Writing Livekit Scenarios
livekit-examples/agent-starter-python
Creates and maintains the scenarios a LiveKit agent simulation runs, and wires the agent to consume them.
Use LLM as a simulator of expert debates and opposing viewpoints instead of getting a single sycophantic answer.
Install Karpathy LLM Simulator
$ npx skills add LearnPrompt/andrej-karpathy-skills --skill karpathy-llm-simulator -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install LearnPrompt/andrej-karpathy-skills karpathy-llm-simulator --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/LearnPrompt/andrej-karpathy-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/karpathy-llm-simulator .claude/skills/karpathy-llm-simulator && 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 "karpathy-llm-simulator" agent skill from https://github.com/LearnPrompt/andrej-karpathy-skills/tree/main/karpathy-llm-simulator into .claude/skills/karpathy-llm-simulator/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "karpathy-llm-simulator", 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/LearnPrompt/andrej-karpathy-skills/tree/main/karpathy-llm-simulatorType 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 LearnPrompt/andrej-karpathy-skills --skill karpathy-llm-simulator -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install LearnPrompt/andrej-karpathy-skills karpathy-llm-simulator --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/LearnPrompt/andrej-karpathy-skills.git skills-src && mkdir -p .agents/skills && cp -r skills-src/karpathy-llm-simulator .agents/skills/karpathy-llm-simulator && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "karpathy-llm-simulator" agent skill from https://github.com/LearnPrompt/andrej-karpathy-skills/tree/main/karpathy-llm-simulator into .agents/skills/karpathy-llm-simulator/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "karpathy-llm-simulator", 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 LearnPrompt/andrej-karpathy-skills --skill karpathy-llm-simulator -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install LearnPrompt/andrej-karpathy-skills karpathy-llm-simulator --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/LearnPrompt/andrej-karpathy-skills.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/karpathy-llm-simulator .cursor/skills/karpathy-llm-simulator && 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 "karpathy-llm-simulator" agent skill from https://github.com/LearnPrompt/andrej-karpathy-skills/tree/main/karpathy-llm-simulator into .cursor/skills/karpathy-llm-simulator/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "karpathy-llm-simulator", 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/LearnPrompt/andrej-karpathy-skills.git --path karpathy-llm-simulator--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 LearnPrompt/andrej-karpathy-skills --skill karpathy-llm-simulator -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install LearnPrompt/andrej-karpathy-skills karpathy-llm-simulator --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/LearnPrompt/andrej-karpathy-skills.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/karpathy-llm-simulator .gemini/skills/karpathy-llm-simulator && 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 "karpathy-llm-simulator" agent skill from https://github.com/LearnPrompt/andrej-karpathy-skills/tree/main/karpathy-llm-simulator into .gemini/skills/karpathy-llm-simulator/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "karpathy-llm-simulator", 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 LearnPrompt/andrej-karpathy-skills karpathy-llm-simulatorInstalls 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 LearnPrompt/andrej-karpathy-skills --skill karpathy-llm-simulator -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/LearnPrompt/andrej-karpathy-skills.git skills-src && mkdir -p .github/skills && cp -r skills-src/karpathy-llm-simulator .github/skills/karpathy-llm-simulator && 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 "karpathy-llm-simulator" agent skill from https://github.com/LearnPrompt/andrej-karpathy-skills/tree/main/karpathy-llm-simulator into .github/skills/karpathy-llm-simulator/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "karpathy-llm-simulator", 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 LearnPrompt/andrej-karpathy-skills --skill karpathy-llm-simulator -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install LearnPrompt/andrej-karpathy-skills karpathy-llm-simulator --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/LearnPrompt/andrej-karpathy-skills.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/karpathy-llm-simulator .opencode/skills/karpathy-llm-simulator && 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 "karpathy-llm-simulator" agent skill from https://github.com/LearnPrompt/andrej-karpathy-skills/tree/main/karpathy-llm-simulator into .opencode/skills/karpathy-llm-simulator/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "karpathy-llm-simulator", 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
karpathy-llm-simulator- GitHub stars
- 110
- Token cost
- ~1.3k tokens
- SKILL.md length
- 258 words
- Files
- 1
- Skills in repo
- 15
- Repo updated
- First seen
- Licence
- MIT
At a glance
Use LLM as a simulator of expert debates and opposing viewpoints instead of getting a single sycophantic answer.
- The user needs to make an important decision
- SKILL.md covers Core Principle, The 4 Simulator Modes, Anti-Sycophancy Patterns and Decision Framework, plus 4 more sections
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
- Wants to stress-test an idea
What it does
Karpathy LLM Simulator is an agent skill from LearnPrompt/andrej-karpathy-skills. Use LLM as a simulator of expert debates and opposing viewpoints instead of getting a single sycophantic answer. Use this skill when the user needs to make an important decision, wants to stress-test an idea, needs devil's advocate analysis, wants to avoid confirmation bias, or says "argue against this", "what are the counterarguments", "simulate experts", "debate this", "challenge my thinking". Based on Karpathy 31k-like post.
Its SKILL.md is about 1.3k 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 Testing & QA, covering Load testing. The repository describes itself as: Karpathy-inspired Agent Skills collection. The licence is MIT.
When your agent uses it
- The user needs to make an important decision
- Wants to stress-test an idea
- Needs devils advocate analysis
- Wants to avoid confirmation bias
Example prompts
- “s advocate analysis, wants to avoid confirmation bias, or says”
- “what are the counterarguments”
- “simulate experts”
- “/karpathy-llm-simulator”
What it can do on your machine
Read from SKILL.md and the folder at commit 9e46dec. 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):
x.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
Karpathy LLM Simulator loads about 1.3k tokens when it runs. Until then it costs about 114 tokens; SKILL.md has 258 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 LearnPrompt/andrej-karpathy-skills at commit 9e46dec, republished under its MIT licence (© LearnPrompt). 258 words, ~1,300 tokens.
Download SKILL.mdSave it as
.claude/skills/karpathy-llm-simulator/SKILL.md (or your agent's skills folder).- name
- karpathy-llm-simulator
- description
- Use LLM as a simulator of expert debates and opposing viewpoints instead of getting a single sycophantic answer. Use this skill when the user needs to make an important decision, wants to stress-test an idea, needs devil's advocate analysis, wants to avoid confirmation bias, or says "argue against this", "what are the counterarguments", "simulate experts", "debate this", "challenge my thinking". Based on Karpathy 31k-like post.
- disable-model-invocation
- false
- user-invocable
- true
- related_skills
- karpathy-understanding-first, karpathy-system-prompt-learning, karpathy-meta-reflection
Skill 3: LLM as Simulator（LLM模拟器思维）
Source: https://x.com/karpathy/status/2037921699824607591 | https://x.com/karpathy/status/2049907410303865030 "Drafted a blog post → LLM argue the opposite" — 31k likes
Core Principle
Don't ask what the LLM thinks. Ask it to simulate what a diverse group of experts would argue.
LLMs are trained to please. A direct question gets a sycophantic answer. A simulation request gets a distribution of real perspectives — including the uncomfortable ones.
Karpathy's method: write a draft → ask LLM to argue the strongest possible opposite position → synthesize a better view.
The 4 Simulator Modes
Mode 1: Expert Debate Panel
Best for: technical decisions, architecture choices, research directions
Simulate a structured debate between these 3 expert personas on [TOPIC/DECISION]:
Expert A: [most optimistic / pro position]
Expert B: [most skeptical / con position]
Expert C: [pragmatic outsider / unexpected angle]
For each expert:
- State their core argument in 3 sentences
- Cite 2 specific examples or data points they'd use
- Identify what they'd say is the FATAL FLAW in the opposing view
After the debate, synthesize: what's the strongest hybrid position that survives all three critiques?
Topic: [YOUR_TOPIC]
My current position: [YOUR_DRAFT_VIEW]Mode 2: Steel Man the Opposite
Best for: before publishing, before committing to a decision
I'm about to [ACTION / PUBLISH / DECIDE]:
[YOUR PLAN OR DRAFT]
Steel man the strongest possible argument AGAINST this. Be merciless.
Don't hedge. Don't say "while this has merit...".
Argue as if you genuinely believe the opposite and need to convince a skeptical expert.
Then: what would it take to make my original position survive this attack?Mode 3: Pre-Mortem Simulation
Best for: project planning, product launches, major decisions
Imagine it's [DATE 6 MONTHS FROM NOW] and [YOUR PROJECT/PLAN] has failed completely.
Simulate 3 different failure modes — each from a different root cause:
1. Technical failure: what went wrong in the implementation?
2. Strategic failure: what assumption proved wrong?
3. Execution failure: what human/process error occurred?
For each: describe the specific sequence of events that led to failure.
Then: what early warning signals would have been visible by [DATE 1 MONTH FROM NOW]?Mode 4: Socratic Drill
Best for: testing your own understanding of a concept
I believe I understand [CONCEPT].
Ask me 5 increasingly hard Socratic questions to test my understanding.
After each answer I give, probe a potential gap or inconsistency.
At the end, grade my understanding on a scale of 1-10 and identify my biggest blind spot.
Start with question 1.Anti-Sycophancy Patterns
Always add one of these to prevent the LLM from capitulating to your framing:
"Do not soften your critique because you think I want to hear it.""If my position is clearly wrong, say so directly.""Ignore that I wrote the original draft — evaluate it as an anonymous submission.""Your job is to find the fatal flaw, not to validate."
Decision Framework
Before any major decision:
1. Write down your current position (1-2 paragraphs)
2. Run Mode 2 (Steel Man the Opposite)
3. Update your position based on the strongest critique
4. Run Mode 1 (Expert Debate) to get broader perspective
5. Make the decision — now you've genuinely stress-tested it
Total time: 15-20 minutes. Quality of decision: dramatically better.When NOT to Use This
- For factual lookups (just ask directly)
- For code generation (use agentic engineering instead)
- When you've already decided and need to execute (move forward, don't ruminate)
Workflow
属于工作流：反偏见决策（任何重要判断）
| 位置 | 上游 | 下游 |
|---|---|---|
| 入口 | 用户面临重要决策时直接触发 | karpathy-understanding-first（验证自己是否真正理解） |
完整链路：llm-simulator → understanding-first → system-prompt-learning
也在月度体检工作流中用于 stress-test 月度结论。
Prompt Contract
Simulate a structured debate between 3-5 expert personas with conflicting incentives on <DECISION/TOPIC>. Each persona must: state their core argument, cite specific evidence, identify the fatal flaw in opposing views. After the debate, synthesize the strongest hybrid position that survives all critiques. End with: key assumptions I must verify myself.Verification Checklist
- 至少有 3 个角色，且利益/立场互相冲突
- 每个角色都给出了具体论据（不是泛泛而谈）
- 每个角色都指出了对方的致命缺陷
- 综合结论经受住了所有角色的攻击
- 列出了「我必须亲自验证」的假设清单
- 没有出现讨好用户原始立场的倾向
© LearnPrompt, 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 karpathy-llm-simulator of LearnPrompt/andrej-karpathy-skills.
Open the folder on GitHubat commit 9e46dec
Compare with similar skills
Karpathy LLM Simulator 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 |
|---|---|---|---|---|---|---|
| Karpathy LLM Simulator this skillLearnPrompt/andrej-karpathy-skills | 110 | — | ~1.3k | Automated safety check: Pass | MIT | |
| Writing Livekit Scenarioslivekit-examples/agent-starter-python | 264 | 1 repos | ~2.5k | Automated safety check: Pass | MIT | |
| Go Testingcxuu/golang-skills | 173 | 1 repos | ~1.3k | Automated safety check: Pass | Apache-2.0 | |
| Goalcraftgrp06/goalcraft | 102 | — | ~3.8k | Automated safety check: Pass | MIT | |
| Thinking Partnermattnowdev/thinking-partner | 206 | — | ~4.4k | Automated safety check: Pass | MIT | |
| Visionkunchenguid/vision | 331 | — | ~2.9k | Automated safety check: Pass | MIT |
Similar skills
Go Testing
cxuu/golang-skills
A skill your agent uses when writing, reviewing, or improving Go test code — including table-driven tests, subtests, parallel tests, test helpers, test doubles, and assertions with cmp.Diff.
Goalcraft
grp06/goalcraft
Turn a rough draft, vague ambition, or messy task brief into a powerful Codex /goal objective for persistent, evidence-checked work.
Thinking Partner
mattnowdev/thinking-partner
A deterministic thinking partner that challenges assumptions and applies mental models to sharpen decisions, solve problems, and think more clearly.
Vision
kunchenguid/vision
Draft and stress-test a VISION.md for a repository, then iterate with the author on an interactive review board until approved.
Volt Load Testing
owenHochwald/volt
Safely exercise and evaluate HTTP APIs with the Volt CLI, including authenticated requests, JSON bodies, staged load, machine-readable results, performance baselines, and before/after comparisons.
More from LearnPrompt/andrej-karpathy-skills
All 15 skills in this repoKarpathy Methodology Index
LearnPrompt/andrej-karpathy-skills
Apply Andrej Karpathy AI methodology and principles from his 2023-2026 insights. Use this skill when the user wants to apply Karpathy-style thinking, needs…
Karpathy Agentic Engineering
LearnPrompt/andrej-karpathy-skills
Apply Karpathy-style agentic engineering to any coding or building task.
AutoResearch Loop
LearnPrompt/andrej-karpathy-skills
Sets up an autonomous research loop where an agent runs experiments on git branches, logs results and proposes the next iteration while you approve each hypothesis change.
Karpathy Education First
LearnPrompt/andrej-karpathy-skills
Apply the education-first mindset — make everything you build teachable, create nano-project explanations, write for beginners.
Karpathy Idea Files
LearnPrompt/andrej-karpathy-skills
Create and share ideas as abstract Gist-style specs instead of code — letting agents or others implement.
Karpathy LLM Wiki
LearnPrompt/andrej-karpathy-skills
Build and maintain an LLM-powered personal knowledge base or wiki.
Related
Categories
Questions about Karpathy LLM Simulator
What does Karpathy LLM Simulator do?
Use LLM as a simulator of expert debates and opposing viewpoints instead of getting a single sycophantic answer. Karpathy LLM Simulator is an agent skill from LearnPrompt/andrej-karpathy-skills. Use LLM as a simulator of expert debates and opposing viewpoints instead of getting a single sycophantic answer.
When should I use Karpathy LLM Simulator?
Karpathy LLM Simulator fits situations like: the user needs to make an important decision; wants to stress-test an idea; needs devils advocate analysis; wants to avoid confirmation bias.
How do I install Karpathy LLM Simulator in Claude Code?
Run `npx skills add LearnPrompt/andrej-karpathy-skills --skill karpathy-llm-simulator -a claude-code`. Or copy the skill folder (karpathy-llm-simulator in LearnPrompt/andrej-karpathy-skills) into .claude/skills/karpathy-llm-simulator in your project. Claude Code loads it when a task matches its description.
How do I install Karpathy LLM Simulator in Codex?
Run `npx skills add LearnPrompt/andrej-karpathy-skills --skill karpathy-llm-simulator -a codex`. Or copy the skill folder (karpathy-llm-simulator in LearnPrompt/andrej-karpathy-skills) into .agents/skills/karpathy-llm-simulator in your project. Codex loads it when a task matches its description.
Can I use Karpathy LLM Simulator 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 LearnPrompt/andrej-karpathy-skills --skill karpathy-llm-simulator -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/karpathy-llm-simulator, .gemini/skills/karpathy-llm-simulator, .github/skills/karpathy-llm-simulator and .opencode/skills/karpathy-llm-simulator in your project.
What does Karpathy LLM Simulator need to run?
SKILL.md names no scripts, command-line tools or credentials: Karpathy LLM Simulator is instructions for the agent only.
Does Karpathy LLM Simulator access the network?
SKILL.md names 1 domain. As links in the text: x.com. This is read from the text; nothing was executed.
Is Karpathy LLM Simulator 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 Karpathy LLM Simulator use?
Karpathy LLM Simulator 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 Karpathy LLM Simulator use?
About 1.3k tokens (SKILL.md is roughly 5.2k 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 Karpathy LLM Simulator?
Skills that share tags, products or a category with Karpathy LLM Simulator: Writing Livekit Scenarios (livekit-examples/agent-starter-python, 264 stars), Go Testing (cxuu/golang-skills, 173 stars), Goalcraft (grp06/goalcraft, 102 stars) and Thinking Partner (mattnowdev/thinking-partner, 206 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Karpathy LLM Simulator?
LearnPrompt (a GitHub user) maintains it in LearnPrompt/andrej-karpathy-skills, which has 110 GitHub stars. The repository holds 15 skills in this directory. The repository was last updated on July 10, 2026.
Source: LearnPrompt/andrej-karpathy-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.