New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Pieter Abbeel

by K-Dense-AI in K-Dense-AI/mimeo

Applies the reasoning of Pieter Abbeel, robotics and reinforcement learning expert, UC Berkeley professor, and co-founder of Covariant.

MITAuto-check passedAI & LLM Engineering

Install Pieter Abbeel

skills CLI
$ npx skills add K-Dense-AI/mimeo --skill pieter-abbeel -a claude-code

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

GitHub CLI
$ gh skill install K-Dense-AI/mimeo pieter-abbeel --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/K-Dense-AI/mimeo.git skills-src && mkdir -p .claude/skills && cp -r skills-src/output/pieter-abbeel .claude/skills/pieter-abbeel && 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
pieter-abbeel
GitHub stars
282
Token cost
~1.5k tokens
SKILL.md length
727 words
Files
10 (incl. references)
Skills in repo
21
Repo updated
First seen
Licence
MIT

At a glance

Applies the reasoning of Pieter Abbeel, robotics and reinforcement learning expert, UC Berkeley professor, and co-founder of Covariant.

  • Works in 4 steps: Build many versions of the simulator. → Randomize physical parameters (friction,… → Train a single neural network across all… → …
  • You are designing AI systems
  • SKILL.md covers Core principles, How Pieter Abbeel reasons, Applying the frameworks and Anti-patterns he pushes against, plus 2 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Pieter Abbeel is an agent skill from K-Dense-AI/mimeo. Applies the reasoning of Pieter Abbeel, robotics and reinforcement learning expert, UC Berkeley professor, and co-founder of Covariant. Use this skill whenever you are designing AI systems, tackling Sim2Real transfer, deploying machine learning in the physical world, or evaluating reinforcement learning architectures. Trigger this skill for questions about domain randomization, reward design, bootstrapping real-world AI, robotics hardware assumptions, or shifting from hard-coded rules to data-driven deep…

Its SKILL.md is about 1.5k tokens, which your agent loads only when the skill is triggered. The skill folder holds 10 other files, including reference files (for example `AGENTS.md`, `references/anti-patterns.md` and `references/frameworks.md`).

It sits in AI & LLM Engineering, covering Reinforcement learning, Deep learning and Deployment. The repository describes itself as: Mimeograph an expert into a SKILL.md or AGENTS.md for your agent. The licence is MIT.

When your agent uses it

  • You are designing AI systems
  • Tackling Sim2Real transfer
  • Deploying machine learning in the physical world
  • Evaluating reinforcement learning architectures

Example prompts

  • “Use the pieter-abbeel skill to apply the reasoning of Pieter Abbeel, robotics and reinforcement learning expert, UC Berkeley professor, and…”
  • “/pieter-abbeel”

Workflow steps

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

  1. Build many versions of the simulator.
  2. Randomize physical parameters (friction, mass, lighting) rather than trying to match reality.
  3. Train a single neural network across all simulators.
  4. Deploy to the real world, which the network treats as just another variation.

What it can do on your machine

Read from SKILL.md and the folder at commit a4cea18. 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):

    • arxiv.org

    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

Pieter Abbeel loads about 1.5k tokens when it runs, and up to ~7k if it reads all its reference files. Until then it costs about 153 tokens; SKILL.md has 727 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~153
When it runs · the whole SKILL.md, loaded when a task matches
~1.5k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~7k

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 K-Dense-AI/mimeo at commit a4cea18, republished under its MIT licence (© K-Dense-AI). 727 words, ~1,515 tokens.

Download SKILL.mdSave it as .claude/skills/pieter-abbeel/SKILL.md (or your agent's skills folder). This skill also uses 9 other files; get the full folder from GitHub.
name
pieter-abbeel
description
Applies the reasoning of Pieter Abbeel, robotics and reinforcement learning expert, UC Berkeley professor, and co-founder of Covariant. Use this skill whenever you are designing AI systems, tackling Sim2Real transfer, deploying machine learning in the physical world, or evaluating reinforcement learning architectures. Trigger this skill for questions about domain randomization, reward design, bootstrapping real-world AI, robotics hardware assumptions, or shifting from hard-coded rules to data-driven deep learning. It helps ground theoretical AI in physical embodiment and pragmatic deployment.

Thinking like Pieter Abbeel

Pieter Abbeel is a pioneer in robotics and deep reinforcement learning. His thinking bridges the gap between cutting-edge artificial intelligence research and messy, real-world physical deployment. He views physical embodiment—robotics—as the ultimate reality check for AI, preventing researchers from overfitting to simple, forgiving simulators.

Reach for this skill whenever you are designing AI architectures for physical systems, tackling Sim2Real transfer, deciding how to bootstrap a reinforcement learning agent, or evaluating the trade-offs between hard-coded rules and deep learning.

Core principles

  • Robotics as the Ultimate Reality Check: Build AI tied into physical systems, because physical embodiment quickly reveals the true capabilities and limitations of algorithms.
  • Software 2.0 (Data Over Hard-Coded Rules): Shift from writing explicit lines of code to curating data; hard-coding rules requires endless exceptions that become fragile in the real world.
  • Sim2Real via Domain Randomization: Instead of trying to build a perfect simulator, expose models to massive simulated variations so the real world just looks like another variation.
  • Bootstrapping Real-World RL: Bootstrap real-world AI deployment with human behavioral cloning before applying reinforcement learning, as pure RL from scratch is too slow and unsafe.

For detailed rationale and quotes, see references/principles.md.

How Pieter Abbeel reasons

Abbeel approaches AI through the lens of probabilistic reasoning and optimization, treating them as the mathematical bedrock of modern systems. However, he is fiercely pragmatic about deployment. He asks first: How does this survive the real world? He dismisses approaches that rely on perfect models or endless "if-then-else" rules, favoring deep networks that learn patterns directly from data. He views unsupervised exploration as "play" and treats the reinforcement learning algorithm itself as something that can be optimized (Meta-Learning).

For a deeper dive into his conceptual lenses, see references/mental-models.md.

Applying the frameworks

Domain Randomization

When to use: Transferring a model trained in simulation to the real world without a perfect simulator.

  1. Build many versions of the simulator.
  2. Randomize physical parameters (friction, mass, lighting) rather than trying to match reality.
  3. Train a single neural network across all simulators.
  4. Deploy to the real world, which the network treats as just another variation. (See references/frameworks.md for the full catalog).
Bootstrapped Reinforcement Learning Deployment

When to use: Deploying AI agents in real-world scenarios where safety and time are critical constraints.

  1. Start with supervised learning and behavioral cloning where humans do the work.
  2. Have the ML system match human actions and make suggestions.
  3. Once highly capable, gradually fuse in reinforcement learning by providing actual achievement objectives. (See references/frameworks.md for the full catalog).
Show full SKILL.md (305 more words)Show less

Anti-patterns he pushes against

  • Hard-Coding Rules and Assumptions: Adding "if-then-else" rules creates unwieldy, fragile systems that fail to generalize.
  • Perfecting the Simulator: Trying to perfectly match simulation to reality is a trap; slight errors will cause catastrophic real-world failures.
  • Deploying Pure RL from Scratch: Letting a robot learn entirely through trial and error in the real world is dangerous and time-consuming.
  • Manual Reward Design for Complex Tasks: Manually defining rewards leads to "reward exploitation" where agents find unintended loopholes.

For the full catalog with rationale and quotes, see references/anti-patterns.md.

Heuristics and rules of thumb

  • Randomize the Simulator: If you can't perfectly match a simulator to reality, randomize its parameters instead.
  • Bootstrap RL with Imitation: Use supervised learning on human demonstrations to initialize a policy before letting it explore.
  • Robotics as a Reality Check: Use physical robots to ensure algorithms aren't just overfitting to simple simulators.
  • Deep Networks for Patterns: If there is a pattern in the data, assume a deep network can represent and capture it.

See references/heuristics.md for the full list with attribution.

How to use this skill in conversation

When the user is designing an AI system, especially one that interacts with the physical world or relies on reinforcement learning, surface Abbeel's frameworks by name. If they suggest hard-coding edge cases, gently push back using the "Software 2.0" principle, explaining why data scales better than rules. If they are struggling with simulation fidelity, introduce "Domain Randomization." Apply these concepts directly to their architecture or code, citing where the idea comes from (e.g., "Pieter Abbeel suggests bootstrapping this with behavioral cloning first because..."). Avoid impersonation—do not pretend to be Abbeel; channel his pragmatic, data-driven, physical-first reasoning.

Generated with mimeo. If this material contributes to published work, please cite Kassis, T. (2026). "mimeo: Compiling Public Expert Corpora into Agent Skills and Testing What Transfers." arXiv:2609.00453.

© K-Dense-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

SKILL.md and 9 other files (references) in output/pieter-abbeel of K-Dense-AI/mimeo.

  • SKILL.md
  • AGENTS.md
  • avatar.png
  • references/anti-patterns.md
  • references/frameworks.md
  • references/heuristics.md
  • references/mental-models.md
  • references/principles.md
  • references/quotes.md
  • references/sources.md

Open the folder on GitHubat commit a4cea18

Used in 1 other repository

We found 1 copy of this SKILL.md (exact, near-identical or edited) in other folders. This page covers the copy in K-Dense-AI/mimeo, which our catalogue first saw on October 7, 2026.

Compare with similar skills

Pieter Abbeel 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.

Pieter Abbeel compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Pieter Abbeel this skillK-Dense-AI/mimeo282—~1.5kAutomated safety check: PassMIT
Hung-Yi Lee Teaching Stylevoidful/hung-yi-lee-skill1.3k—~13kAutomated safety check: PassNone
Scaffold Examplecomet-ml/comet-examples174—~1kAutomated safety check: PassNone
PyTorch Lightning TrainingOrchestra-Research/AI-Research-SKILLs13k6 repos~2.3kAutomated safety check: PassMIT
Ray Train Distributed TrainingOrchestra-Research/AI-Research-SKILLs13k2 repos~2.7kAutomated safety check: PassMIT
torchforge RL TrainingOrchestra-Research/AI-Research-SKILLs13k2 repos~2.5kAutomated safety check: PassMIT

Similar skills

  • Hung-Yi Lee Teaching Style

    voidful/hung-yi-lee-skill

    Explains machine learning, LLMs, AI agents and speech modeling in a Hung-Yi Lee-inspired teaching style, drawing on a knowledge base built from his lectures and research references.

    1.3k GitHub stars~13k tokensUpdated 2 mo ago
    EducationAuto-check passed

  • Scaffold Example

    comet-ml/comet-examples

    Scaffold a brand-new Comet example in this repo from the canonical template under templates/integration-example/.

    174 GitHub stars~1k tokensUpdated 1 mo ago
    AI & LLM EngineeringAuto-check passed

  • PyTorch Lightning Training

    Orchestra-Research/AI-Research-SKILLs

    Shows how to organize PyTorch training with Lightning's LightningModule and Trainer, covering validation, DDP, callbacks and learning-rate scheduling.

    13k GitHub starsUsed in 6 repos~2.3k tokens
    AI & LLM EngineeringAuto-check passed

  • Ray Train Distributed Training

    Orchestra-Research/AI-Research-SKILLs

    Scales PyTorch, TensorFlow and Hugging Face training from a single GPU to multi-node clusters with Ray Train, including Ray Tune sweeps and checkpoint recovery.

    13k GitHub starsUsed in 2 repos~2.7k tokens
    AI & LLM EngineeringAuto-check passed

  • torchforge RL Training

    Orchestra-Research/AI-Research-SKILLs

    Guides reinforcement-learning research with torchforge, Meta's PyTorch-native library that keeps RL algorithms apart from infrastructure, including GRPO math-reasoning runs.

    13k GitHub starsUsed in 2 repos~2.5k tokens
    AI & LLM EngineeringAuto-check passed

  • ML Engineer

    davila7/claude-code-templates

    Build production ML systems with PyTorch 2.x, TensorFlow, and modern ML frameworks.

    33k GitHub starsUsed in 9 repos~2.3k tokens
    AI & LLM EngineeringAuto-check passed

More from K-Dense-AI/mimeo

All 21 skills in this repo

  • Andrej Karpathy

    K-Dense-AI/mimeo

    Applies the mental models and frameworks of Andrej Karpathy (deep learning, former Director of AI at Tesla, founding member of OpenAI, Eureka Labs).

    282 GitHub stars~1.9k tokensUpdated 1 mo ago
    Auto-check passed

  • Andrew Ng

    K-Dense-AI/mimeo

    Applies the reasoning, principles, and frameworks of Andrew Ng (machine learning pioneer, co-founder of Coursera and DeepLearning.AI, Stanford University, and former Google Brain lead).

    282 GitHub stars~1.5k tokensUpdated 1 mo ago
    Auto-check passed

  • Christopher Manning

    K-Dense-AI/mimeo

    Applies the reasoning, architectural principles, and AI philosophy of Christopher Manning (natural language processing expert, Stanford University, director of Stanford AI Lab).

    282 GitHub stars~1.8k tokensUpdated 1 mo ago
    Auto-check passed

  • Daphne Koller

    K-Dense-AI/mimeo

    Applies the reasoning style of Daphne Koller (machine learning pioneer, co-founder of Coursera, founder and CEO of Insitro).

    282 GitHub stars~1.8k tokensUpdated 1 mo ago
    Auto-check passed

  • Demis Hassabis

    K-Dense-AI/mimeo

    This skill channels the strategic and scientific reasoning of Demis Hassabis, CEO and co-founder of Google DeepMind, AlphaGo and AlphaFold, and 2024 Nobel Prize in Chemistry.

    282 GitHub stars~2k tokensUpdated 1 mo ago
    Auto-check passed

  • Fei Fei Li

    K-Dense-AI/mimeo

    Applies the reasoning, frameworks, and mental models of Fei-Fei Li, computer vision pioneer, ImageNet creator, and co-director of Stanford HAI.

    282 GitHub stars~1.8k tokensUpdated 1 mo ago
    Auto-check passed

Categories

Questions about Pieter Abbeel

What does Pieter Abbeel do?

Applies the reasoning of Pieter Abbeel, robotics and reinforcement learning expert, UC Berkeley professor, and co-founder of Covariant. Pieter Abbeel is an agent skill from K-Dense-AI/mimeo. Applies the reasoning of Pieter Abbeel, robotics and reinforcement learning expert, UC Berkeley professor, and co-founder of Covariant.

When should I use Pieter Abbeel?

Pieter Abbeel fits situations like: you are designing AI systems; tackling Sim2Real transfer; deploying machine learning in the physical world; evaluating reinforcement learning architectures.

How do I install Pieter Abbeel in Claude Code?

Run `npx skills add K-Dense-AI/mimeo --skill pieter-abbeel -a claude-code`. Or copy the skill folder (output/pieter-abbeel in K-Dense-AI/mimeo) into .claude/skills/pieter-abbeel in your project. Claude Code loads it when a task matches its description.

How do I install Pieter Abbeel in Codex?

Run `npx skills add K-Dense-AI/mimeo --skill pieter-abbeel -a codex`. Or copy the skill folder (output/pieter-abbeel in K-Dense-AI/mimeo) into .agents/skills/pieter-abbeel in your project. Codex loads it when a task matches its description.

Can I use Pieter Abbeel 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 K-Dense-AI/mimeo --skill pieter-abbeel -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/pieter-abbeel, .gemini/skills/pieter-abbeel, .github/skills/pieter-abbeel and .opencode/skills/pieter-abbeel in your project.

What does Pieter Abbeel need to run?

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

Does Pieter Abbeel access the network?

SKILL.md names 1 domain. As links in the text: arxiv.org. This is read from the text; nothing was executed.

Is Pieter Abbeel 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 Pieter Abbeel use?

Pieter Abbeel 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 Pieter Abbeel 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. Its references folder adds about 5.5k tokens, read only when the agent opens those files.

What are the alternatives to Pieter Abbeel?

Skills that share tags, products or a category with Pieter Abbeel: Hung-Yi Lee Teaching Style (voidful/hung-yi-lee-skill, 1.3k stars), Scaffold Example (comet-ml/comet-examples, 174 stars), PyTorch Lightning Training (Orchestra-Research/AI-Research-SKILLs, 13k stars) and Ray Train Distributed Training (Orchestra-Research/AI-Research-SKILLs, 13k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Pieter Abbeel?

K-Dense-AI (a GitHub organization) maintains it in K-Dense-AI/mimeo, which has 282 GitHub stars. The repository holds 21 skills in this directory. The repository was last updated on September 2, 2026.

Source: K-Dense-AI/mimeo on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.