agentic-evals

Run the agentic evaluation repo for a target skill. Use when asked to execute repo-defined suites, collect evidence, write per-case results, and produce a short audit report for the target skill. Also supports evaluation modes: AB tests, subjective scoring, and vendor comparisons via evaluation YAML files in the eval repo.

Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to "open a website", "fill out a form", "click a button", "take a screenshot", "scrape data from a page", "test this web app", "login to a site", "automate browser actions", or any task requiring programmatic web interaction.