Search
Model Context Protocol · By agent-sh
4 skills found.
Skills
Sort:BestMost starsTrending todayTrending this weekTrending this monthNewestRecently updatedName
| # | Skill | Repository | Stars | Used in | Tokens | Auto-check | Licence | Updated |
|---|---|---|---|---|---|---|---|---|
| 1 | Lets an agent observe and operate a local Linux desktop through the computer-use-linux MCP server or Pi tools: accessibility trees, screenshots, windows and input. | agent-sh/ | 675 | — | ~2.8k | Automated safety check: Pass | MIT | 2 days ago |
| 2 | 2.Agnix A skill your agent uses when user asks to 'lint agent configs', 'validate skills', 'check CLAUDE.md', 'validate hooks', 'lint MCP'. | agent-sh/ | 446 | — | ~874 | Automated safety check: Pass | Apache-2.0 | yesterday |
| 3 | Drives a hidden, agent-owned Linux desktop and browser over MCP for GUI testing and web automation without touching the user's real desktop. | agent-sh/ | 186 | — | ~2.1k | Automated safety check: Pass | MIT | 7 days ago |
| 4 | 4.Agnix A skill your agent uses when user asks to 'lint agent configs', 'validate skills', 'check CLAUDE.md', 'validate hooks', 'lint MCP'. | agent-sh/ | 446 | — | ~563 | Automated safety check: Pass | Apache-2.0 | yesterday |
