Open Source Agent Skills
Agent skills are reusable packages of instructions, domain knowledge, and workflows that help AI agents handle specific tasks more reliably. They provide relevant context and step-by-step procedures when needed, reducing repeated prompting and helping agents follow consistent practices across coding, research, and other work. Skills can be adapted to particular tools or environments and may include scripts, examples, or reference materials alongside written guidance.
Open source options include skill collections, task-specific workflow packages, authoring utilities, and frameworks for organizing or evaluating skills. When choosing one, check its license, documentation, maintenance activity, compatibility with your agent and workflow, and any runtime or access requirements. Review how skills are loaded and whether their instructions are clear, secure, and easy to customize. These resources are useful to developers, teams, and researchers building or extending AI agents.
59 repositories · updated October 5, 2026
image-blaster: Turn Images into 3D Environments and Assets
image-blaster uses Claude skills and external generation services to turn an image into a 3D environment, object meshes, and sound effects. It is designed to quickly create starting points for game, 3D, and web projects.
skillrank: Find and Evaluate AI-Agent Skills
SkillRank is a Rust CLI for discovering, installing, and evaluating skills used by coding agents. Its paired local evaluations compare a skill-enabled run with a control to show changes in success, tokens, time, and cost.
web-design: Create Consistent Web Pages with a Claude Code Skill
web-design is a Claude Code skill that turns product briefs, reference URLs, or screenshots into an editable design specification before generating web code. It is suited to developers and designers who want a repeatable, spec-led workflow for building consistent pages.
meshtastic-mcp: Connect AI Agents to Meshtastic Devices
A Python MCP server and agent skills for discovering, operating, observing, and testing Meshtastic devices and apps. Its portable core works over serial or TCP, with optional capabilities for firmware builds, mobile-app testing, replay, and hardware benches.
text-to-cad: Give AI Agents CAD and Fabrication Workflows
text-to-cad provides agent skills for creating and working with CAD, drawings, robot descriptions, and fabrication files. It suits engineering and robotics workflows where an agent needs to produce or inspect practical design artifacts.
i-have-adhd: Make Coding Assistant Responses Easier to Scan
i-have-adhd is a skill for coding assistants that makes replies more direct and easier to act on. It suits people who prefer numbered steps, concise answers, and a clear next action without extra preamble or tangents.
skills: Improve Interfaces with Agent Skills
A collection of agent skills for improving interface design, covering UI, typography, color, accessibility, layout, and product writing. Useful for designers and developers who want targeted reviews and iteration support inside an AI-assisted workflow.
AREX-Skill: Give Coding Agents Reusable ML Workflows
AREX-Skill is a library of executable, agent-readable workflows distilled from machine-learning repositories and research. Use it to help coding agents run, validate, and recover ML tasks with less unguided trial and error.
agentic-engineering: Give Coding Agents a Persistent Project Workflow
A documentation-first skill suite for coding agents, covering project specs, decisions, session memory, verification, and Git workflow. It suits teams running multi-session development who want agents to follow explicit contracts and leave merges to humans.
oh-my-hermes: Add Governed Workflows to Hermes Agent
oh-my-hermes adds model routing, coding workflows, verification gates, and reviewed long-term project memory to Hermes Agent. It suits developers who want structured, observable agent work without replacing Hermes or silently treating a reported result as verified.
Awesome-Self-Evolving-Agents: Explore Research on Evolving Agents
A curated research index and survey companion covering self-evolving AI agents. It organizes papers, benchmarks, libraries, and applications for researchers and practitioners exploring how agents improve through model, environment, and combined evolution.
session-to-skill: Turn OpenCode Sessions into Reusable Skills
An OpenCode skill that turns shared session links into reusable, publishable AI agent skills. It analyzes session patterns, checks the generated skill against TRACE and security criteria, then packages the result as a ZIP.