claudegoodies
Skill

browser-test

From ruvnet

UI test recipe -- composes browser-record (capture) + browser-replay (verify) so every test produces a replayable RVF artifact, not an ephemeral run

Drives browser UI interactions via MCP tools and records them into a replayable RVF session artifact.

Use it when

  • Verifying UI flows or frontend changes in a real browser
  • Creating a baseline session for future regression diffs
  • Re-running a stored test session when CI fails without re-authoring
  • Comparing screenshots against a prior session id

Skip it if

  • Requires claude-flow MCP server with browser_* and aidefence_is_safe tools
  • Depends on RVF container, ruvector trajectory, and AgentDB indexing infrastructure
  • Not a standalone tool -- composes browser-record and browser-replay skills

Facts

Repository
ruvnet/ruflo
Status
Actively maintained
Last commit
Declared tools
mcp__claude-flow__browser_open mcp__claude-flow__browser_cli
Source file
plugins/ruflo-browser/skills/browser-test/SKILL.md

Source preview

The instructions Claude Code reads when this skill runs.

# Browser Test

Automated UI testing. **Now backed by a recorded RVF session container** instead of an ephemeral run, so every test produces a replayable artifact.

## When to use

- Verifying UI functionality, user flows, or that frontend changes work in a real browser.
- Producing a baseline session that future regressions can diff against.
- Re-running a stored test session when CI fails (no need to re-author the test).

## Steps

1. **Record the test run** by composing `browser-record`:
   - Allocates an RVF container with `--kind browser-session`.
   - Begins a ruvector trajectory.
2. **Drive interactions** — `browser_open`, `browser_click`, `browser_fill`, `browser_type`, `browser_select`. Each action emits a `trajectory-step`.
3. **Wait** for elements / network idle via `browser_wait` before assertions.
4. **Validate** with `browser_get-text` / `browser_get-value` / `browser_get-title` / `browser_get-url`. Validation outcomes go into `findings.md` inside the RVF container.
5. **Screenshot** before / after key interactions for visual regression. Filenames follow `<step-id>.png`.
6. **Snapshot** the accessibility tree at navigation boundaries.
7. **End** the session: `trajectory-end --verdict pass|fail`, `rvf compact`, AgentDB index in `browser-sessions`.
8. **(Optional) Diff against `--against <prior-session-id>`**: invoke `browser-screenshot-diff` to compare the new run
View full source on GitHub →

Other skills