Awesome Claude Skills

A curated list of Claude Skills and related tools for customizing Claude's workflows, including official document, design and development skills plus guidance on installing and building them.

Visit website github.com

Awesome Claude Skills catalogs Claude Skills: specialized folders of instructions, scripts and resources that Claude loads dynamically when relevant to a task, using a progressive-disclosure approach that only loads full instructions once a skill's summary matches the task at hand.

It lists official skills for working with document formats such as Word, PDF, PowerPoint and Excel, design and creative skills for generative art and GIF creation, and development skills such as one for frontend design and one for building Claude.ai artifacts, alongside notes on enabling skills in Claude apps, installing them in Claude Code, and using the Skills 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