菜单
Build, run, and review browser-using AI agents with Playwright, Browser Use, MCP browser tools, or hosted browser runtimes. Use for web navigation agents, form-filling, UI task automation, screenshots, DOM/vision checks, auth/session handling, and browser-task reliability reviews.
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。
Build and run lightweight regression evaluations for agents, tools, prompts, and workflows. Use when comparing agent versions, catching behavior drift, measuring pass rates over repeated runs, or turning production failures into replayable test cases.
Audit agent repositories, MCP configurations, tool schemas, prompts, and logs for common security risks: secret exposure, prompt injection payloads, tool poisoning, command execution, broad filesystem access, and unsafe auto-approval.
Inspect agent traces, tool-call logs, and OpenTelemetry/OpenInference-style span exports. Use when debugging why an agent skipped a tool, called the wrong tool, hit errors, exceeded latency budgets, or produced an unsupported answer.
Design and validate graph/state-machine agent workflows with explicit starts, terminal states, guarded cycles, human approval points, and side-effecting tool boundaries. Use when building LangGraph-style, multi-agent, or durable agent workflows.
Safely list, create, and extract zip/tar archives with path traversal checks. Use when packaging artifacts, unpacking downloaded files, or inspecting archive contents on a user's computer.
Read from and write to the system clipboard on macOS or Linux when clipboard commands are available. Use for transferring short text snippets between agent work and the user's desktop applications.
基于 SOC 职业分类
| name | browser-agent |
| description | Build, run, and review browser-using AI agents with Playwright, Browser Use, MCP browser tools, or hosted browser runtimes. Use for web navigation agents, form-filling, UI task automation, screenshots, DOM/vision checks, auth/session handling, and browser-task reliability reviews. |
| version | 1.0.0 |
| author | Zijian Guo |
| license | MIT |
| platforms | ["linux","macos"] |
| prerequisites | {"commands":["python3"]} |
| metadata | {"hermes":{"tags":["agent","browser","playwright","browser-use","web-automation","ui"]}} |
Use this skill when an agent needs to operate a real website rather than only fetch static HTML.
Browser agents are a fast-growing public category. Browser Use reports real-world browser task benchmarks and exposes custom tools, hosted/cloud execution, MCP, and authentication patterns. The production gap is reliability: screenshots, DOM state, session handling, CAPTCHAs, consent screens, and side effects must be handled deliberately.
~/.hermes/skills/browser-agent/scripts/browser_env_check.py
| Check | Why it matters |
|---|---|
| Python packages | Detects Browser Use and Playwright availability |
| Node commands | Detects Playwright CLI/npm availability |
| Browser binaries | Indicates whether a local browser can run |
| Environment variables | Warns about API keys needed by hosted runtimes |