Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Install and configure Linktree SDK/API authentication. Use when setting up a new Linktree integration. Trigger: "install linktree", "setup linktree", "linktree auth".
.claude/skills/jeremylongshore-linktree-install-auth/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✗→✓ | ▲ Improved | 4% | 0% |
| case-02 | ✗→✓ | ▲ Improved | -31% | 0% |
| case-03 | ✗→✓ | ▲ Improved | -47% | 0% |
| case-05 | ✗→✓ | ▲ Improved | -41% | 0% |
| case-06 | ✗→✓ | ▲ Improved | -43% | 0% |
Set up Linktree API for programmatic link-in-bio management with 25M+ creators.
bashnpm install @linktree/sdk # or: pip install linktree-sdk
bashexport LINKTREE_API_KEY="your-api-key-here" echo 'LINKTREE_API_KEY=your-api-key' >> .env
typescriptimport { LinktreeClient } from '@linktree/sdk'; const client = new LinktreeClient({ apiKey: process.env.LINKTREE_API_KEY }); const profile = await client.profiles.get('myprofile'); console.log(`Profile: ${profile.username} — ${profile.links.length} links`);
pythonimport linktree client = linktree.Client(api_key=os.environ['LINKTREE_API_KEY']) profile = client.profiles.get('myprofile') print(f'Profile: {profile.username} — {len(profile.links)} links')
| Error | Code | Solution | |-------|------|----------| | Invalid API key | 401 | Verify credentials in dashboard | | Permission denied | 403 | Check API scopes/permissions | | Rate limited | 429 | Implement backoff |
After auth, proceed to linktree-hello-world.
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→pass | 17,258 | 14,357 | -17% | 1 | 1 | 0% | 2,226 | 2,304 | +4% | 0 | 0 | — |
case-02 | fail→pass | 19,746 | 12,723 | -36% | 1 | 1 | 0% | 2,943 | 2,040 | -31% | 0 | 0 | — |
case-03 | fail→pass | 20,227 | 10,591 | -48% | 1 | 1 | 0% | 2,966 | 1,561 | -47% | 0 | 0 | — |
case-04 | pass→pass | 15,201 | 8,059 | -47% | 1 | 1 | 0% | 1,733 | 956 | -45% | 0 | 0 | — |
case-05 | fail→pass | 13,219 | 7,303 | -45% | 1 | 1 | 0% | 1,451 | 850 | -41% | 0 | 0 | — |
case-06 | fail→pass | 15,460 | 7,439 | -52% | 1 | 1 | 0% | 1,437 | 820 | -43% | 0 | 0 | — |
case-07 | pass→pass | 15,866 | 7,488 | -53% | 1 | 1 | 0% | 1,550 | 865 | -44% | 0 | 0 | — |
case-08 | fail→pass | 9,792 | 6,755 | -31% | 1 | 1 | 0% | 917 | 700 | -24% | 0 | 0 | — |
case-09 | pass→pass | 14,390 | 9,696 | -33% | 1 | 1 | 0% | 1,589 | 1,258 | -21% | 0 | 0 | — |
case-10 | pass→pass | 17,081 | 11,535 | -32% | 1 | 1 | 0% | 2,120 | 1,570 | -26% | 0 | 0 | — |
case-11 | pass→pass | 17,726 | 17,188 | -3% | 1 | 1 | 0% | 1,939 | 2,115 | +9% | 0 | 0 | — |
case-21 | pass→pass | 11,735 | 10,244 | -13% | 1 | 1 | 0% | 1,980 | 2,610 | +32% | 0 | 0 | — |
case-12 | pass→pass | 16,737 | 6,732 | -60% | 1 | 1 | 0% | 1,936 | 685 | -65% | 0 | 0 | — |
case-13 | fail→pass | 14,982 | 7,467 | -50% | 1 | 1 | 0% | 1,718 | 690 | -60% | 0 | 0 | — |
case-14 | fail→pass | 20,411 | 8,164 | -60% | 1 | 1 | 0% | 2,204 | 980 | -56% | 0 | 0 | — |
case-15 | fail→pass | 15,644 | 2,568 | -84% | 1 | 1 | 0% | 1,427 | 718 | -50% | 0 | 0 | — |
case-22 | pass→pass | 16,179 | 20,809 | +29% | 1 | 1 | 0% | 1,827 | 2,869 | +57% | 0 | 0 | — |
case-16 | fail→pass | 15,280 | 12,003 | -21% | 1 | 1 | 0% | 1,844 | 1,472 | -20% | 0 | 0 | — |
case-17 | fail→pass | 13,282 | 7,227 | -46% | 1 | 1 | 0% | 1,285 | 771 | -40% | 0 | 0 | — |
case-18 | fail→pass | 4,484 | 6,620 | +48% | 1 | 1 | 0% | 543 | 673 | +24% | 0 | 0 | — |
case-19 | pass→pass | 17,817 | 4,073 | -77% | 1 | 1 | 0% | 1,781 | 895 | -50% | 0 | 0 | — |
case-20 | pass→pass | 14,309 | 5,059 | -65% | 1 | 1 | 0% | 1,708 | 1,430 | -16% | 0 | 0 | — |
case-23 | pass→pass | 16,952 | 6,455 | -62% | 1 | 1 | 0% | 1,950 | 1,492 | -23% | 0 | 0 | — |
case-24 | fail→pass | 27,439 | 9,365 | -66% | 1 | 1 | 0% | 3,982 | 1,329 | -67% | 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 +54 percentage points is the difference between those two pass rates over the 24 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.