Which AI tools support Agent Skills: a client showcase
The Agent Skills format (SKILL.md) is a portable specification that lets you define reusable instructions, tools, and workflows for AI coding agents. If you write a skill once in this format, any agent product that supports it can load and use it. This page lists 44 products that currently support the format, with links to their product pages and skills documentation.
What it does
Instead of writing the same prompt or configuration for every agent you use, you drop a SKILL.md file into your project or agent's context directory. The agent reads it and adjusts its behaviour accordingly. The format is product-agnostic, so the same skill file works across different agents that implement the spec. This showcase helps you find which agents you can target when authoring skills, and which ones you can use to run skills written by others.
Before you start
There are no universal prerequisites. Each product has its own installation and setup process. You will need to install the agent product of your choice and follow its documentation to enable or load skills. The source page lists 44 products; the list is not exhaustive and may grow over time.
Products that support Agent Skills
Junie
Junie is an LLM-agnostic coding agent built for real-world development. It is built on top of the IntelliJ Platform, so it understands your project the same way your editor does.
- Product: https://junie.jetbrains.com/
- Skills documentation: https://junie.jetbrains.com/docs/agent-skills.html
ZeroClaw
ZeroClaw is an open-source, Rust-first AI agent runtime for local, provider-agnostic personal agents with Agent Skills support.
- Product: https://www.zeroclawlabs.ai/
- Skills documentation: https://docs.zeroclawlabs.ai/master/en/tools/skills.html
- Source code: https://github.com/zeroclaw-labs/zeroclaw
Gemini CLI
Gemini CLI is an open-source AI agent that brings the power of Gemini directly into your terminal.
- Product: https://geminicli.com
- Skills documentation: https://geminicli.com/docs/cli/skills/
- Source code: https://github.com/google-gemini/gemini-cli
Autohand Code CLI
Autohand Code CLI is an autonomous LLM-powered coding agent that lives in your terminal. It uses the ReAct (Reason + Act) pattern to understand your codebase, plan changes, and execute them with your approval.
- Product: https://autohand.ai/
- Skills documentation: https://autohand.ai/docs/working-with-autohand-code/agent-skills.html
- Source code: https://github.com/autohandai/code-cli
OpenCode
OpenCode is an open source agent that helps you write code in your terminal, IDE, or desktop.
- Product: https://opencode.ai/
- Skills documentation: https://opencode.ai/docs/skills/
- Source code: https://github.com/sst/opencode
OpenHands
OpenHands is the open platform for cloud coding agents. Scale from one to thousands of agents, open source, model-agnostic, and enterprise-ready.
- Product: https://openhands.dev/
- Skills documentation: https://docs.openhands.dev/overview/skills
- Source code: https://github.com/OpenHands/OpenHands
Mux
Mux makes it easy to run parallel coding agents, each with its own isolated workspace, right from your browser or desktop. Mux is open source and LLM provider-agnostic.
- Product: https://mux.coder.com/
- Skills documentation: https://mux.coder.com/agent-skills
- Source code: https://github.com/coder/mux
Cursor
Cursor is an AI editor and coding agent. Use it to understand your codebase, plan and build features, fix bugs, review changes, and work with the tools you already use.
- Product: https://cursor.com/
- Skills documentation: https://cursor.com/docs/context/skills
Amp
Amp is the frontier coding agent that lets you wield the full power of leading models.
- Product: https://ampcode.com/
- Skills documentation: https://ampcode.com/manual#agent-skills
Letta
Letta is the platform for building stateful agents: AI with advanced memory that can learn and self-improve over time.
- Product: https://www.letta.com/
- Skills documentation: https://docs.letta.com/letta-code/skills/
- Source code: https://github.com/letta-ai/letta
Firebender
Firebender is the first Android-native coding agent that writes features, tests them in the emulator, and fixes issues automatically.
- Product: https://firebender.com/
- Skills documentation: https://docs.firebender.com/multi-agent/skills
Goose
Goose is an open source, extensible AI agent that goes beyond code suggestions, install, execute, edit, and test with any LLM.
- Product: https://block.github.io/goose/
- Skills documentation: https://block.github.io/goose/docs/guides/context-engineering/using-skills/
- Source code: https://github.com/block/goose
GitHub Copilot
GitHub Copilot works alongside you directly in your editor, suggesting whole lines or entire functions for you.
- Product: https://github.com/
- Skills documentation: https://docs.github.com/en/copilot/concepts/agents/about-agent-skills
- Source code: https://github.com/microsoft/vscode-copilot-chat
VS Code
Visual Studio Code combines the simplicity of a code editor with what developers need for their core edit-build-debug cycle.
- Product: https://code.visualstudio.com/
- Skills documentation: https://code.visualstudio.com/docs/copilot/customization/agent-skills
- Source code: https://github.com/microsoft/vscode
Claude Code
Claude Code is an agentic coding tool that reads your codebase, edits files, runs commands, and integrates with your development tools. Available in your terminal, IDE, desktop app, and browser.
- Product: https://claude.ai/code
- Skills documentation: https://code.claude.com/docs/en/skills
Claude
Claude is Anthropic's AI, built for problem solvers. Tackle complex challenges, analyze data, write code, and think through your hardest work.
- Product: https://claude.ai/
- Skills documentation: https://platform.claude.com/docs/en/agents-and-tools/agent-skills/overview
OpenAI Codex
Codex is OpenAI's coding agent for software development.
- Product: https://developers.openai.com/codex
- Skills documentation: https://developers.openai.com/codex/skills/
- Source code: https://github.com/openai/codex
Piebald
Piebald is a desktop & web app that makes it easier than ever to do agentic development, while at the same time giving you complete control over the configuration, context, and flow.
- Product: https://piebald.ai
Factory
Factory is an AI-native software development platform that works everywhere you do. From IDE to CI/CD, delegate complete tasks like refactors, incident response, and migrations to Droids without changing your tools, models, or workflow.
- Product: https://factory.ai/
- Skills documentation: https://docs.factory.ai/cli/configuration/skills
pi
Pi is a minimal terminal coding harness. Adapt pi to your workflows, not the other way around.
- Product: https://shittycodingagent.ai/
- Skills documentation: https://github.com/badlogic/pi-mono/blob/main/packages/coding-agent/docs/skills.md
- Source code: https://github.com/badlogic/pi-mono
Databricks Genie Code
Genie Code is an autonomous AI partner purpose-built for data work in Databricks.
- Product: https://databricks.com/
- Skills documentation: https://docs.databricks.com/aws/en/assistant/skills
Agentman
Agentman is an agentic healthcare platform. It automates revenue cycle workflows using AI agents without sacrificing control. Every action is testable, traceable, and auditable.
- Product: https://agentman.ai/
- Skills documentation: https://agentman.ai/agentskills
TRAE
Trae is an adaptive AI IDE that transforms how you work, collaborating with you to run faster.
- Product: https://trae.ai/
- Skills documentation: https://www.trae.ai/blog/trae_tutorial_0115
- Source code: https://github.com/bytedance/trae-agent
Spring AI
Spring AI aims to streamline the development of applications that incorporate artificial intelligence functionality without unnecessary complexity.
- Product: https://docs.spring.io/spring-ai/reference
- Skills documentation: https://spring.io/blog/2026/01/13/spring-ai-generic-agent-skills/
- Source code: https://github.com/spring-projects/spring-ai
Roo Code
Roo Code puts an entire AI dev team right in your editor, outpacing closed tools with deep project-wide context, multi-step agentic coding, and unmatched developer-centric flexibility.
- Product: https://roocode.com
- Skills documentation: https://docs.roocode.com/features/skills
- Source code: https://github.com/RooCodeInc/Roo-Code
Mistral AI Vibe
Mistral Vibe is a command-line coding assistant powered by Mistral's models. It provides a conversational interface to your codebase, allowing you to use natural language to explore, modify, and interact with your projects through a powerful set of tools.
- Product: https://github.com/mistralai/mistral-vibe
- Skills documentation: https://github.com/mistralai/mistral-vibe
- Source code: https://github.com/mistralai/mistral-vibe
Command Code
Command Code is a coding agent that continuously learns your coding taste. Our meta neuro-symbolic AI model taste-1 with continuous reinforcement learning combines LLMs with your coding taste.
- Product: https://commandcode.ai/
- Skills documentation: https://commandcode.ai/docs/skills
Ona
Ona is a platform for background agents. Run a team of AI software engineers in the cloud. Orchestrated, governed, secured at the kernel.
- Product: https://ona.com
- Skills documentation: https://ona.com/docs/ona/agents-md#skills-for-repository-specific-workflows
VT Code
VT Code is an open-source coding agent with LLM-native code understanding and robust shell safety. Supports multiple LLM providers with automatic failover and efficient context management.
- Product: https://github.com/vinhnx/vtcode
- Skills documentation: https://github.com/vinhnx/vtcode/blob/main/docs/skills/SKILLS_GUIDE.md
- Source code: https://github.com/vinhnx/VTCode
Qodo
Qodo is an agentic code integrity platform for reviewing, testing, and writing code, integrating AI across development workflows to strengthen code quality at every stage.
- Product: https://www.qodo.ai/
- Skills documentation: https://www.qodo.ai/blog/how-i-use-qodos-agent-skills-to-auto-fix-issues-in-pull-requests/
Laravel Boost
Laravel Boost accelerates AI-assisted development by providing the essential guidelines and agent skills that help AI agents write high-quality Laravel applications that adhere to Laravel best practices.
- Product: https://github.com/laravel/boost
- Skills documentation: https://laravel.com/docs/12.x/boost#agent-skills
- Source code: https://github.com/laravel/boost
Emdash
Emdash is a provider-agnostic desktop app that lets you run multiple coding agents in parallel, each isolated in its own git worktree, either locally or over SSH on a remote machine.
- Product: https://emdash.sh
- Skills documentation: https://docs.emdash.sh/skills
- Source code: https://github.com/generalaction/emdash
Snowflake Cortex Code
Cortex Code is an AI-driven intelligent agent integrated into the Snowflake platform, optimized for complex data engineering, analytics, machine learning, and agent-building tasks.
- Product: https://docs.snowflake.com/en/user-guide/cortex-code/cortex-code
- Skills documentation: https://docs.snowflake.com/en/user-guide/cortex-code/extensibility#extensibility-skills
Kiro
Kiro helps you do your best work by bringing structure to AI coding with spec-driven development.
- Product: https://kiro.dev/
- Skills documentation: https://kiro.dev/docs/skills/
Workshop
Workshop is a cross-platform AI coding agent for building full applications. It supports multi-LLM models, sub-agents, custom agents, and skills, available as a desktop app, web app, and CLI.
- Product: https://workshop.ai/
- Skills documentation: https://docs.workshop.ai/core-concepts/working-with-the-agent#create-your-own-agents
Google AI Edge Gallery
Google AI Edge Gallery is the premier destination for running the world's most powerful open-source Large Language Models (LLMs) on your mobile device
- Product: https://github.com/google-ai-edge/gallery
- Skills documentation: https://github.com/google-ai-edge/gallery/tree/main/skills
- Source code: https://github.com/google-ai-edge/gallery
nanobot
nanobot is an ultra-lightweight, open-source personal AI agent. It runs across multiple platforms, terminal, Telegram, Discord, Slack, WeChat, and more, with built-in MCP support and a skills system for extensibility.
- Product: https://nanobot.wiki/
- Skills documentation: https://nanobot.wiki/docs/0.1.5/use-nanobot/skills
- Source code: https://github.com/HKUDS/nanobot
fast-agent
fast-agent is a simple, extendable way to interact with LLMs. Excellent for Coding, Evals, ACPX and Skills development.
- Product: https://fast-agent.ai/
- Skills documentation: https://fast-agent.ai/agents/skills/
- Source code: https://github.com/evalstate/fast-agent
bub
Bub is a lightweight, hook-first Python framework for channel-native agents that live alongside people.
- Product: https://bub.build/
- Skills documentation: https://bub.build/docs/build/skills/
- Source code: https://github.com/bubbuild/bub
Tabnine
Tabnine is an AI engineering platform that combines code assistants, agentic workflows, and enterprise context to help development teams build, review, and maintain software with context-aware AI, while keeping code private, secure, and fully under your control.
- Product: https://www.tabnine.com/
- Skills documentation: https://docs.tabnine.com/main/getting-started/tabnine-cli/features/agent-skills
Vita
Vita provides autonomous digital workers with virtual desktops to execute complex workflows. It learns your intent to automate end-to-end tasks like creating and posting engaging social media content.
- Product: https://www.vita-ai.net
- Skills documentation: https://www.vita-ai.net/docs/features/agent-skills
Superconductor
Superconductor is a multiplayer workspace for your team and coding agents. Run many agents in the cloud, build together in shared sessions, and ship faster with live app previews and guided code review.
- Product: https://superconductor.com/
- Skills documentation: https://superconductor.com/docs/project/mcp-and-skills
Deep Code
Deep Code is an open-source terminal AI coding assistant for the DeepSeek model, supporting deep thinking, reasoning effort control, and extending its capabilities with Skills and MCP.
- Product: https://deepcode.vegamo.cn/en
- Skills documentation: https://deepcode.vegamo.cn/en/docs/configuration/agent-skills
- Source code: https://github.com/lessweb/deepcode-cli
Pulumi Neo
Pulumi Neo is an AI agent that manages cloud infrastructure with Pulumi. It runs in Pulumi Cloud, the CLI, GitHub, and Slack, and works within your organization's policies and approvals.
- Product: https://www.pulumi.com/product/neo/
- Skills documentation: https://www.pulumi.com/docs/ai/skills/
When not to use it
The source does not list alternatives or exclusions. If you need an agent that does not support the Agent Skills format, you will have to rely on that product's native configuration or prompting mechanisms.
Limits and gotchas
The source does not list limitations or caveats. The list is a snapshot of 44 products; support may change, and not every product may implement the full specification. Always check the individual product's skills documentation for details on how to load and author skills.
What pairs with this
The source page is part of the Agent Skills documentation at https://agentskills.io. Related pages on that site cover the SKILL.md format specification, authoring guidelines, and best practices. The product-specific documentation links above are the best next step for learning how to use skills in a particular agent.
The #1 AI Newsletter
The most important ai updates, guides, and fixes — one weekly email.
No spam, unsubscribe anytime. Privacy policy