Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Create a minimal working Bright Data example. Use when starting a new Bright Data integration, testing your setup, or learning basic Bright Data API patterns. Trigger with phrases like "brightdata hello world", "brightdata example", "brightdata quick start", "simple brightdata code".
.claude/skills/jeremylongshore-brightdata-hello-world/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-03 | ✗→✓ | ▲ Improved | 9% | 0% |
| case-01 | ✗→✓ | ▲ Improved | 6% | 0% |
| case-10 | ✗→✓ | ▲ Improved | 3% | 0% |
| case-12 | ✗→✓ | ▲ Improved | 1% | 0% |
| case-15 | ✗→✓ | ▲ Improved | 2% | 0% |
Run the smallest possible request against Bright Data's test endpoint. Keep proxy credentials out of the URL and process output, inspect current x-brd-* and Proxy-Status headers, and stop after one bounded proof.
geo.brdtest.com from the test environmentRead the runbook and Grep the allowlist for geo.brdtest.com. Refuse arbitrary or authenticated targets for this proof.
Pass proxy authentication separately from the proxy host so the credential does not appear in the URL.
bash# 33335 is Bright Data's documented proxy gateway port. curl --silent --show-error --include \ --proxy http://brd.superproxy.io:33335 \ --proxy-user "$BRIGHTDATA_PROXY_USERNAME:$BRIGHTDATA_PROXY_PASSWORD" \ https://geo.brdtest.com/welcome.txt
Record the HTTP status plus redacted Proxy-Status, x-brd-err-code, x-brd-error, and x-brd-err-msg values. Never retain the proxy authorization header or full username.
Store the timestamp, zone alias, target, result class, and owner decision. A successful test proves connectivity only; it does not authorize production collection.
Use Read and Grep to confirm the approved target and redaction policy. Use Bash(curl:) for exactly the bounded Bright Data test request shown here. Do not write target content, rotate identities, or retry policy denials.
Use a dedicated development zone and run one request to geo.brdtest.com. A 200 with expected provider metadata is a connectivity pass. A 407 is an access failure; a policy 403 is a stop condition, not a reason to switch networks.
| Failure | Meaning | Response | |---------|---------|----------| | 407 with client_10000 or related code | Invalid or missing zone credentials | Verify the zone binding without printing credentials | | Policy 403 | Target or network is not permitted | Stop and escalate to the authorization owner | | 429 | Account, target, or per-IP throttling | Stop the smoke test and follow the rate-control workflow |
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-03 | fail→pass | 10,710 | 6,249 | -42% | 1 | 1 | 0% | 2,119 | 2,305 | +9% | 0 | 0 | — |
case-01 | fail→pass | 12,471 | 9,355 | -25% | 1 | 1 | 0% | 2,472 | 2,621 | +6% | 0 | 0 | — |
case-02 | fail→fail | 10,522 | 7,317 | -30% | 1 | 1 | 0% | 2,282 | 2,699 | +18% | 0 | 0 | — |
case-04 | pass→pass | 7,503 | 3,747 | -50% | 1 | 1 | 0% | 1,458 | 1,815 | +24% | 0 | 0 | — |
case-05 | pass→pass | 6,816 | 2,549 | -63% | 1 | 1 | 0% | 1,197 | 1,579 | +32% | 0 | 0 | — |
case-06 | pass→pass | 12,953 | 8,938 | -31% | 1 | 1 | 0% | 2,471 | 2,787 | +13% | 0 | 0 | — |
case-07 | pass→pass | 13,037 | 4,947 | -62% | 1 | 1 | 0% | 2,132 | 1,944 | -9% | 0 | 0 | — |
case-08 | pass→pass | 9,907 | 3,951 | -60% | 1 | 1 | 0% | 1,754 | 1,769 | +1% | 0 | 0 | — |
case-09 | pass→pass | 13,355 | 3,375 | -75% | 1 | 1 | 0% | 2,130 | 1,615 | -24% | 0 | 0 | — |
case-10 | fail→pass | 10,951 | 5,475 | -50% | 1 | 1 | 0% | 2,062 | 2,125 | +3% | 0 | 0 | — |
case-11 | pass→pass | 10,826 | 3,501 | -68% | 1 | 1 | 0% | 1,865 | 1,706 | -9% | 0 | 0 | — |
case-12 | fail→pass | 7,385 | 1,776 | -76% | 1 | 1 | 0% | 1,317 | 1,324 | +1% | 0 | 0 | — |
case-13 | pass→pass | 8,922 | 3,411 | -62% | 1 | 1 | 0% | 1,571 | 1,659 | +6% | 0 | 0 | — |
case-14 | pass→pass | 6,663 | 2,725 | -59% | 1 | 1 | 0% | 1,147 | 1,604 | +40% | 0 | 0 | — |
case-15 | fail→pass | 12,243 | 6,603 | -46% | 1 | 1 | 0% | 2,262 | 2,298 | +2% | 0 | 0 | — |
case-16 | pass→pass | 4,311 | 1,611 | -63% | 1 | 1 | 0% | 629 | 1,295 | +106% | 0 | 0 | — |
case-17 | fail→pass | 8,538 | 3,031 | -64% | 1 | 1 | 0% | 1,464 | 1,473 | +1% | 0 | 0 | — |
case-18 | fail→pass | 7,179 | 4,579 | -36% | 1 | 1 | 0% | 1,430 | 1,966 | +37% | 0 | 0 | — |
case-19 | pass→pass | 7,669 | 2,653 | -65% | 1 | 1 | 0% | 1,283 | 1,555 | +21% | 0 | 0 | — |
case-20 | fail→pass | 6,103 | 2,731 | -55% | 1 | 1 | 0% | 1,028 | 1,573 | +53% | 0 | 0 | — |
case-21 | fail→pass | 10,544 | 4,918 | -53% | 1 | 1 | 0% | 1,942 | 1,922 | -1% | 0 | 0 | — |
case-22 | pass→pass | 9,397 | 8,473 | -10% | 1 | 1 | 0% | 1,914 | 2,700 | +41% | 0 | 0 | — |
case-23 | pass→pass | 13,437 | 9,760 | -27% | 1 | 1 | 0% | 2,447 | 2,964 | +21% | 0 | 0 | — |
case-24 | pass→pass | 10,960 | 10,858 | -1% | 1 | 1 | 0% | 2,111 | 3,142 | +49% | 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. 24 cases were attempted. The headline lift of +38 percentage points is the difference between those two pass rates over the 24 comparable cases.
The publisher has shipped newer versions since this run, so these numbers describe v1, not the version currently listed.
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.