Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Diagnose and fix Bright Data common errors and exceptions. Use when encountering Bright Data errors, debugging failed requests, or troubleshooting integration issues. Trigger with phrases like "brightdata error", "fix brightdata", "brightdata not working", "debug brightdata".
.claude/skills/jeremylongshore-brightdata-common-errors/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✗→✓ | ▲ Improved | 37% | 0% |
| case-02 | ✗→✓ | ▲ Improved | 18% | 0% |
| case-03 | ✗→✓ | ▲ Improved | 7% | 0% |
| case-04 | ✗→✓ | ▲ Improved | 9% | 0% |
| case-05 | ✗→✓ | ▲ Improved | 33% | 0% |
Separate provider, target, client, and policy failures using HTTP status, Proxy-Status, and current x-brd-* fields. Never treat an access or compliance denial as a cue to rotate products, regions, or identities.
Read the receipt and Grep for status, Proxy-Status, x-brd-err-code, x-brd-error, x-brd-err-msg, snapshot state, and request time. Exclude credentials, full URLs, and bodies.
Classify authentication (407/client), policy (403/policy), throttling (429), peer/target (408/502), provider incident, or dataset lifecycle failure.
Use Bash(curl:) only for one authorized provider test endpoint or a read-only status check. Do not reproduce against a sensitive target or change network type to defeat a denial.
Fix deterministic client/auth errors; back off transient/provider errors within budget; pause policy, target-data, account, empty, or persistent errors for owner review.
Use Read and Grep to analyze redacted evidence. Use Bash(curl:) only for a bounded provider-controlled test. This workflow never writes raw response data, prints credentials, or authorizes product or identity switching.
For 429 with a per-IP code, reduce pressure and review distribution; do not automatically rotate to more identities. For a policy 403, stop. For a provider-wide incident, preserve the receipt and wait for recovery.
| Failure | Meaning | Response | |---------|---------|----------| | Only an HTTP status is available | Provider detail was discarded | Capture current redacted headers on the next approved attempt | | Legacy header is the only parser path | x-luminati-* support is stale | Migrate to Proxy-Status and x-brd-* | | Failure repeats after bounded retry | Classification or provider state is unresolved | Open support escalation with sanitized identifiers |
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→pass | 15,034 | 14,006 | -7% | 1 | 1 | 0% | 3,015 | 4,118 | +37% | 0 | 0 | — |
case-02 | fail→pass | 20,837 | 12,118 | -42% | 1 | 1 | 0% | 3,194 | 3,756 | +18% | 0 | 0 | — |
case-03 | fail→pass | 15,825 | 8,776 | -45% | 1 | 1 | 0% | 2,768 | 2,962 | +7% | 0 | 0 | — |
case-04 | fail→pass | 10,843 | 4,748 | -56% | 1 | 1 | 0% | 2,031 | 2,222 | +9% | 0 | 0 | — |
case-05 | fail→pass | 16,169 | 9,598 | -41% | 1 | 1 | 0% | 2,331 | 3,094 | +33% | 0 | 0 | — |
case-06 | pass→pass | 16,262 | 10,537 | -35% | 1 | 1 | 0% | 2,937 | 3,205 | +9% | 0 | 0 | — |
case-07 | pass→pass | 12,639 | 4,241 | -66% | 1 | 1 | 0% | 2,145 | 2,084 | -3% | 0 | 0 | — |
case-08 | fail→pass | 10,548 | 5,573 | -47% | 1 | 1 | 0% | 1,788 | 2,352 | +32% | 0 | 0 | — |
case-09 | fail→pass | 6,362 | 2,921 | -54% | 1 | 1 | 0% | 1,157 | 1,665 | +44% | 0 | 0 | — |
case-10 | pass→pass | 5,108 | 4,113 | -19% | 1 | 1 | 0% | 839 | 1,674 | +100% | 0 | 0 | — |
case-11 | fail→pass | 11,475 | 2,057 | -82% | 1 | 1 | 0% | 1,910 | 1,632 | -15% | 0 | 0 | — |
case-12 | pass→pass | 9,360 | 5,495 | -41% | 1 | 1 | 0% | 1,680 | 2,296 | +37% | 0 | 0 | — |
case-13 | pass→pass | 11,822 | 6,734 | -43% | 1 | 1 | 0% | 1,880 | 2,388 | +27% | 0 | 0 | — |
case-14 | pass→pass | 11,356 | 3,815 | -66% | 1 | 1 | 0% | 1,986 | 1,903 | -4% | 0 | 0 | — |
case-15 | fail→pass | 11,200 | 5,809 | -48% | 1 | 1 | 0% | 2,135 | 2,448 | +15% | 0 | 0 | — |
case-16 | fail→pass | 4,910 | 2,058 | -58% | 1 | 1 | 0% | 804 | 1,658 | +106% | 0 | 0 | — |
case-17 | fail→pass | 8,479 | 3,355 | -60% | 1 | 1 | 0% | 1,605 | 1,920 | +20% | 0 | 0 | — |
case-18 | pass→pass | 9,267 | 4,272 | -54% | 1 | 1 | 0% | 1,385 | 1,959 | +41% | 0 | 0 | — |
case-19 | pass→pass | 9,542 | 6,053 | -37% | 1 | 1 | 0% | 1,754 | 2,390 | +36% | 0 | 0 | — |
case-20 | pass→pass | 10,661 | 8,948 | -16% | 1 | 1 | 0% | 2,087 | 3,017 | +45% | 0 | 0 | — |
case-21 | pass→pass | 11,402 | 12,792 | +12% | 1 | 1 | 0% | 2,215 | 3,620 | +63% | 0 | 0 | — |
case-22 | pass→pass | 9,856 | 5,744 | -42% | 1 | 1 | 0% | 1,760 | 2,299 | +31% | 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. The headline lift of +50 percentage points is the difference between those two pass rates over the 22 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.