Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Install and configure Bright Data SDK/CLI authentication. Use when setting up a new Bright Data integration, configuring API keys, or initializing Bright Data in your project. Trigger with phrases like "install brightdata", "setup brightdata", "brightdata auth", "configure brightdata API key".
.claude/skills/jeremylongshore-brightdata-install-auth/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✗→✓ | ▲ Improved | -1% | 0% |
| case-02 | ✗→✓ | ▲ Improved | 36% | 0% |
| case-03 | ✗→✓ | ▲ Improved | 24% | 0% |
| case-05 | ✗→✓ | ▲ Improved | 100% | 0% |
| case-08 | ✗→✓ | ▲ Improved | 17% | 0% |
Establish the product, identity, zone, target, and secret boundaries before any live collection. Native proxy clients use a zone username/password, while REST API clients use a named-user API key; treat them as different credentials with different blast radii.
Read the integration and Grep for existing Bright Data hosts, environment names, and secret references. Classify each call as native proxy, Browser API, or REST API before choosing credentials.
Write an example-only configuration that declares names but contains no values.
dotenvBRIGHTDATA_API_KEY= BRIGHTDATA_PROXY_USERNAME= BRIGHTDATA_PROXY_PASSWORD= BRIGHTDATA_ZONE=
Record the named owner, permitted zone, approved target classes, expiry or review condition, and revocation path. Do not reuse an account-wide API key when a zone credential is sufficient.
Use Bash(python:) only to check that required names are present and mutually consistent; never print values. Run one separately approved smoke test through the product-specific workflow.
Use Read and Grep to inventory existing access. Use Write and Edit only for approved example, configuration, and runbook paths. Use Bash(python:) for local presence/schema checks that never print secret values; this skill does not authorize a live request.
For a Web Scraper API worker, bind one named-user API key in the deployment secret manager and keep proxy username/password variables absent. For a Playwright proxy client, bind only the approved zone credentials. Stop if the product or target authorization is ambiguous.
| Failure | Meaning | Response | |---------|---------|----------| | Both credential modes are populated | Integration boundaries are mixed | Split the clients and remove unused secrets | | Zone is inactive or missing | Wrong account, spelling, or entitlement | Have the account owner verify the zone; do not broaden access | | Secret appears in logs | Unsafe diagnostics or command construction | Revoke it, scrub retained output, and correct the logging path |
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-22 | pass→pass | 16,157 | 8,896 | -45% | 1 | 1 | 0% | 1,777 | 2,983 | +68% | 0 | 0 | — |
case-06 | pass→pass | 4,251 | 2,291 | -46% | 1 | 1 | 0% | 651 | 1,505 | +131% | 0 | 0 | — |
case-01 | fail→pass | 15,308 | 9,541 | -38% | 1 | 1 | 0% | 3,137 | 3,118 | -1% | 0 | 0 | — |
case-02 | fail→pass | 12,251 | 10,247 | -16% | 1 | 1 | 0% | 2,450 | 3,337 | +36% | 0 | 0 | — |
case-03 | fail→pass | 13,792 | 18,341 | +33% | 1 | 1 | 0% | 2,640 | 3,286 | +24% | 0 | 0 | — |
case-04 | pass→pass | 9,402 | 4,097 | -56% | 1 | 1 | 0% | 1,770 | 1,887 | +7% | 0 | 0 | — |
case-05 | fail→pass | 4,263 | 2,757 | -35% | 1 | 1 | 0% | 727 | 1,456 | +100% | 0 | 0 | — |
case-19 | pass→pass | 4,289 | 3,178 | -26% | 1 | 1 | 0% | 648 | 1,493 | +130% | 0 | 0 | — |
case-07 | pass→pass | 4,631 | 2,852 | -38% | 1 | 1 | 0% | 879 | 1,660 | +89% | 0 | 0 | — |
case-08 | fail→pass | 7,207 | 2,173 | -70% | 1 | 1 | 0% | 1,304 | 1,525 | +17% | 0 | 0 | — |
case-09 | pass→pass | 3,002 | 2,531 | -16% | 1 | 1 | 0% | 515 | 1,416 | +175% | 0 | 0 | — |
case-10 | pass→pass | 4,981 | 2,370 | -52% | 1 | 1 | 0% | 870 | 1,505 | +73% | 0 | 0 | — |
case-20 | pass→pass | 18,447 | 14,474 | -22% | 1 | 1 | 0% | 1,545 | 2,866 | +86% | 0 | 0 | — |
case-11 | fail→pass | 10,765 | 3,043 | -72% | 1 | 1 | 0% | 2,130 | 1,698 | -20% | 0 | 0 | — |
case-12 | pass→pass | 8,271 | 2,973 | -64% | 1 | 1 | 0% | 1,464 | 1,581 | +8% | 0 | 0 | — |
case-13 | pass→pass | 9,097 | 4,922 | -46% | 1 | 1 | 0% | 1,738 | 2,105 | +21% | 0 | 0 | — |
case-14 | pass→pass | 13,309 | 9,982 | -25% | 1 | 1 | 0% | 2,376 | 2,830 | +19% | 0 | 0 | — |
case-21 | pass→pass | 13,395 | 12,856 | -4% | 1 | 1 | 0% | 2,389 | 3,732 | +56% | 0 | 0 | — |
case-15 | pass→pass | 15,708 | 7,378 | -53% | 1 | 1 | 0% | 1,955 | 2,461 | +26% | 0 | 0 | — |
case-16 | fail→fail | 7,948 | 5,153 | -35% | 1 | 1 | 0% | 1,514 | 2,153 | +42% | 0 | 0 | — |
case-17 | pass→pass | 9,333 | 2,846 | -70% | 1 | 1 | 0% | 1,618 | 1,535 | -5% | 0 | 0 | — |
case-18 | pass→pass | 3,649 | 1,359 | -63% | 1 | 1 | 0% | 529 | 1,323 | +150% | 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 +27 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.