2026-05
This Claude Code skill adds a platform-neutral browser automation capability to the open-browser-use repository, allowing AI agents to control web browsers programmatically. The skill includes trigger metadata, core workflows, safety rules, CLI usage examples, and tab lifecycle management, with installation and technical details isolated in separate reference documents to keep the main skill guide focused and accessible.
git clone --depth 1 https://github.com/iFurySt/open-browser-use /tmp/2026-05 && cp -r /tmp/2026-05/docs/histories/2026-05/20260509-1507-open-browser-use- ~/.claude/skills/2026-0520260509-1507-open-browser-use-skill.md
## [2026-05-09 15:07] | Task: add Open Browser Use skill ### Execution Context - **Agent ID**: `Codex` - **Base Model**: `GPT-5` - **Runtime**: `Codex CLI` ### User Query > Add `./skills/open-browser-use` based on the bundled Chrome skill, but adapt it for this open-source, platform-neutral browser plugin that is a superset for all AI agents. Keep one-time installation details in references and make `SKILL.md` an index plus usage guide. ### Changes Overview **Scope:** Agent skill documentation and repository architecture docs. **Key Actions:** - **[Skill]**: Added `skills/open-browser-use/SKILL.md` with trigger metadata, core workflow, safety rules, common CLI usage, tab lifecycle guidance, and reference index. - **[References]**: Added installation, SDK/protocol, and troubleshooting references so larger or one-time details load only when needed. - **[Docs Sync]**: Added `skills/open-browser-use/` to the architecture structure. ### Design Intent The bundled Chrome skill is Codex.app-specific and assumes plugin UI repair paths, Node REPL bootstrap, and Codex Chrome Extension naming. Open Browser Use needs a reusable skill that speaks to any AI agent runtime, points to the public CLI/SDK/protocol surface, and keeps high-volume setup details out of the main skill body. ### Files Modified - `skills/open-browser-use/SKILL.md` - `skills/open-browser-use/agents/openai.yaml` - `skills/open-browser-use/references/installation.md` - `skills/open-browser-use/references/sdk-and-protocol.md` - `skills/open-browser-use/references/troubleshooting.md` - `docs/ARCHITECTURE.md` - `docs/histories/2026-05/20260509-1507-open-browser-use-skill.md`
Browser automation for the user's Chrome browser. Use for browser tasks that require the user's cookies, logged-in sessions, existing tabs, extensions, or remote authenticated sites.
Platform-neutral guidance for using Open Browser Use, the open-source Chrome automation stack for AI agents. Use when an agent needs to install, verify, troubleshoot, or operate Open Browser Use through its browser extension, native CLI, JavaScript SDK, Python SDK, Go SDK, or Browser Use style JSON-RPC methods; use for tasks involving real Chrome tabs, user tab claiming, CDP commands, downloads, file choosers, clipboard helpers, or session cleanup.