Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Trigger.dev expert for background jobs, AI workflows, and reliable async execution with excellent developer experience and TypeScript-first design. Use when: trigger.dev, trigger dev, background task, ai background job, long running task.
.claude/skills/davila7-trigger-dev/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-07 | ✗→✓ | ▲ Improved | 2% | 0% |
| case-16 | ✓→✗ | ▼ Worse | 44% | 0% |
| case-13 | ✓→✓ | = Same ✓ | 13% | 0% |
| case-01 | ✓→✓ | = Same ✓ | -23% | 0% |
| case-12 | ✓→✓ | = Same ✓ | 19% | 0% |
You are a Trigger.dev expert who builds reliable background jobs with exceptional developer experience. You understand that Trigger.dev bridges the gap between simple queues and complex orchestration - it's "Temporal made easy" for TypeScript developers.
You've built AI pipelines that process for minutes, integration workflows that sync across dozens of services, and batch jobs that handle millions of records. You know the power of built-in integrations and the importance of proper task design.
Setting up Trigger.dev in a Next.js project
Using built-in OpenAI integration with automatic retries
Tasks that run on a schedule
| Issue | Severity | Solution | |-------|----------|----------| | Task timeout kills execution without clear error | critical | # Configure explicit timeouts: | | Non-serializable payload causes silent task failure | critical | # Always use plain objects: | | Environment variables not synced to Trigger.dev cloud | critical | # Sync env vars to Trigger.dev: | | SDK version mismatch between CLI and package | high | # Always update together: | | Task retries cause duplicate side effects | high | # Use idempotency keys: | | High concurrency overwhelms downstream services | high | # Set queue concurrency limits: | | trigger.config.ts not at project root | high | # Config must be at package root: | | wait.for in loops causes memory issues | medium | # Batch instead of individual waits: |
Works well with: nextjs-app-router, vercel-deployment, ai-agents-architect, llm-architect, email-systems, stripe-integration
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-13 | pass→pass | 7,707 | 5,829 | -24% | 1 | 1 | 0% | 1,481 | 1,670 | +13% | 0 | 0 | — |
case-01 | pass→pass | 15,117 | 9,641 | -36% | 1 | 1 | 0% | 3,159 | 2,432 | -23% | 0 | 0 | — |
case-02 | fail→fail | 18,383 | 14,865 | -19% | 1 | 1 | 0% | 4,095 | 3,850 | -6% | 0 | 0 | — |
case-12 | pass→pass | 14,154 | 12,696 | -10% | 1 | 1 | 0% | 2,383 | 2,827 | +19% | 0 | 0 | — |
case-03 | fail→fail | 7,594 | 6,720 | -12% | 1 | 1 | 0% | 1,339 | 1,685 | +26% | 0 | 0 | — |
case-04 | pass→pass | 11,796 | 7,611 | -35% | 1 | 1 | 0% | 2,115 | 1,872 | -11% | 0 | 0 | — |
case-05 | pass→pass | 6,406 | 5,020 | -22% | 1 | 1 | 0% | 1,156 | 1,340 | +16% | 0 | 0 | — |
case-06 | pass→pass | 21,960 | 14,527 | -34% | 1 | 1 | 0% | 1,589 | 1,600 | +1% | 0 | 0 | — |
case-07 | fail→pass | 21,206 | 24,974 | +18% | 1 | 1 | 0% | 2,268 | 2,317 | +2% | 0 | 0 | — |
case-08 | pass→pass | 15,463 | 17,956 | +16% | 1 | 1 | 0% | 1,691 | 1,760 | +4% | 0 | 0 | — |
case-09 | pass→pass | 13,842 | 19,642 | +42% | 1 | 1 | 0% | 1,264 | 1,097 | -13% | 0 | 0 | — |
case-10 | pass→pass | 19,075 | 11,613 | -39% | 1 | 1 | 0% | 1,481 | 2,229 | +51% | 0 | 0 | — |
case-11 | fail→fail | 19,339 | 18,554 | -4% | 1 | 1 | 0% | 2,136 | 2,764 | +29% | 0 | 0 | — |
case-14 | pass→pass | 8,244 | 5,656 | -31% | 1 | 1 | 0% | 1,620 | 1,495 | -8% | 0 | 0 | — |
case-15 | fail→fail | 12,997 | 7,919 | -39% | 1 | 1 | 0% | 2,497 | 1,960 | -22% | 0 | 0 | — |
case-16 | pass→fail | 7,729 | 8,126 | +5% | 1 | 1 | 0% | 1,467 | 2,112 | +44% | 0 | 0 | — |
case-17 | fail→fail | 11,298 | 10,955 | -3% | 1 | 1 | 0% | 2,036 | 2,368 | +16% | 0 | 0 | — |
case-18 | pass→pass | 11,379 | 9,385 | -18% | 1 | 1 | 0% | 2,075 | 2,319 | +12% | 0 | 0 | — |
case-19 | fail→fail | 15,020 | 9,710 | -35% | 1 | 1 | 0% | 2,063 | 2,184 | +6% | 0 | 0 | — |
case-20 | pass→pass | 7,849 | 9,604 | +22% | 1 | 1 | 0% | 1,692 | 2,005 | +18% | 0 | 0 | — |
case-21 | pass→pass | 8,171 | 5,848 | -28% | 1 | 1 | 0% | 1,634 | 1,685 | +3% | 0 | 0 | — |
case-22 | pass→pass | 7,470 | 4,625 | -38% | 1 | 1 | 0% | 1,234 | 1,342 | +9% | 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 0 percentage points is the difference between those two pass rates over the 22 comparable cases. 1 case got worse with the skill loaded, and it is 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.