Superpowers is a browser-based game development engine and collaborative integrated development environment. It provides a unified workspace for building two-dimensional interactive experiences, allowing users to manage code, assets, and scene logic directly within a web browser without the need for local compilers or heavy desktop software. The platform distinguishes itself through a modular, component-based scripting architecture where game objects are defined by attached logic and visual properties. It supports real-time synchronization, enabling multiple developers to work on the same pro
Agent Skills is a centralized registry and management system designed for the discovery, auditing, and integration of reusable procedural modules into automated agent workflows. It provides a structured environment for sourcing verified capabilities that extend the functional range of AI agents, enabling the development and scaling of complex, multi-step automated processes. The platform distinguishes itself through a security-first approach to module integration, utilizing audit-verified data to ensure that capabilities meet safety requirements before they are deployed. It incorporates a dec
This project is a framework for integrating modular instruction packages and domain-specific tools into large language model agents. It provides a system for managing agent context and extending coding assistants through a modular prompt library of persona-based instruction sets and skill trees. The framework distinguishes itself through a persistent memory layer that tracks architectural decisions and infrastructure patterns to prevent regressions during autonomous code modifications. It includes an orchestrator for managing multi-agent swarms and autonomous coding loops that cycle through g
Agent-skills is a collection of structured instructions and behavioral personas designed to standardize how AI coding agents perform engineering tasks. It functions as a workflow orchestrator that maps natural language intent to repeatable technical sequences and verification checklists. The project distinguishes itself through the use of specialized markdown-defined roles, such as security auditors or test engineers, to apply targeted domain expertise. It employs an evidence-based verification model that requires runtime data or passing tests as mandatory exit criteria to ensure AI-generated
This project provides a standardized framework for extending the functional range of artificial intelligence agents through a registry of modular, declarative instructions. It enables agentic workflow automation by allowing developers to define task-specific behaviors and operational constraints that guide how agents interact with external tools and execute multi-step processes.
The main features of anthropics/skills are: Declarative Skill Orchestrations, Agent Configuration Specifications, Agent Capability Extensions, Agent Capability Registries, Agentic Workflow Automations, Agent Skill Sets, Agent & Tool Integrations, AI Agent Plugins.
Open-source alternatives to anthropics/skills include: obra/superpowers — Superpowers is a browser-based game development engine and collaborative integrated development environment. It… vercel-labs/agent-skills — Agent Skills is a centralized registry and management system designed for the discovery, auditing, and integration of… alirezarezvani/claude-skills — This project is a framework for integrating modular instruction packages and domain-specific tools into large language… addyosmani/agent-skills — Agent-skills is a collection of structured instructions and behavioral personas designed to standardize how AI coding… composiohq/awesome-claude-skills — This project serves as a centralized directory and resource hub for extending the functional capabilities of AI… kilo-org/kilocode — Kilocode is an autonomous engineering platform designed to orchestrate AI agents for complex software development…