opencli-browser
Use when an agent needs to drive a real Chrome window via opencli — inspect a page, fill forms, click through logged-in flows, or extract data ad-hoc. Covers the selector-first target contract, compound form fields, stale-ref handling, network capture, and the agent-native envelopes the CLI returns. Not for writing adapters — see opencli-adapter-author for that.
- installs 8w
- 3,178
- 30-day movement
- starts with the next reading
- Related entries
- 1
- Connections
- 4
opencli-browser is a SKILL.md that teaches an AI coding agent to drive a real Chrome window through the opencli CLI. It documents the selector-first target contract, session lifecycle, structured success/error envelopes, compound form controls, network capture, and troubleshooting for browser automation commands.
Reach for it when your agent needs to inspect pages, fill forms, click through logged-in flows, or extract data from a live browser instead of guessing at CLI flags.
Use it to
- Inspect a page's state before interacting with it
- Fill compound date, select, and file form fields
- Click through logged-in multi-step flows
- Capture network responses during a flow
- Extract page content as Markdown with web read
For AI coding agents automating a real Chrome browser
- Host repository
- jackwener/OpenCLI
- Installs, lifetime
- 19k
- Installs, 8 weeks
- 3,178
- Allowed tools
- Bash(opencli:*), Read, Edit, Write
- Host stars
- 29k
- Host language
- JavaScript