BjornMelin/dev-skills / archive/skills/browser-workbench-setup
browser-workbench-setup
VerifiedSet up browser automation and UI QA for a new repository using playwright-interactive as the primary interactive tool and agent-browser as the secondary CLI smoke-check tool. Use when a user wants to bootstrap browser testing, screenshots, auth-state reuse, or local UI debugging conventions in a fresh repo.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 8.1 KB |
| agents/openai.yaml | config | 631 B |
| archive.json | config | 1.1 KB |
| references/agent-browser.md | markdown | 3.2 KB |
| references/auth-auth0.md | markdown | 3.5 KB |
| references/auth-clerk.md | markdown | 3.0 KB |
| references/auth-neon.md | markdown | 3.3 KB |
| references/auth-supabase.md | markdown | 3.2 KB |
| references/playwright-interactive.md | markdown | 2.6 KB |
references/agent-browser.md
View on GitHub# Agent Browser Setup
Use this file when configuring the secondary CLI browser workflow.
## Purpose
`agent-browser` is the secondary tool for:
- quick smoke checks
- annotated screenshots
- accessibility-tree snapshots
- fast console and page-error reads
- lightweight DOM or screenshot diffs
Official source:
- https://github.com/vercel-labs/agent-browser
Key upstream capabilities from the README:
- session names for saved state
- persistent profiles
- annotated screenshots
- console and page error inspection
- snapshot and screenshot diff commands
## Install and Baseline
Install once at the user level and install Chromium:
```bash
agent-browser install
```
On Linux, if needed:
```bash
agent-browser install --with-deps
```
## User-Level Config
Preferred user config at `~/.agent-browser/config.json`:
```json
{
"headed": true,
"contentBoundaries": true,
"maxOutput": 50000
}
```
This belongs outside the repo.
## Repo-Level Convention
Preferred repo artifact directory:
- `output/agent-browser/`
Ignore it in git:
```gitignore
output/agent-browser/
```
## Persistence Standard
Choose one of these:
- `--profile <path>` when you want full browser persistence including cookies, local storage, IndexedDB, and service workers
- `--session <name> --restore` when you want lighter automatic session restore through agent-browser's saved state
Preferred defaults for repo work:
- quick repeated local UI checks: `--profile ./output/agent-browser/profile`
- lightweight smoke path reuse: `--session <repo-name> --restore`
> Compatibility: the legacy `--session-name <name>` flag is accepted as an alias for `--session <name> --restore` but is deprecated; prefer the canonical form.
Use profiles when auth flows are complex or rely on richer browser state.
## Retention and rotation
Rotate or delete saved agent-browser state when switching users, rotating credentials, after a security incident, or on a regular schedule:
- set `AGENT_BROWSER_ENCRYPTION_KEY` (a 64-character hex value) to enable AES-256-GCM at-rest encryption of state files
- set `AGENT_BROWSER_STATE_EXPIRE_DAYS` (default `30`) to auto-purge state older than the window
- run the `close` command (or `--session <name> close`) to terminate a session explicitly when finished
- delete profiles and `storageState` artifacts you no longer need; they are gitignored for a reason
## Auth Handling
For most real apps, sign in normally once, then persist the authenticated state with a profile or session name.
Do not rely on the credential vault flow unless the app uses a simple username/password form that the CLI can drive cleanly. For OAuth-heavy or redirect-heavy apps, browser-state persistence is more reliable.
## Recommended Commands
Quick smoke:
```bash
agent-browser --profile ./output/agent-browser/profile open http://127.0.0.1:3000
agent-browser snapshot -i
agent-browser console
agent-browser errors
agent-browser screenshot --annotate ./output/agent-browser/home.png
```
Reuse session later:
```bash
agent-browser --profile ./output/agent-browser/profile open http://127.0.0.1:3000/dashboard
```
## Role Split
If the task becomes stateful, complex, auth-heavy, or visually subtle, switch to `playwright-interactive`.
Do not force `agent-browser` to be the primary debugger.
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| finishing-a-development-branchobra/superpowersUse when implementation is complete, all tests pass, and you need to decide how to integrate the work | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| systematic-debuggingobra/superpowersUse when encountering any bug, test failure, or unexpected behavior, before proposing fixes | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| test-driven-developmentobra/superpowersUse when implementing any feature or bugfix, before writing implementation code | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| skill-creatoranthropics/skillsCreate new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy. | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |