Agent skill

Karpathy Meta Reflection

by LearnPrompt in LearnPrompt/andrej-karpathy-skills

Run a structured reflection on how AI is reshaping your skills, career, and leverage.

MITAuto-check passed

Install Karpathy Meta Reflection

skills CLI
$ npx skills add LearnPrompt/andrej-karpathy-skills --skill karpathy-meta-reflection -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install LearnPrompt/andrej-karpathy-skills karpathy-meta-reflection --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/LearnPrompt/andrej-karpathy-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/karpathy-meta-reflection .claude/skills/karpathy-meta-reflection && rm -rf skills-src

Use ~/.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/

Facts

Skill name
karpathy-meta-reflection
GitHub stars
110
Token cost
~1.5k tokens
SKILL.md length
184 words
Files
1
Skills in repo
15
Repo updated
First seen
Licence
MIT

At a glance

Run a structured reflection on how AI is reshaping your skills, career, and leverage.

  • Works in 3 steps: What skills are atrophying (AI is taking… → What's exploding (new leverage you… → What's your real job now (has the role…
  • Monthly career audits
  • SKILL.md covers Core Principle, Monthly Career Audit Prompt, The Atrophy/Leverage Matrix and The Role Redefinition Prompt, plus 6 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Karpathy Meta Reflection is an agent skill from LearnPrompt/andrej-karpathy-skills. Run a structured reflection on how AI is reshaping your skills, career, and leverage. Use this skill for monthly career audits, skill atrophy reviews, understanding what's worth learning vs delegating to AI, or when the user says "career audit", "skills review", "what should I learn", "am I becoming obsolete", "AI impact on my work", "leverage review", "meta reflection". Based on Karpathy 56k-like programmer identity post.

Its SKILL.md is about 1.5k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

The repository describes itself as: Karpathy-inspired Agent Skills collection. The licence is MIT.

When your agent uses it

  • Monthly career audits
  • Skill atrophy reviews
  • Understanding whats worth learning vs delegating to AI
  • The user says career audit

Example prompts

  • “s worth learning vs delegating to AI, or when the user says”
  • “skills review”
  • “what should I learn”
  • “/karpathy-meta-reflection”

Workflow steps

3 steps, taken from the first numbered list in SKILL.md.

  1. What skills are atrophying (AI is taking over, for better or worse)
  2. What's exploding (new leverage you didn't have before)
  3. What's your real job now (has the role description changed under your feet?)

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 Meta Reflection loads about 1.5k tokens when it runs. Until then it costs about 113 tokens; SKILL.md has 184 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~113
When it runs · the whole SKILL.md, loaded when a task matches
~1.5k

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). 184 words, ~1,535 tokens.

Download SKILL.mdSave it as .claude/skills/karpathy-meta-reflection/SKILL.md (or your agent's skills folder).
name
karpathy-meta-reflection
description
Run a structured reflection on how AI is reshaping your skills, career, and leverage. Use this skill for monthly career audits, skill atrophy reviews, understanding what's worth learning vs delegating to AI, or when the user says "career audit", "skills review", "what should I learn", "am I becoming obsolete", "AI impact on my work", "leverage review", "meta reflection". Based on Karpathy 56k-like programmer identity post.
disable-model-invocation
false
user-invocable
true
related_skills
karpathy-understanding-first, karpathy-practice-environments, karpathy-education-first, karpathy-system-prompt-learning

Skill 10: Meta-Reflection(元反思)

Source: https://x.com/karpathy/status/2004607146781278521 | https://x.com/karpathy/status/2015883857489522876 "I've never felt this much behind as a programmer" — 56k likes

Core Principle

The landscape is shifting faster than your intuition updates. Deliberate reflection is how you stay calibrated.

Karpathy tracks three things relentlessly:

  1. What skills are atrophying (AI is taking over, for better or worse)
  2. What's exploding (new leverage you didn't have before)
  3. What's your real job now (has the role description changed under your feet?)

Monthly Career Audit Prompt

Run this once a month, 20-30 minutes:

Monthly AI Impact Audit — [MONTH YEAR]

My role/field: [YOUR JOB OR DOMAIN]

Part 1: ATROPHYING SKILLS
Things I've been having AI do in the last month:
[LIST 5-10 TASKS YOU DELEGATED TO AI]

For each, analyze:
- How much would it hurt if AI wasn't available for this?
- Is my ability to do this manually getting worse?
- Is that acceptable? (YES = commodity skill / NO = must maintain)

Part 2: EXPLODING LEVERAGE
New things I can now do (or do much faster) because of AI:
[LIST 3-5 NEW CAPABILITIES OR SPEED MULTIPLIERS]

For each: what specifically unlocked this? What should I double down on?

Part 3: ROLE REDEFINITION
Complete this: "In 2023, my job was to [X]. In [CURRENT YEAR], my job is actually to [Y]."

Part 4: NEXT MONTH FOCUS
1. One skill I will DELIBERATELY practice without AI:
2. One new AI capability I will DELIBERATELY learn:
3. One thing I will STOP doing manually because AI is better:

The Atrophy/Leverage Matrix

For any skill you have, plot it on this 2x2:

                    HIGH LEVERAGE WITH AI
                           │
    MUST RETAIN            │      MAXIMIZE
    (ai makes it faster    │      (your competitive
     but you need the      │      edge lives here)
     judgment)             │
                           │
HIGH ──────────────────────┼────────────────────── LOW
ATROPHY                    │                      ATROPHY
                           │
    SAFELY DELEGATE        │      ABANDON/AUTOMATE
    (commodity, ai is      │      (low value, losing
     better, let it go)    │      it doesn't matter)
                           │
                    LOW LEVERAGE WITH AI

The Role Redefinition Prompt

Every 6 months, do this deep reflection:

Help me understand how my role has evolved.

My job title/domain: [ROLE]
Experience: [YEARS]

Before AI tools (2022 and earlier), my core value was:
[WHAT YOU WERE HIRED/VALUED FOR]

Today, with current AI tools:
1. What percentage of my old tasks can AI now do at 80%+ quality?
2. What tasks have INCREASED in value because AI can't do them (judgment, relationships, taste, ethics)?
3. What new tasks exist now that didn't exist 2 years ago?
4. If I were hiring for my own role today, what would the job description say?
5. What would I tell my 2022 self about what skills to prioritize?

Be specific. Name actual tasks, not abstract concepts.

Tracking the Phase Shift

Karpathy described 2025 as a "phase shift" — not incremental improvement but a different mode. This prompt helps you notice phase shifts in your own domain:

Diagnose if my field/work has hit a phase shift.

Domain: [YOUR FIELD]
Recent changes I've noticed: [LIST 3-5 CHANGES IN HOW WORK IS DONE]

Is this:
A) Incremental improvement (same work, faster tools)
B) Role shift (different emphasis within same field)  
C) Phase shift (fundamentally different mode of working)
D) Field transformation (new field is emerging from the old one)

Evidence for your diagnosis. And: what does this mean for where I should invest my time in the next 12 months?

Weekly 5-Minute Check-In

Lighter version for weekly cadence:

Quick weekly AI reflection — [DATE]

3 things AI helped me do better this week:
1.
2.
3.

1 thing I learned from reviewing AI output:

1 skill I exercised without AI:

One thing I want to pay more attention to next week:

The "Karpathy Test" for Any Skill

Before investing time learning something, ask:

Should I learn [SKILL] deeply in the current AI landscape?

Evaluate:
1. Can current LLMs do this at 80%+ quality? (yes/no)
2. Is human judgment still required for the 20% that matters? (yes/no)
3. Does understanding this deeply make me better at directing AI to do it? (yes/no)
4. Is this skill a prerequisite for judgment that AI can't replicate? (yes/no)

Recommendation: LEARN_DEEPLY / LEARN_BASICS / DELEGATE / SKIP
Reasoning: [2-3 sentences]

Workflow

属于工作流:月度体检(入口)

位置上游下游
入口每月定期触发 / 用户感到焦虑时karpathy-understanding-first(定位理解力盲区)

完整链路:meta-reflection → understanding-first → practice-environments → education-first

Prompt Contract

text
Run a monthly career atrophy audit. Step 1: List my completed tasks this month (I'll provide or you pull from context). Step 2: For each, mark if I delegated to AI and the atrophy risk level. Step 3: Identify my top 3 leverage points (where AI made me 10x). Step 4: Identify my top 2 atrophy risks (skills degrading). Step 5: Recommend one thing to practice next month and one thing to fully delegate. Output as a structured report.

Verification Checklist

  • 任务清单来自实际工作(不是假设)
  • 萎缩风险有具体证据(不是泛泛焦虑)
  • 杠杆点有量化感知(「快了多少」)
  • 下月练习计划具体到可执行(不是「多学习」)
  • 下月委托计划明确到什么任务完全交给 AI
  • 报告可以月月对比追踪变化趋势

© 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-meta-reflection of LearnPrompt/andrej-karpathy-skills.

Open the folder on GitHubat commit 9e46dec

Compare with similar skills

Karpathy Meta Reflection 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.

Karpathy Meta Reflection compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Karpathy Meta Reflection this skillLearnPrompt/andrej-karpathy-skills110—~1.5kAutomated safety check: PassMIT
MCP Server Builderanthropics/skills180k63 repos~2.3kAutomated safety check: PassApache-2.0
Vercel Composition Patternssupabase/supabase111k58 repos~726Automated safety check: PassMIT
Finishing a Development Branchobra/superpowers297k5 repos~1.9kAutomated safety check: PassMIT
Agent Browser CLIvercel-labs/agent-browser44k24 repos~864Automated safety check: PassApache-2.0
Hook Development for Claude Code Pluginsanthropics/claude-plugins-official38k10 repos~4.1kAutomated safety check: NotesApache-2.0

Similar skills

  • MCP Server Builder

    anthropics/skills

    Official

    Guides the design and implementation of Model Context Protocol servers in TypeScript or Python, from tool naming and error messages to evaluation.

    180k GitHub starsUsed in 63 repos~2.3k tokens
    Agent WorkflowsAuto-check passed
  • Official

    React composition patterns that scale. An agent skill from supabase/supabase.

    111k GitHub starsUsed in 58 repos~726 tokens
    DevelopmentAuto-check passed
  • Walks the last step of a branch: confirm tests pass, detect the git environment, ask how to integrate, carry out your choice and clean up the worktree.

    297k GitHub starsUsed in 5 repos~1.9k tokens
    DevelopmentAuto-check passed
  • Agent Browser CLI

    vercel-labs/agent-browser

    Official

    Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking…

    44k GitHub starsUsed in 24 repos~864 tokens
    Productivity & AutomationAuto-check passed
  • Hook Development for Claude Code Plugins

    anthropics/claude-plugins-official

    Official

    Explains how to write Claude Code plugin hooks, both prompt-based checks and bash commands, for events such as PreToolUse, Stop and SessionStart.

    38k GitHub starsUsed in 10 repos~4.1k tokens
    Agent WorkflowsAuto-check: notes
  • Typescript Advanced Types

    rolling-scopes/rsschool-app

    Master TypeScript's advanced type system including generics, conditional types, mapped types, template literals, and utility types for building type-safe applications.

    10k GitHub starsUsed in 25 repos~4.2k tokens
    DevelopmentAuto-check passed

More from LearnPrompt/andrej-karpathy-skills

All 15 skills in this repo
  • Karpathy 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…

    110 GitHub stars~1.5k tokensUpdated 3 mo ago
    Auto-check passed
  • Karpathy Agentic Engineering

    LearnPrompt/andrej-karpathy-skills

    Apply Karpathy-style agentic engineering to any coding or building task.

    110 GitHub stars~1.2k tokensUpdated 3 mo ago
    Auto-check passed
  • 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.

    110 GitHub stars~1.4k tokensUpdated 3 mo ago
    Auto-check passed
  • Karpathy Education First

    LearnPrompt/andrej-karpathy-skills

    Apply the education-first mindset — make everything you build teachable, create nano-project explanations, write for beginners.

    110 GitHub stars~1.8k tokensUpdated 3 mo ago
    Auto-check passed
  • Karpathy Idea Files

    LearnPrompt/andrej-karpathy-skills

    Create and share ideas as abstract Gist-style specs instead of code — letting agents or others implement.

    110 GitHub stars~1.5k tokensUpdated 3 mo ago
    Auto-check passed
  • Karpathy LLM Simulator

    LearnPrompt/andrej-karpathy-skills

    Use LLM as a simulator of expert debates and opposing viewpoints instead of getting a single sycophantic answer.

    110 GitHub stars~1.3k tokensUpdated 3 mo ago
    Auto-check passed

Questions about Karpathy Meta Reflection

What does Karpathy Meta Reflection do?

Run a structured reflection on how AI is reshaping your skills, career, and leverage. Karpathy Meta Reflection is an agent skill from LearnPrompt/andrej-karpathy-skills. Run a structured reflection on how AI is reshaping your skills, career, and leverage.

When should I use Karpathy Meta Reflection?

Karpathy Meta Reflection fits situations like: monthly career audits; skill atrophy reviews; understanding whats worth learning vs delegating to AI; the user says career audit.

How do I install Karpathy Meta Reflection in Claude Code?

Run `npx skills add LearnPrompt/andrej-karpathy-skills --skill karpathy-meta-reflection -a claude-code`. Or copy the skill folder (karpathy-meta-reflection in LearnPrompt/andrej-karpathy-skills) into .claude/skills/karpathy-meta-reflection in your project. Claude Code loads it when a task matches its description.

How do I install Karpathy Meta Reflection in Codex?

Run `npx skills add LearnPrompt/andrej-karpathy-skills --skill karpathy-meta-reflection -a codex`. Or copy the skill folder (karpathy-meta-reflection in LearnPrompt/andrej-karpathy-skills) into .agents/skills/karpathy-meta-reflection in your project. Codex loads it when a task matches its description.

Can I use Karpathy Meta Reflection 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-meta-reflection -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-meta-reflection, .gemini/skills/karpathy-meta-reflection, .github/skills/karpathy-meta-reflection and .opencode/skills/karpathy-meta-reflection in your project.

What does Karpathy Meta Reflection need to run?

SKILL.md names no scripts, command-line tools or credentials: Karpathy Meta Reflection is instructions for the agent only.

Does Karpathy Meta Reflection 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 Meta Reflection 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 Meta Reflection use?

Karpathy Meta Reflection 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 Meta Reflection use?

About 1.5k tokens (SKILL.md is roughly 6.1k 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 Meta Reflection?

Skills that share tags, products or a category with Karpathy Meta Reflection: MCP Server Builder (anthropics/skills, 180k stars), Vercel Composition Patterns (supabase/supabase, 111k stars), Finishing a Development Branch (obra/superpowers, 297k stars) and Agent Browser CLI (vercel-labs/agent-browser, 44k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Karpathy Meta Reflection?

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.