Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Install and configure Hex SDK/CLI authentication. Use when setting up a new Hex integration, configuring API keys, or initializing Hex in your project. Trigger with phrases like "install hex", "setup hex", "hex auth", "configure hex API key".
.claude/skills/jeremylongshore-hex-install-auth/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✗→✓ | ▲ Improved | -5% | 0% |
| case-02 | ✗→✓ | ▲ Improved | -25% | 0% |
| case-05 | ✗→✓ | ▲ Improved | -30% | 0% |
| case-06 | ✗→✓ | ▲ Improved | -41% | 0% |
| case-10 | ✗→✓ | ▲ Improved | -20% | 0% |
Configure Hex API authentication using OAuth 2.0 Bearer tokens. The Hex API at app.hex.tech/api/v1/ lets you programmatically trigger project runs, check status, manage users, and configure connections. Tokens are generated per-user in the Hex workspace settings.
bash# .env (NEVER commit) HEX_API_TOKEN=hex_token_abc123... HEX_WORKSPACE_URL=https://app.hex.tech # .gitignore .env .env.local
typescript// verify-hex.ts import 'dotenv/config'; const TOKEN = process.env.HEX_API_TOKEN!; async function verify() { const response = await fetch('https://app.hex.tech/api/v1/projects', { headers: { 'Authorization': `Bearer ${TOKEN}`, 'Content-Type': 'application/json' }, }); if (!response.ok) throw new Error(`Hex API ${response.status}`); const projects = await response.json(); console.log(`Connected! Found ${projects.length} projects`); return projects; } verify().catch(console.error);
bash# curl verification curl -s -H "Authorization: Bearer $HEX_API_TOKEN" \ https://app.hex.tech/api/v1/projects | python3 -m json.tool
| Scope | Endpoints | Use Case | |-------|-----------|----------| | Read projects | ListProjects, GetProjectRuns, GetRunStatus | Monitoring | | Run projects | RunProject, CancelRun (+ all read) | Orchestration |
| Error | Cause | Solution | |-------|-------|----------| | 401 Unauthorized | Invalid or expired token | Regenerate in workspace settings | | 403 Forbidden | Missing scope | Create token with "Run projects" scope | | 404 Not Found | Wrong workspace URL | Verify HEX_WORKSPACE_URL |
After auth, proceed to hex-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 | 23,301 | 15,818 | -32% | 1 | 1 | 0% | 2,871 | 2,737 | -5% | 0 | 0 | — |
case-02 | fail→pass | 18,779 | 13,165 | -30% | 1 | 1 | 0% | 2,444 | 1,845 | -25% | 0 | 0 | — |
case-03 | fail→fail | 15,298 | 14,318 | -6% | 1 | 1 | 0% | 2,708 | 2,510 | -7% | 0 | 0 | — |
case-04 | pass→pass | 23,767 | 2,515 | -89% | 1 | 1 | 0% | 3,545 | 1,127 | -68% | 0 | 0 | — |
case-05 | fail→pass | 18,163 | 10,100 | -44% | 1 | 1 | 0% | 2,189 | 1,527 | -30% | 0 | 0 | — |
case-06 | fail→pass | 12,989 | 7,291 | -44% | 1 | 1 | 0% | 1,836 | 1,092 | -41% | 0 | 0 | — |
case-07 | pass→pass | 11,503 | 4,083 | -65% | 1 | 1 | 0% | 1,019 | 1,304 | +28% | 0 | 0 | — |
case-08 | pass→pass | 8,553 | 7,182 | -16% | 1 | 1 | 0% | 541 | 1,049 | +94% | 0 | 0 | — |
case-09 | pass→pass | 16,768 | 10,003 | -40% | 1 | 1 | 0% | 2,164 | 1,508 | -30% | 0 | 0 | — |
case-10 | fail→pass | 11,242 | 4,426 | -61% | 1 | 1 | 0% | 1,865 | 1,486 | -20% | 0 | 0 | — |
case-11 | fail→pass | 18,401 | 8,931 | -51% | 1 | 1 | 0% | 2,463 | 1,390 | -44% | 0 | 0 | — |
case-12 | fail→pass | 17,751 | 7,403 | -58% | 1 | 1 | 0% | 2,144 | 1,023 | -52% | 0 | 0 | — |
case-13 | pass→pass | 14,103 | 8,608 | -39% | 1 | 1 | 0% | 1,666 | 1,331 | -20% | 0 | 0 | — |
case-14 | fail→pass | 16,186 | 8,389 | -48% | 1 | 1 | 0% | 1,608 | 1,147 | -29% | 0 | 0 | — |
case-15 | pass→pass | 6,901 | 3,270 | -53% | 1 | 1 | 0% | 1,063 | 962 | -10% | 0 | 0 | — |
case-16 | pass→pass | 11,582 | 7,984 | -31% | 1 | 1 | 0% | 1,038 | 1,016 | -2% | 0 | 0 | — |
case-17 | fail→pass | 15,721 | 12,275 | -22% | 1 | 1 | 0% | 2,986 | 2,034 | -32% | 0 | 0 | — |
case-18 | pass→pass | 16,129 | 7,187 | -55% | 1 | 1 | 0% | 1,769 | 1,070 | -40% | 0 | 0 | — |
case-19 | pass→pass | 12,047 | 8,215 | -32% | 1 | 1 | 0% | 1,227 | 1,252 | +2% | 0 | 0 | — |
case-20 | pass→fail | 14,355 | 20,384 | +42% | 1 | 1 | 0% | 1,957 | 2,450 | +25% | 0 | 0 | — |
case-21 | pass→pass | 15,700 | 19,905 | +27% | 1 | 1 | 0% | 1,905 | 3,423 | +80% | 0 | 0 | — |
case-22 | pass→fail | 13,502 | 7,580 | -44% | 1 | 1 | 0% | 1,467 | 1,881 | +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. 22 cases were attempted. The headline lift of +32 percentage points is the difference between those two pass rates over the 22 comparable cases. 2 cases got worse with the skill loaded, and they are included in that figure.
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.