Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →DEPRECATED in v0.2.0 -- use browser-extract instead; this is a thin shim for backward compatibility, removed in v0.3.0
.claude/skills/ruvnet-browser-scrape/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✗→✓ | ▲ Improved | -50% | 0% |
| case-02 | ✗→✓ | ▲ Improved | -35% | 0% |
| case-03 | ✗→✓ | ▲ Improved | -14% | 0% |
| case-08 | ✗→✓ | ▲ Improved | -54% | 0% |
| case-04 | ✗→✓ | ▲ Improved | -34% | 0% |
> Deprecated since plugin v0.2.0. Removed in v0.3.0. > > Use browser-extract instead. It provides the same scraping capability plus: > > - RVF cognitive container per session (replayable, federatable) > - Mandatory AIDefence PII + prompt-injection gates > - Persistent browser-templates namespace for reusable recipes > - Automatic browser-selectors namespace updates so DOM drift is recoverable
| v0.1 invocation | v0.2 equivalent | |-----------------|-----------------| | /browser-scrape <url> | /browser-extract <url> | | /browser-scrape <url> (with template intent) | /browser-extract <url> --template <name> | | Manual selector storage in browser-patterns namespace | Automatic — browser-extract writes to browser-templates and browser-selectors |
This skill delegates to browser-extract. Calling it emits a deprecation notice and proceeds.
bash# This skill is intentionally minimal — it just points the agent at the new skill. echo "browser-scrape is deprecated; running browser-extract instead." >&2
The deprecation notice is captured in the agent's transcript so callers see the remediation. There is no behavior preserved here beyond the redirect — if you depended on a specific extraction shape, port to browser-extract and use --template to encode it.
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→pass | 9,559 | 4,059 | -58% | 1 | 1 | 0% | 2,321 | 1,161 | -50% | 0 | 0 | — |
case-02 | fail→pass | 5,707 | 2,082 | -64% | 1 | 1 | 0% | 1,123 | 726 | -35% | 0 | 0 | — |
case-03 | fail→pass | 6,661 | 4,095 | -39% | 1 | 1 | 0% | 1,259 | 1,089 | -14% | 0 | 0 | — |
case-08 | fail→pass | 7,946 | 2,543 | -68% | 1 | 1 | 0% | 1,509 | 696 | -54% | 0 | 0 | — |
case-04 | fail→pass | 7,295 | 2,781 | -62% | 1 | 1 | 0% | 1,400 | 930 | -34% | 0 | 0 | — |
case-05 | fail→pass | 14,044 | 2,318 | -83% | 1 | 1 | 0% | 2,768 | 774 | -72% | 0 | 0 | — |
case-06 | fail→pass | 7,960 | 2,637 | -67% | 1 | 1 | 0% | 1,230 | 782 | -36% | 0 | 0 | — |
case-07 | fail→pass | 10,372 | 2,131 | -79% | 1 | 1 | 0% | 1,996 | 731 | -63% | 0 | 0 | — |
case-17 | fail→pass | 8,272 | 3,920 | -53% | 1 | 1 | 0% | 1,676 | 840 | -50% | 0 | 0 | — |
case-09 | fail→pass | 12,472 | 2,023 | -84% | 1 | 1 | 0% | 2,446 | 748 | -69% | 0 | 0 | — |
case-10 | fail→pass | 11,784 | 1,857 | -84% | 1 | 1 | 0% | 2,102 | 694 | -67% | 0 | 0 | — |
case-11 | fail→pass | 8,290 | 3,959 | -52% | 1 | 1 | 0% | 1,572 | 1,122 | -29% | 0 | 0 | — |
case-12 | fail→pass | 5,824 | 1,571 | -73% | 1 | 1 | 0% | 1,153 | 660 | -43% | 0 | 0 | — |
case-13 | fail→pass | 13,384 | 4,183 | -69% | 1 | 1 | 0% | 2,516 | 1,155 | -54% | 0 | 0 | — |
case-14 | fail→pass | 11,019 | 3,462 | -69% | 1 | 1 | 0% | 2,018 | 965 | -52% | 0 | 0 | — |
case-15 | fail→pass | 6,329 | 2,033 | -68% | 1 | 1 | 0% | 1,173 | 735 | -37% | 0 | 0 | — |
case-16 | fail→pass | 7,792 | 2,306 | -70% | 1 | 1 | 0% | 1,406 | 852 | -39% | 0 | 0 | — |
case-18 | fail→pass | 9,094 | 1,361 | -85% | 1 | 1 | 0% | 1,760 | 572 | -68% | 0 | 0 | — |
case-19 | pass→pass | 7,103 | 1,801 | -75% | 1 | 1 | 0% | 1,274 | 716 | -44% | 0 | 0 | — |
case-20 | fail→pass | 7,213 | 4,157 | -42% | 1 | 1 | 0% | 1,308 | 1,093 | -16% | 0 | 0 | — |
case-21 | pass→pass | 5,563 | 3,677 | -34% | 1 | 1 | 0% | 1,256 | 1,177 | -6% | 0 | 0 | — |
case-22 | pass→pass | 4,611 | 2,823 | -39% | 1 | 1 | 0% | 972 | 913 | -6% | 0 | 0 | — |
case-23 | pass→pass | 5,327 | 5,195 | -2% | 1 | 1 | 0% | 1,212 | 1,548 | +28% | 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. 23 cases were attempted. The headline lift of +83 percentage points is the difference between those two pass rates over the 23 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.