메뉴
Drive a real Chromium-based browser from an agent loop. Use when a task needs to navigate web pages, fill forms, scrape rendered HTML, or take screenshots.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
SOC 직업 분류 기준
Inventory and explore agent skills installed on the local machine via the `skillview` CLI. Use when asked to discover what skills exist, list SKILL.md files across host agents (claude/codex/cursor/agents), find duplicates between roots, rank skills by cross-agent usage in session logs, or audit for broken frontmatter. JSON output by default.
Skill that lives under the `.agents/` generic root and exercises the agents-generic classification path. Distinctive name for usage scanning purposes.
Investigate tabular data sets with pandas-style operations. Use when asked to explore a CSV, summarize a dataset, or run quick statistics over a table.
Shared cooking recipe definition kept in multiple agent installs so any host can answer recipe questions consistently.
Slightly drifted variant of a baking recipe used to validate that near-duplicate detection clusters skills that share most of their content but not all of it.
Secondary-tier skill (filename is `skill.md`, not `SKILL.md`) used to verify tier classification and that secondary skills still get discovered + validated.
| name | agent-browser |
| description | Drive a real Chromium-based browser from an agent loop. Use when a task needs to navigate web pages, fill forms, scrape rendered HTML, or take screenshots. |
A browser automation harness designed for autonomous agents. Maintains a persistent session across tool calls, exposes a CLI subcommand surface, and returns structured JSON the calling agent can parse.
agent-browser open https://example.com
agent-browser screenshot --out /tmp/page.png
agent-browser fill '#email' user@example.com
The browser stays alive between invocations until the session is closed explicitly, so navigation state survives across multiple agent steps.