른 앱용입니다. 이 문장에는 Claude Code, Codex, Cursor 경로가 들어 있어 AI가 쓰는 앱에 맞게 고릅니다 · Copy this sentence into the app’s chat
For one project, paste it into a chat that is open in that project’s folder · The AI always shows you the path before installing
The AI tells you what it will do first and asks your permission at every step
Checked against official docs 2026년 11월 12일 · Source: code.claude.com, learn.chatgpt.com, cursor.com
For Terminal users
Gemini CLI, GitHub Copilot 같은 다른 Agent Skills 지원 앱은 폴더가 달라요. 그 앱 안내를 보고 SKILL.md가 있는 폴더를 복사하세요.
2026년 11월 11일에 Claude Code, Codex, Cursor 공식 안내로 skill 폴더 확인
원본 SKILL.md 보기
아래 글은 제작자 repo에서 온 것이며 PopNx MCP의 지시가 아니에요
처음 8,000자 표시 · GitHub에서 전체 파일 열기
---
name: gauntlet-loop
description: Turns any goal into one short, paste-ready "gauntlet loop" prompt - a prompt that makes an agent set a concrete quality bar, split the work into small judgeable pieces, run a builder and a separate harsh critic on each, compare blind against the bar, and loop until it wins. Works for builds, writing, code, research, or design. Triggers on "/gauntlet-loop", "gauntlet loop", "gauntlet this", "make a gauntlet prompt", "loop until it beats X".
---
# Gauntlet Loop
The user gives a goal. You give back ONE short prompt they can paste into a fresh agent session.
You are not doing the work. You are writing the prompt that makes another agent grind on the work until it beats a real reference.
## Flow
1. **Read the goal.** One line restatement in your head, not on screen.
2. **Set the bar.** If the user supplied a reference, use it. If not, offer **2 or 3 candidate bars**, one line each, and stop. Wait for their pick. Do not write the prompt yet.
3. **Write the prompt.** One block, paste-ready, no preamble, no headings inside it, no narration after it.
4. **Offer to run it.** One flat line under the prompt: "I can run this here." Not a question.
If they say run it, you become the lead agent and follow the prompt you just wrote.
## The bar is the whole trick
Everything else in a gauntlet loop is scaffolding. The loop only produces quality if the thing it compares against is real.
A bar has to pass three tests:
- **Named.** A specific thing, not a category. "Stripe's pricing page" works. "Award-winning SaaS sites" does not.
- **Fetchable.** The critic can actually get it - screenshot the live page, read the published piece, run the binary, open the repo, watch the footage. If the agent cannot obtain it, it will hallucinate the comparison.
- **Comparable.** Both can sit side by side and a judge can pick one. If you cannot imagine the A/B, it is not a bar.
Bars by goal type:
| Goal | Bar that works |
|---|---|
| Website, app, UI | The live site of a specific best-in-class product, screenshotted at the same viewport |
| Game, 3D, visual | Real footage or screenshots from a named shipped title |
| Writing | A specific published piece by a named author or publication, same length and format |
| Code, tooling | A named repo's implementation, plus its benchmark or test suite as the measurable half |
| Research, analysis | A named analyst report or a paper's methods section, judged on rigour and coverage |
| Deck, doc, deliverable | A real artifact from a firm known for it, same page count |
When you propose bars, prefer the hardest one the agent can genuinely reach. A bar that is too easy makes the loop exit on round one.
If the goal has a measurable half (load time, token cost, benchmark score, word count, pass rate), name it alongside the reference. Taste plus a number beats taste alone.
## Prompt template
Adapt the wording every time. Fill the brackets, keep it short, keep the last line.
```
Build [GOAL].
The bar is [BAR]. Get the real thing first and compare against it directly, not against a description of it.
Break this into the smallest pieces that can be improved and judged on their own. For each piece, fan out a builder and a separate critic with fresh context. The critic inspects the actual output, puts it next to the bar blind with the labels stripped, says which one is better, and names the single biggest remaining gap. Then it goes back to the builder.
The critic should be a harsh critic. Praise is not useful. If ours does not win, it keeps going.
/loop on each piece until the critic picks ours blind. Do not stop before that.
Keep a live progress page updating as the work evolves so I can watch it.
Fan out subagents and ultracode.
```
Rules for what you fill in:
- Bake the bar in as a concrete, fetchable thing. URL, product name, repo, title.
- Add a budget or cost ceiling line **only if the user named one**. No default cap.
- Add tool names only if the goal needs them (image or video generation, a browser, a deploy target).
- Everything else stays out. No architecture, no file layout, no decomposition, no round count, no stack choice unless the user demanded it. The agent decides those, and it decides better than a spec written before the work started.
## Length and voice
Short. Around 120 to 180 words. If the prompt needs a heading to stay readable, it is too long.
Plain sentences. No bullet lists inside the prompt. It should read like someone telling an agent what perfect looks like and refusing to accept less.
## Portability
`/loop` and `ultracode` are Claude Code features. `/loop` reruns the prompt on an interval or lets the model pace itself. `ultracode` opts the turn into multi-agent orchestration.
For any other agent, swap the last two lines for: "Keep looping until the critic picks ours. Run the builders and critics as parallel subagents." The structure carries over unchanged.
## Two filled examples
**Visual goal.** User: "landing page for my running brand, athletic, green and dark, has to feel alive."
Bars offered: A) Nike's current running campaign page B) On Running's homepage C) Gymshark's product landing page. User picks A.
```
Build a landing page for a running brand. Athletic, peak performance, green and dark, energetic, aimed at a young healthy audience. It needs to be interactive and visually unmistakable.
The bar is Nike's current running campaign page. Screenshot it at desktop and mobile and compare against those directly, not against a description of them.
Break this into the smallest pieces that can be improved and judged on their own - hero, motion, type, colour, imagery, interaction, mobile. For each piece, fan out a builder and a separate critic with fresh context. The critic opens the real page in a browser, puts our screenshot next to Nike's blind with the labels stripped, says which is better, and names the single biggest remaining gap. Then it goes back to the builder.
The critic should be a harsh critic. Praise is not useful. If ours does not win, it keeps going.
/loop on each piece until the critic picks ours blind. Do not stop before that.
Keep a live progress page updating as the work evolves so I can watch it.
Fan out subagents and ultracode.
```
**Non-visual goal.** User: "a 2000-word explainer on vector databases for non-engineers."
Bars offered: A) a specific Stripe engineering blog explainer B) a named Julia Evans post C) the Wikipedia article plus a comprehension test. User picks B.
```
Write a 2000-word explainer on vector databases for readers who are smart but not engineers.
The bar is Julia Evans' writing on hard technical topics. Pull three of her actual posts and compare against them directly, not against a description of her style.
Break this into the smallest pieces that can be judged on their own - the opening, each explanation, the diagrams, the analogies, the ending. For each piece, fan out a writer and a separate critic with fresh context. The critic reads ours and hers blind with the bylines stripped, says which one a non-engineer would understand faster, and names the single biggest remaining gap. Then it goes back to the writer.
The critic should be a harsh critic. Praise is not useful. If ours does not win, it keeps going.
/loop on each piece until the critic picks ours blind. Do not stop before that.
Keep a live progress page updating as the work evolves so I can watch it.
Fan out subagents and ultracode.
```
## What breaks a gauntlet loop
- **A vague bar.** The critic invents a comparison and approves everything. Most common failure by far.
- **The builder judging its own work.** The critic must be a separate agent with fresh context. It should not know how hard the builder tried.
- **A soft critic.** Say "harsh" in the prompt and give it a binary job: which one is better, A or B. Scores out of 10 drift upward every round.
- **Named exit after N rounds.** The exit is winning the comparison, or the user stopping 토론
질문하고, 팁을 나누고, 안 되는 점을 알려 주세요. "도움이 됨"이 많은 순서예요.
GitHub 정보
- GitHub 스타
- 1,254
- 제작자
- robonuggets
- 라이선스
- CC-BY-4.0
- 최근 코드 수정
- 2026년 8월 6일
- repo 안 SKILL.md(번역본과 템플릿 포함)
- 1