Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Replay a recorded session trajectory against the same URL or a mutated variant; uses browser-selectors embedding similarity to recover from DOM drift
.claude/skills/ruvnet-browser-replay/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-07 | ✗→✓ | ▲ Improved | -67% | 0% |
| case-04 | ✗→✓ | ▲ Improved | -41% | 0% |
| case-05 | ✗→✓ | ▲ Improved | -63% | 0% |
| case-06 | ✗→✓ | ▲ Improved | -23% | 0% |
| case-08 | ✗→✓ | ▲ Improved | -14% | 0% |
Re-drive a recorded session trajectory. Used for regression testing, deterministic re-runs, and as the verification path that browser-record plus browser-selectors actually produces something replayable.
> This skill is the load-bearing assumption of the v0.2.0 architecture. ADR-0001 Verification §4 requires ≥80% replay success across 10 distinct sites of varying drift profiles before the proposal moves from Proposed → Accepted. If you find replay unreliable, capture the failure modes in findings.md and report them up the ADR.
browser-screenshot-diff./ruflo-browser fork) and replaying the parent before mutating.bash npx -y ruvector@0.2.25 rvf status <session-id>.rvf
bash Read .../trajectory.ndjson Each line is {ts, action, args, selector, result}.
mcp__plugin_ruflo-core_ruflo__browser_open (target URL = original or --url override).browser_click, browser_fill, browser_eval, etc.) with the recorded args.browser-selectors namespace for an embedding-similar selector for the same <host>:<intent> and retry once:bash npx -y @claude-flow/cli@latest memory search --namespace browser-selectors \ --query "<host> <intent>" --limit 5
rvf derive).--tolerance). Verdict goes into findings.md.--mutate to inject expected variation or pin to a fixture.browser-screenshot-diff against the parent session id.| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-07 | fail→pass | 14,100 | 4,543 | -68% | 1 | 1 | 0% | 2,570 | 851 | -67% | 0 | 0 | — |
case-22 | pass→pass | 18,327 | 8,725 | -52% | 1 | 1 | 0% | 3,714 | 2,421 | -35% | 0 | 0 | — |
case-01 | fail→fail | 4,952 | 7,087 | +43% | 1 | 1 | 0% | 305 | 948 | +211% | 0 | 0 | — |
case-02 | fail→fail | 9,621 | 6,810 | -29% | 1 | 1 | 0% | 1,612 | 1,091 | -32% | 0 | 0 | — |
case-03 | fail→fail | 10,397 | 12,218 | +18% | 1 | 1 | 0% | 2,137 | 3,019 | +41% | 0 | 0 | — |
case-04 | fail→pass | 11,356 | 2,273 | -80% | 1 | 1 | 0% | 1,844 | 1,096 | -41% | 0 | 0 | — |
case-05 | fail→pass | 12,697 | 2,820 | -78% | 1 | 1 | 0% | 2,317 | 867 | -63% | 0 | 0 | — |
case-06 | fail→pass | 6,648 | 1,498 | -77% | 1 | 1 | 0% | 1,123 | 864 | -23% | 0 | 0 | — |
case-08 | fail→pass | 15,871 | 4,851 | -69% | 1 | 1 | 0% | 1,170 | 1,006 | -14% | 0 | 0 | — |
case-09 | fail→pass | 11,940 | 1,640 | -86% | 1 | 1 | 0% | 1,878 | 880 | -53% | 0 | 0 | — |
case-10 | pass→pass | 7,400 | 2,947 | -60% | 1 | 1 | 0% | 1,174 | 1,119 | -5% | 0 | 0 | — |
case-11 | fail→pass | 22,984 | 4,057 | -82% | 1 | 1 | 0% | 1,985 | 1,349 | -32% | 0 | 0 | — |
case-12 | fail→pass | 36,913 | 1,180 | -97% | 1 | 1 | 0% | 3,283 | 811 | -75% | 0 | 0 | — |
case-13 | fail→pass | 6,372 | 1,558 | -76% | 1 | 1 | 0% | 1,122 | 890 | -21% | 0 | 0 | — |
case-14 | fail→fail | 12,621 | 3,869 | -69% | 1 | 1 | 0% | 2,265 | 1,373 | -39% | 0 | 0 | — |
case-15 | fail→pass | 6,204 | 1,600 | -74% | 1 | 1 | 0% | 948 | 877 | -7% | 0 | 0 | — |
case-16 | fail→fail | 19,252 | 1,524 | -92% | 1 | 1 | 0% | 1,232 | 879 | -29% | 0 | 0 | — |
case-17 | fail→fail | 7,111 | 2,189 | -69% | 1 | 1 | 0% | 1,215 | 1,023 | -16% | 0 | 0 | — |
case-18 | fail→pass | 5,943 | 9,417 | +58% | 1 | 1 | 0% | 1,071 | 853 | -20% | 0 | 0 | — |
case-19 | fail→pass | 13,557 | 1,414 | -90% | 1 | 1 | 0% | 2,469 | 850 | -66% | 0 | 0 | — |
case-20 | pass→pass | 15,063 | 7,452 | -51% | 1 | 1 | 0% | 2,861 | 2,106 | -26% | 0 | 0 | — |
case-21 | pass→pass | 12,363 | 14,325 | +16% | 1 | 1 | 0% | 2,625 | 3,640 | +39% | 0 | 0 | — |
DecimalAI ran this skill against gemini-3.6-flash twice over the same eval suite — once with the skill loaded and once without — and compared the two runs case by case. 22 cases were attempted, and 18 counted toward the lift figure. The other 4 produced results that are not comparable between the two arms, so they are excluded from the headline rather than averaged into it. The headline lift of +55 percentage points is the difference between those two pass rates over the 18 comparable cases.
Without the skill loaded, the model failed this case. With it loaded, the same prompt on the same model passed. This is one improved case from the latest verified run; every case, including any that regressed, is in the table above.
Other measured skills in the registry, with their headline benchmark lift.