菜单
Browser automation for AI agents. Use when agents need to navigate pages, fill forms, take screenshots, or verify UI.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Build applications where agents are first-class citizens. Use when designing tools, APIs, or features that agents will interact with.
Explore requirements and approaches through collaborative dialogue before planning. Use before ce-plan for new features.
Document solved problems to compound team knowledge. Use after completing any non-trivial feature or bug fix.
Transform feature descriptions into structured implementation plans grounded in repo patterns and research. Use when starting any non-trivial work.
Structured multi-agent code review with tiered personas, confidence-gated findings, and merge/dedup pipeline. Use during the Review phase.
Execute work plans efficiently with atomic commits, verification checkpoints, and state tracking. Use during the Work phase.
| name | agent-browser |
| description | Browser automation for AI agents. Use when agents need to navigate pages, fill forms, take screenshots, or verify UI. |
| slug | agent-browser |
| tags | ["tools","browser"] |
| metadata | {"sources":[{"kind":"github-dir","repo":"EveryInc/compound-engineering-plugin","path":"plugins/compound-engineering/skills/agent-browser","commit":"main","url":"https://github.com/EveryInc/compound-engineering-plugin"}]} |
Referenced from compound-engineering plugin. Provides browser automation capabilities for testing and verification.
