Agent Skills
Open folder format (a SKILL.md plus optional scripts and files) for packaging instructions an agent loads on demand.
Reference by Originally developed by Anthropic, released as an open standard
About
Use cases: prompt-engineering
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
About the protocol
- Specification
- agentskills.io/specification
- Maintainer
- Originally developed by Anthropic, released as an open standardagentskills.io
- Governance
- Agentic AI Foundation (Linux Foundation) projectaaif.io
- Launched
- 2025-10-16anthropic.com
- Published as an open standard for cross-platform use on 2025-12-18. anthropic.com
- Client showcase lists Claude Code, Codex, Gemini CLI, GitHub Copilot, Cursor, goose and others. agentskills.io
Listings that use it
124,017 visible listings declare Agent Skills: 123,917 skills, 83 agents, 17 harnesses & sdks.
Skills
- 0.891score
diagnosing-superpowers
obra
Use when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't…
SkillAFreshness: A★ 304.6KClaude Code +9 - 0.891score
executing-plans
obra
Use when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool…
SkillAFreshness: A★ 304.6KClaude Code +9 - 0.891score
ui-ux-pro-max
nextlevelbuilder
UI/UX design intelligence for web, mobile, and desktop.
SkillAFreshness: A★ 139.9KClaude Code +9 - 0.891score
reverse-engineer-anything
morluto
Reverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of…
SkillAFreshness: A★ 377.4KClaude Code +9 - 0.891score
cloud
browser-use
Documentation reference for using Browser Use Cloud — the hosted API and SDK for browser automation.
SkillAFreshness: A★ 119KClaude Code +9 - 0.891score
version-bump
thedotmack
Automated semantic versioning and release workflow for Claude Code plugins.
SkillAFreshness: A★ 102.8KClaude Code +9
Agents
- 0.740score
Hermes Agent
Nous Research
Self-hosted agent from Nous Research that builds skills from experience and is reachable from the terminal and chat apps
AgentAFreshness: A★ 256.8K - 0.735score
DeerFlow
ByteDance
Open-source super agent harness that runs sub-agents, memory, sandboxes and skills for research, coding and content tasks lasting minutes to hours.
AgentAFreshness: A★ 84.4K - 0.732score
Cline
Cline Bot Inc.
Open-source coding agent for VS Code, JetBrains, the terminal and a desktop app that asks for approval before each action
AgentAFreshness: A★ 70.8K - 0.731score
Open Interpreter
Open Interpreter
Terminal coding agent, forked from OpenAI's Codex, tuned for low-cost open models and compatible with ACP editors
AgentAFreshness: A★ 68.7K - 0.729score
Gemini CLI
Google
Open-source terminal agent that queries and edits codebases and automates tasks with Gemini models
AgentAFreshness: A★ 107.7K↓ 231.3K/wk - 0.728score
Goose
Agentic AI Foundation (Linux Foundation)
Open-source general-purpose agent with a desktop app, CLI and API that works with many LLM providers and MCP extensions
AgentAFreshness: A★ 55.6K
Harnesses & SDKs
- 0.787score
trueforge
truefoundry
Open-source agent harness that runs the model loop for you, with MCP tools, skills, sandboxing, approvals and a chat UI.
HarnessAFreshness: A★ 6.4K - 0.700score
AgentScope
Alibaba Tongyi Lab
Python agent framework from Alibaba that lets the model drive tool use, with team pipelines, MCP, agent skills, A2A, memory and tracing.
HarnessAFreshness: A★ 33.8K↓ 50.9K/wk - 0.667score
OGX (formerly Llama Stack)
OGX
OpenAI-compatible agentic API server for inference, vector stores, files and skills, on any model or infrastructure.
HarnessAFreshness: A★ 8.4K↓ 14.2K/wk - 0.665score
RubyLLM
Carmine Paolino
Ruby AI framework with one API for chat, tools, agents, streaming, embeddings and Rails integration across many providers.
HarnessAFreshness: A★ 4.5K - 0.662score
fast-agent
evalstate
CLI-first Python agent framework and coding agent with MCP, A2A and Agent Skills support, live streaming and human input.
HarnessAFreshness: A★ 3.9K↓ 19.5K/wk - 0.657score
Stirrup
ArtificialAnalysis
Lightweight Python framework and starting template for agents that let the model choose its own approach to each task.
HarnessAFreshness: A★ 667↓ 65.3K/wk
Signals
- Stars
- 26,562
- Forks
- 1,955
- Open issues
- 49
- Contributors
- 42
- Last commit
- Aug 9, 2026 (2 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- Apache-2.0
- Repository
- github.com/agentskills/agentskills
- Website
- agentskills.io/home
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
Cite this page
Agent Skills. Agent Mart. https://agentmart.dev/reference/agent-skills (last updated 2026-10-24)