Skill comparison
Compare agent skills before installing.
Comparing 4 skills
Use this as a shortlist, then open the skill detail page before adopting.
Decision summary
Cua is the strongest overall pick here because it has a 100/100 readiness score and fits Local desktop.
Strongest overall
Cua
Use this as a leading candidate, then validate the README and install path in your own agent stack.
Fastest prototype
Cua
Best first install candidate based on install readiness and adoption.
Freshest repo
Cua
Most recent maintenance signal among this shortlist.
| Signal | OS Agent Survey This is the repo for the paper "OS Agents: A Survey on MLLM-based Agents for Computer, Phone and Browser Use" (ACL 2025 Oral). | ShowUI [CVPR 2025] Open-source, End-to-end, Vision-Language-Action model for GUI Agent & Computer Use. | Cua Open-source infrastructure for Computer-Use Agents. Sandboxes, SDKs, and benchmarks to train and evaluate AI agents that can control full desktops (macOS, Linux, Windows). | Fara Fara-7B: An Efficient Agentic Model for Computer Use |
|---|---|---|---|---|
| Quality | 61/100 Promising | 98/100 Excellent | 100/100 Excellent | 100/100 Excellent |
| Decision verdict | 51/100 Needs manual review Do a manual repository review before adding this to an agent workflow. | 100/100 Production-ready Use this as a leading candidate, then validate the README and install path in your own agent stack. | 100/100 Production-ready Use this as a leading candidate, then validate the README and install path in your own agent stack. | 100/100 Production-ready Use this as a leading candidate, then validate the README and install path in your own agent stack. |
| Adoption | 485 stars 0 installs | 1.9K stars 0 installs | 18K stars 0 installs | 5.5K stars 0 installs |
| Freshness | Aug 16, 2025 | Apr 24, 2026 | Jun 13, 2026 | May 29, 2026 |
| Use-case fit | ||||
| Stack fit | ||||
| Platform hints | Computer Use, Claude Code, Browser agents | Python, Computer Use, Claude Code | HTML, Computer Use, Claude Code | Python, Computer Use, Claude Code, Browser agents |
| Warnings | No OpenAgentSkill engagement data yet | No OpenAgentSkill engagement data yet | No major risk signals from current metadata | No OpenAgentSkill engagement data yet |
| Best for | Local desktop workflows · Claude Code teams · builders willing to evaluate younger projects | Local desktop workflows · Claude Code teams · teams that value GitHub adoption signals | Local desktop workflows · Claude Code teams · teams that value GitHub adoption signals | Local desktop workflows · Claude Code teams · teams that value GitHub adoption signals |
| Not ideal for | teams that need a vendor-supported SLA · high-compliance environments without internal security review | teams that need a vendor-supported SLA · high-compliance environments without internal security review | teams that need a vendor-supported SLA · high-compliance environments without internal security review | teams that need a vendor-supported SLA · high-compliance environments without internal security review |
| OpenAgentSkill engagement | 0 views 0 install copies | 0 views 0 install copies | 3 views 0 install copies | 0 views 0 install copies |
| Install | $ npx skills add OS-Agent-Survey/OS-Agent-Survey | $ npx skills add showlab/ShowUI | $ npx skills add trycua/cua | $ npx skills add microsoft/fara |