opencli-browser
Installation
Summary
Drive a real Chrome window to inspect pages, fill forms, click through flows, and extract data.
- Selector-first target contract: interact via numeric refs (resilient to DOM drift) or CSS selectors, with structured
match_levelfeedback (exact,stable,reidentified) on every action - Session lifecycle management: use stable session names for multi-step flows, bind existing tabs for logged-in pages, and leverage idle timeouts or explicit
closefor cleanup - Compound form metadata: date/time/select/file controls expose format strings, option lists (capped at 50), and current values—use these instead of regex-guessing or blind clicks
- Network capture and extraction: inspect API responses by shape, fetch full bodies on demand, or use
extractwith continuation cursors for long-form content - Structured error codes and candidates: branch on
code(not message strings), and usecandidatesoravailablearrays to recover from ambiguous selectors or missing options
SKILL.md
opencli-browser
The first reader of this CLI is an agent, not a human. Every subcommand returns a structured envelope that tells you exactly what matched, how confident the match is, and what to do if it didn't. Lean on those envelopes — do not guess.
This skill is for driving a live browser to accomplish an agent task. If you are building a reusable adapter under ~/.opencli/clis/<site>/ use opencli-adapter-author instead.
Prerequisites
opencli doctor
Until doctor is green, nothing else will work. Typical failures: Chrome not running, extension not installed, debug port blocked by 1Password / other extensions. The doctor output tells you which.