Anthropic Agent Skills

Anthropic's example skills for Claude: folders of instructions, scripts and resources that Claude loads for specialized tasks, plus the Agent Skills specification and a template.

Agent skills

Visit website github.com

This repository holds Anthropic's implementation of skills for Claude. A skill is a folder with a SKILL.md file of instructions and metadata, plus any scripts and resources, that Claude loads dynamically to complete a task in a repeatable way.

The examples range from creative work and design to testing web apps, MCP server generation and enterprise communication. It also includes the document skills behind Claude's docx, pdf, pptx and xlsx handling, which are source-available rather than open source, along with the Agent Skills specification and a skill template.

The skills can be installed as a Claude Code plugin marketplace and used in Claude.ai and the Claude API.

More in Agent skills

See all 581

Provenance gate
github.com
A deterministic authorization gateway that sits between an AI agent and its tools, tracing where each parameter of a side-effect call came from, and blocking the call or asking a human when the source does not check out.
- Agent skills
- AI evals
Expected Harm Calculus (EHC-4): Asimov's Four Laws for Autonomous AI Agents
github.com
A markdown framework of system rules that restates Isaac Asimov's Four Laws of Robotics as a set of prioritized loss calculations for large-language-model agents to follow, published as a discovery file for agents and crawlers to read.
- Agent skills
Vitruvius
github.com
An engineering research agent that runs a discover, read, synthesize, verify and review loop over technical questions, reading sources directly rather than inferring from titles, and publishing its own scored verifier benchmark, weaknesses included.
- Agent skills
- AI evals

More in Agent skills

Provenance gate

Expected Harm Calculus (EHC-4): Asimov's Four Laws for Autonomous AI Agents

Vitruvius

Cookies