BehiSecc/awesome-claude-skills

A curated list of Claude Skills.

Awesome Claude Skills is a curated list of skills — small, reusable capabilities that extend what the AI assistant Claude can do. Think of them as add‑on tools: one skill helps create Word documents, another runs safe database queries, another generates presentations.

The project is simply a directory (a long list) of links to these skills, each with a one‑line description. It does not host the skills itself; it points to their original GitHub repositories.

How it’s organized:

  • Skills are grouped into categories like Document Skills, Development & Code Tools, Data & Analysis, Scientific & Research Tools, Writing & Research, Learning & Knowledge, and more.
  • Each entry is a link to the skill’s repository, followed by a short summary of what that skill does.
  • The list also includes a few sponsor mentions at the top (Atlas Cloud and APIMart) that are commercial AI API platforms.

Who it’s for:

  • Developers and users of Claude who want to quickly find ready‑made skills to add to their own projects — for example, to handle PDFs, query databases, generate charts, or automate social media posting.

Key takeaway:

  • It’s a curated index — a convenient starting point to discover and choose Claude skills, saving you from searching GitHub on your own. The README itself contains no code; it’s a reference list.

Related

  • Project
    OthersideAI/self-operating-computer

    A framework that enables multimodal AI models to view a computer screen and drive mouse and keyboard actions to reach objectives. Supports GPT-4o, Claude 3, Gemini, and others, plus OCR and Set-of-Mark modes for better clicking.

  • Project
    astrid-runtime/astrid

    Astrid is a Rust‑based, user‑space OS runtime that runs WebAssembly “capsules” in a sandbox, connects them via a typed event bus, and enforces fine‑grained, cryptographically signed capabilities. It isolates each principal (agent) with its own storage, secrets, and quota, and provides a minimal kernel (`astrid‑daemon`) that routes IPC and maintains an immutable audit chain. The system is designed for building secure LLM‑driven agents or modular services, letting the model decide *what* to do while the runtime decides *how* it may act.

  • Project
    AgriciDaniel/claude-ads

    Claude Ads is an open‑source AI skill for Claude Code that audits ad‑account data from twelve major platforms, producing evidence‑backed pass/fail reports and optional drafts for planning, creative, monitoring, optimisation and testing. It is read‑only by default, runs via simple slash commands, and includes an optional UI companion (Cockpit). The project is in development‑candidate status and distributed under the MIT license.

  • Project
    a16z-infra/ai-town

    A deployable starter kit for building virtual towns where AI characters socialize, featuring a JS/TS framework and support for multiple LLM providers.