anthropics

Public repository for Agent Skills

Claude Code is an agentic coding tool that lives in your terminal, understands your codebase, and helps you code faster by executing routine tasks, explaining complex code, and handling git...

A collection of notebooks/recipes showcasing some fun and effective ways of using Claude.

Official, Anthropic-managed directory of high quality Claude Code Plugins.

Anthropic's Interactive Prompt Engineering Tutorial

Open source repository of plugins primarily intended for knowledge workers to use in Claude Cowork

Anthropic's educational courses

A collection of projects designed to help developers quickly get started with building deployable applications using the Claude API

A suite of plugins for legal workflows

Skills for threat modeling, scanning, triage, patching, plus an autonomous scanning harness you can /customize

A lightweight sandboxing tool for enforcing filesystem and network restrictions on arbitrary processes at the OS level, without requiring a container.

An AI-powered security review GitHub Action using Claude to analyze code changes for security vulnerabilities.

Community plugin marketplace for Claude Cowork and Claude Code. Read-only mirror — submit plugins at clau.de/plugin-directory-submission.

Anthropic's original performance take-home, now open for you to try!

Reference blueprint for building shopping and merchant agents with Claude. Examples in retail, commerce, telecom, and entertainment included.

Claude Opus 4.6 wrote a dependency-free C compiler in Rust, with backends targeting x86 (64- and 32-bit), ARM, and RISC-V, capable of compiling a booting Linux kernel.

Claude Code SDK Demos

Reference and an example for the Bluetooth API for makers in Claude Cowork & Claude Code Desktop

Access to Anthropic's safety-first language model APIs in TypeScript

Companion code for the global workspace interpretability paper

Human preference data for "Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback"

Access to Anthropic's safety-first language model APIs via Go

Claude Code skills that take a founder from idea to a live Claude Managed Agent: interview, scope a v0, launch in their own account, grade it, iterate, and schedule it

This repo is a mirror of the contents of base-action in https://github.com/anthropics/claude-code-action.

A research prototype for zero-knowledge proofs of AI inference. Not maintained.

Rust implementation of protobuf with editions support, JSON serialization, and zero-copy views

Prompts, templates, and scripts for running large-scale language migrations with Claude Code

The CLI for the Claude API

HTML effectiveness examples

Repo for the Claude Code Marketplace to use with the Claude for Life Sciences Launch. This will continue to host the marketplace.json long-term, but not the actual MCP servers.

Skills and eval rubrics for K-12 teachers, co-developed with Learning Commons

Report issues related to MCP integration with Claude here.

Claude support for Apple Foundation Models

Access to Anthropic's safety-first language model APIs in C#

Anthropic Dev Container Features, including Claude Code CLI

Starter kit for a Claude-assisted on-call: mines your incident history into triage playbooks, sets up through human-approved gates, and runs read-only in your Slack channel — humans deploy every fix.

A library for bridging Python and HTML/Javascript (via Svelte) for creating interactive visualizations

Lightweight demo using the Anthropic Python SDK to experiment with Claude's Search and Retrieval capabilities over a variety of knowledge bases (Elasticsearch, vector databases, web search, and...

Access to Anthropic's safety-first language model APIs in PHP

Notebooks accompanying Anthropic's "Toy Models of Superposition" paper

Contains random samples referenced in the paper "Sleeper Agents: Training Robustly Deceptive LLMs that Persist Through Safety Training".

The foundational document describing Claude's values and behavior

Claude for Financial Advisors: a Claude Cowork plugin with ready-to-run workflows for financial advisors, drawing on third-party connectors.

This repo contains detailed implementation information about Anthropic's paired prompts approach for evaluating political neutrality.

https://transformer-circuits.pub/2025/attribution-graphs/methods.html

A Nix plugin that resolves Cargo workspaces natively and allows for crate level builds

Benchmark for evaluating LLM agents on smart-contract vulnerability discovery and exploitation