Skip to content
Alternatives
Software like OpenAgentSkill
What else does this job. Matched on what each project does, not on who links to whom.
Closest first
- Agent Skills Overviewagentskills.ioAgent Skills is an open format designed to extend the capabilities of AI agents by packaging specialized knowledge and workflows into modular units called skills. md file, which holds metadata such as the name and description, along with instructions that guide an agent in performing a specific task. Additional resources like scripts, reference materials, templates, and other files can also be included within the skill folder, allowing for a comprehensive and portable solution to augment agent functionality. The format addresses the challenge of providing AI agents with the necessary context and procedural knowledge to perform complex or domain-specific tasks reliably. By encapsulating expertise—such as legal review processes, data analysis workflows, or presentation formatting—into reusable and version-controlled folders, Agent Skills enables agents to access and execute repeatable, auditable procedures tailored to company, team, or user-specific contexts. Skills are loaded by agents through a progressive disclosure process: initially, only basic metadata is loaded to determine relevance; when a task matches a skill, the full instructions are read into context; and during execution, the agent may utilize bundled code or reference additional resources as needed. This approach allows agents to manage a large set of skills efficiently, minimizing context overhead until detailed instructions are required. Agent Skills can be used across a variety of AI tools and agentic clients that support the format, promoting cross-product reuse of skills. The format is open and was originally developed by Anthropic, released as a standard that welcomes contributions from the broader community. The development process is collaborative and ongoing, with opportunities for engagement through GitHub and Discord. Agent Skills is positioned as an open standard for enhancing AI agents with modular, context-rich expertise and workflows.
- agent-skill-evalpypi.orgagent-skill-eval is an open-source CLI framework for evaluating the skills of code-generating agents across models like OpenCode, Claude Code, and Codex. It enables researchers and developers to benchmark agent performance using standardized tests.
- agent-skill-installergithub.comagent-skill-installer is an open-source CLI tool that enables developers to install and manage agent skills in their projects. It is designed for projects that distribute or consume modular agent skills, supporting easy integration and updates.
- SkillDBskilldb.devSkillDB offers a searchable database of over 5,900 agent-ready skills across 37 domains that can be installed instantly via CLI or the MCP (Model Context Protocol) server. It integrates with Claude Code, Cursor, and other agent frameworks, allowing agents to automatically discover and use specialized capabilities such as security audits, React performance optimization, and more. The platform eliminates repetitive prompting by giving agents expert-level knowledge on demand.
- Agent Skillstechleads.clubAgent Skills is an open-source infrastructure project offering a curated collection of reusable skills to extend AI coding agents like Cursor, Claude Code, and GitHub Copilot. It provides packaged instructions and workflows for specialized tasks, accessible via CLI and web interfaces.
- Skills Manageridoevergreen.meSkills Manager is an open-source desktop application designed to centralize the management and sharing of AI agent skills across a wide range of coding agents. It addresses the challenge of fragmented skill management by providing a unified interface where users can install, enable, disable, and transfer skills between agents such as Claude Code, Cursor, Windsurf, GitHub Copilot, Gemini CLI, Goose, OpenAI Codex, OpenCode, Kilo Code, Trae, and Antigravity. The platform allows users to view all installed skills for their agents in a single location, eliminating the need to manually search through configuration directories. Skills Manager supports installation of skills directly from GitHub by accepting any repository URL, and it is compatible with both public repositories and custom registries. Users can copy skills between supported agents quickly, without the need for manual file copying or path adjustments. Additionally, the ability to enable or disable skills without deleting them makes it easier to experiment with different setups and roll back changes as needed. Skills Manager is available for Windows and Linux, with a Mac version planned for future release. It is distributed under the MIT license and does not require users to create an account. The source code is publicly accessible, reflecting its open-source nature. The tool is developed by Zunalabs and encourages user feedback and community engagement through channels such as Discord and GitHub. By offering a centralized solution for managing AI agent skills, Skills Manager streamlines workflows for users working with multiple coding agents and reduces the time spent on manual setup and configuration.
- LazySkillslazyskills.shLazySkills provides a terminal-based user interface for managing agent skills across a wide range of AI agents. Designed as a mission control for agent skills, it allows users to view all installed skills in one place and determine which agents can access each skill, both at the project and global level. The tool addresses the challenge of tracking, diagnosing, and managing skills for multiple agents by offering a consolidated view and actionable insights directly within the terminal. Key features include grouping skills by their source—project, global, universal, or agent-specific—and enabling users to switch between agents to see which skills are actually usable by each. md files, invalid frontmatter, broken symlinks, missing lock entries, and ghost agent skills, helping users quickly spot and address broken installs. Before performing actions, users can inspect skill metadata, view rendered content, and preview the exact command that will be run, supporting safe management of skills. The platform supports opening, reinstalling, updating, removing, and pruning orphaned locks for skills, as well as running bulk actions with confirmation prompts. sh registry from within the interface to preview and install new skills either to a project or globally. For automation or integration with other tools, LazySkills offers a CLI mode that enables registry search and returns results in JSON format, making it accessible to agents programmatically. LazySkills is compatible with macOS, Linux, and Windows, and can be installed via curl, Homebrew, Go, or PowerShell. Once installed, users can launch the terminal UI by typing 'lazyskills'. The interface includes command shortcuts for searching, filtering, managing, and editing skills, streamlining the workflow for users managing complex agent environments.
- skillhub-aipypi.orgskillhub-ai is an open-source CLI package manager for AI agent skills, enabling developers to install, compose, and publish skills for various AI agents. It supports integration with platforms like Claude Code, Cursor, Codex, and Gemini, streamlining skill management for agent developers.
- awesome-skill-forgepypi.orgawesome-skill-forge is an open-source repository offering over 90,000 universal AI agent skills compatible with Claude Code, OpenAI Agents, Hermes, AutoGen, LangChain, and other LLM frameworks. It is designed for developers building AI agents.
- skillnet-aiopenkg.cnskillnet-ai is an open-source Python SDK that allows developers to create, evaluate, and connect modular AI skills using the SkillNet framework. It is designed for AI researchers and developers seeking to build and integrate AI capabilities in a flexible, modular way.
- AgentSkills Directoryallagentskills.comAgentSkills Directory is a web application for organizing, tracking, and sharing agent skills. It provides categorized skill listings, favorites, user accounts, administrative tools, and API documentation for teams and solo users.
- OpenSkill CLIopenskill.onlineOpenSkill CLI is a command-line tool for creating and managing Claude skills. It focuses on turning reusable instructions into permanent slash commands, so repeated prompts do not have to be explained again each time. The page frames skills as recipes for AI behavior and shows an example command such as /code-review. Its features include 8 pre-built templates for code review, testing, debugging, API design, and similar tasks. Skills can be organized with tags and groups, filtered by category, and kept in Git repositories for backup and team sharing. OpenSkill CLI also supports import and export in JSON, YAML, or Markdown, along with importing from files, URLs, or other sources. Version history is built in, with automatic versioning, diffs, and rollback to previous versions. It also offers context providers that can use files, globs, commands, and URLs, plus workspaces for project-specific configuration and pre- and post-execution hooks. The tool works with Claude Code, described as Anthropic's official CLI, and it is powered by Groq, OpenAI, Anthropic, and Ollama. Installation is shown with a shell command, and the supported platforms listed on the page are macOS, Linux, ARM64, and x86_64. The site also states that it is released under the MIT License, built with Go, and made by Rakshit-gen.
- asmluongnv.comagent-skill-manager (asm) is an open-source tool designed for managing skills used by AI coding agents. It provides both a text user interface (TUI) and a command-line interface (CLI), enabling users to install, search, audit, and organize agent skills across a range of platforms. The tool supports integration with agents such as Claude Code, Codex, Cursor, Windsurf, and over 15 additional AI coding agents. A central feature of asm is its companion catalog, which indexes more than 3,800 skills sourced from 35 repositories and organized into 16 categories. This catalog allows users to browse and select from a wide range of agent skills, streamlining the process of enhancing and maintaining their AI agents. js package management. asm is positioned for those who work with AI coding agents and require a unified interface to manage a diverse set of agent skills. As an open-source project, its source code is available on GitHub, allowing for community contributions and transparency in development.
- Skillselionskillselion.comSkillselion is a searchable directory and MCP server for discovering Claude Code skills, MCP servers, plugins, and related marketplaces. Developers can browse ranked, categorized agent tools or load skills into coding agents through its CLI and MCP integration.
- agent-skill-registrypypi.orgagent-skill-registry is an open-source, Git-backed registry for sharing and managing agent skills. It provides guardrails and CLI workflows for developers maintaining reusable skills across agent projects.
- LoopSkillpypi.orgLoopSkill is an open-source CLI client for interacting with an open registry of runnable agent artifacts, including skills, bundles, loops, and personalities. It supports the Model Context Protocol (MCP) and is designed for AI agent developers and researchers to discover, manage, and deploy agent skills efficiently.
- OpenAgentsopenagents.orgOpenAgents is an open-source platform for collaborating with and managing AI agents. It provides a unified workspace for shared threads, files, and browser sessions, and includes a launcher to install and manage various AI agents. Designed for developers and researchers building multi-agent AI systems.
- aiagentskills-site-kitaiagentskills.netaiagentskills-site-kit is an open-source toolkit that provides metadata and URL helper utilities for integrating with the AI Agent Skills directory. It is designed for developers managing or building curated directories of AI agent skills, supporting platforms like Claude and Codex.
- SkillDepotskilldepot.devSkillDepot operates as the largest marketplace for AI agent capabilities, allowing developers to browse, install via a single CLI command, and execute production-ready skills. It handles dependency resolution automatically and supports both local execution and API calls with built-in monitoring. The platform targets AI developers building agents, offering community-contributed skills across categories and frameworks with no configuration required.
- lotr-skillspypi.orglotr-skills is an open-source CLI tool that enables developers to install and manage AI agent skills compatible with frameworks like Claude Code, Cursor, Cline, and more. It streamlines the process of equipping agentic AI systems with the right capabilities, supporting prompt engineering and MCP integration. Ideal for AI agent developers seeking a unified skill management solution.
- agentskills-toolsagentskills.ioagentskills-tools is an MIT-licensed command-line package for authoring and validating Agent Skills. It is intended for developers creating and checking Agent Skills, with source code hosted on GitHub.
- skill-auditorpypi.orgskill-auditor is an open-source command-line tool that scans AI Agent skills for security issues before installation. It acts as an install gate, helping developers and maintainers ensure that only safe and validated skills are added to their AI agents. Ideal for those building or managing AI agent frameworks.
- skillgen-aigithub.comAnalyze any codebase and auto-generate AI agent skill files for Claude Code, Cursor, and other AI tools
- SkillsHubskillshub.wtfSkillsHub is an AI Agent Skills Registry built around a single API call that describes a task and returns a best-fit skill. Its own page says it is meant to help users avoid manual searching and comparing, with a claim of 250x fewer tokens than searching by hand. The service provides API endpoints for quick start, skill resolution, and search. It also supports browsing and fetching skills, with examples showing a resolve request, a fetched skill page, and a markdown format for retrieved skills. The registry is described as growing, and the page highlights community-rated skills with trust scores so users can find reliable, well-maintained skills. Example skill entries cover tasks such as Terraform and OpenTofu work, Terraform testing, dark-themed React interfaces, presentation slide decks, and GitHub issue handling. SkillsHub says it is built for agents, and it also offers an “I’m a Human” entry point alongside an “I’m an Agent” path. The page lists support for Claude Code, Codex, Cursor, Gemini, Cline, GitHub Copilot, Windsurf, OpenClaw, and Antigravity. It also states that no registration is needed to resolve, fetch, and use skills. The site includes links for browse, docs, login, publish, and registry, and it shows a live GitHub-linked interface. The page gives a version label of 0.2.0 and identifies the project as SkillsHub. It also displays live counts for skills, stars, installs, and users, but those figures are only presented as page stats rather than as documented product details.
Ranked by how close each one sits to OpenAgentSkill in the index, not by popularity. Back to OpenAgentSkill →