agent-browser
agent-browser
agent-browser is the fresh-session deterministic browser verification skill in this repo.
Use it when the real need is: open a clean disposable browser, inspect the current page state, perform one concrete action, and prove what changed with explicit evidence. The key behaviors are isolation, stable refs from snapshots, and an observe → act → observe verification loop.
When to use this skill
Use agent-browser when the task needs one or more of these:
- a clean reproducible browser session instead of the user's real browser profile
- deterministic form checks, navigation checks, and page-state verification
- structured snapshot refs (
@e1,@e2, …) before interacting with the page - explicit before/after evidence such as snapshot diffs, screenshots, or extracted text
- CI-style or automation-friendly browser checks where reproducibility matters more than session continuity
- isolated parallel browser tasks with named sessions
Do not use agent-browser by default for:
More from akillness/skills-template
backend-testing
>
71data-analysis
>
54plannotator
>
35task-planning
Plan and organize software development tasks effectively. Use when breaking down features, creating user stories, or planning sprints. Handles task breakdown, user stories, acceptance criteria, and backlog management.
35omc
Use when you need Teams-first multi-agent orchestration in Claude Code. Triggers on: omc, autopilot, ralph, ulw, ccg, team. 29+ specialized agents, smart model routing (Haiku→Opus), persistent execution loops, skill layers, real-time HUD.
33vibe-kanban
Manage AI coding agents on a visual Kanban board. Run parallel agents through a To Do→In Progress→Review→Done flow with automatic git worktree isolation and GitHub PR creation.
32