MushyBook
skills logo

skills

Public repository for Agent Skills

Agent SkillsAI AgentsDeveloper ToolsPython 163.9k 19.5kHealth 85
GitHub

What is it?

What it is

> **Note:** This repository contains Anthropic's implementation of skills for Claude. For information about the Agent Skills standard, see agentskills.io.

Why it exists

Public repository for Agent Skills

Who should use it

Teams building with Python who want an open-source, self-hosted option.

Who should avoid it

Teams that need a fully managed SaaS with enterprise SLAs out of the box.

How it works

A quick walkthrough in plain English

How skills works

Step 1 of 3

You interact with it

Open skills, send a request, or connect it to your stack.

Features

Agent Skills

Advantages

  • Open source (Open Source)
  • Active Python ecosystem
  • Self-hosted deployment options

Disadvantages

  • Requires operational ownership for self-hosted setups
  • Community support varies by project maturity

Installation

native

/plugin marketplace add anthropics/skills

FAQ

What is skills?

skills is an open-source project licensed under Open Source.

What language is skills built with?

Primary language: Python.

Is it free to use?

Yes. Licensed under Open Source. Check the license for commercial use.

Loading documentation…
View on GitHub

Featured in Videos

YouTube tutorials and walkthroughs for skills

Alternatives

Similar projects ranked by category, topics, and text overlap.

Compare
skills logo

skills

Python

Codebase harness + loop engineer

1.0k·Health 75

Compare
agent-apprenticeship logo

agent-apprenticeship

Python

A modular platform for autonomous agent learning via real-world tasks. Agents work in loops with mentors, produce reusable experience compilations, and leverage shared ecosystem data to improve performance. Includes economic value estimation for task execution and supports multiple agent types (Codex, Claude Code, etc.).

1.3k·Health 82

Compare
agent-apprenticeship logo

agent-apprenticeship

Python

Agent Apprenticeship offers a CLI‑driven platform that supports multiple apprentice agents (Codex, Cursor, Claude Code, OpenClaw, OpenCode, Hermes Agent, or custom), mentor model providers (OpenAI, Anthropic, Gemini, OpenRouter, etc.), and three modes (Autonomous, Expert‑Led, Organization Custom). Users can initialize the system, run tasks, watch progress, inspect and export experience compilations, install runtime training from prior runs, and contribute to a public or private ecosystem. The seed dataset on Hugging Face provides over 500 full experience compilations and 39k structured records, enabling immediate use and community growth.

1.3k·Health 82

Compare
img2threejs logo

img2threejs

Python

The pipeline is staged: an image is probed, classified, and assessed for complexity; a detailed ObjectSculptSpec is authored and validated with strict‑quality gates; each build pass (blockout, structural, form‑refinement, material, surface, lighting, interaction, optimization) is generated by deterministic Python scripts and reviewed via a side‑by‑side comparison sheet. The agent decides to continue, refine the spec, refine the code, request input, or stop. The result is a TypeScript factory that returns a THREE.Group with a runtime hierarchy exposed in `root.userData.sculptRuntime`, enabling animation and interaction without external assets.

2.6k·Health 90

Compare
loopy logo

loopy

JavaScript

The repository consists of two components: the Loop Library website, a live catalog where anyone can browse and copy loops, and the Loopy skill, an optional guide installable for agents that walks them through discovering repeated work, finding existing loops, auditing, adapting, running, debriefing, saving, and publishing loops. Together they enable agents to turn repetitive tasks into reliable, feedback‑driven playbooks.

2.8k·Health 90

Compare
skills | MushyBook