Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →No-code automation democratizes workflow building. Zapier and Make (formerly Integromat) let non-developers automate business processes without writing code. But no-code doesn't mean no-complexity - these platforms have their own patterns, pitfalls, and breaking points. This skill covers when to use which platform, how to build reliable automations, and when to graduate to code-based solutions. Key insight: Zapier optimizes for simplicity and integrations (7000+ apps), Make optimizes for power
.claude/skills/davila7-zapier-make-patterns/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✗→✓ | ▲ Improved | 8% | 0% |
| case-13 | ✓→✓ | ＝ Same ✓ | 29% | 0% |
| case-02 | ✓→✓ | ＝ Same ✓ | -5% | 0% |
| case-03 | ✓→✓ | ＝ Same ✓ | 11% | 0% |
| case-04 | ✓→✓ | ＝ Same ✓ | 29% | 0% |
You are a no-code automation architect who has built thousands of Zaps and Scenarios for businesses of all sizes. You've seen automations that save companies 40% of their time, and you've debugged disasters where bad data flowed through 12 connected apps.
Your core insight: No-code is powerful but not unlimited. You know exactly when a workflow belongs in Zapier (simple, fast, maximum integrations), when it belongs in Make (complex branching, data transformation, budget), and when it needs to g
Single trigger leads to one or more actions
Chain of actions executed in order
Different actions based on conditions
| Issue | Severity | Solution | |-------|----------|----------| | Issue | critical | # ALWAYS use dropdowns to select, don't type | | Issue | critical | # Prevention: | | Issue | high | # Understand the math: | | Issue | high | # When a Zap breaks after app update: | | Issue | high | # Immediate fix: | | Issue | medium | # Handle duplicates: | | Issue | medium | # Understand operation counting: | | Issue | medium | # Best practices: |
Works well with: workflow-automation, agent-tool-builder, backend, api-designer
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-13 | pass→pass | 9,828 | 9,139 | -7% | 1 | 1 | 0% | 1,563 | 2,014 | +29% | 0 | 0 | — |
case-01 | fail→pass | 18,502 | 17,085 | -8% | 1 | 1 | 0% | 3,041 | 3,287 | +8% | 0 | 0 | — |
case-02 | pass→pass | 13,018 | 9,734 | -25% | 1 | 1 | 0% | 2,234 | 2,113 | -5% | 0 | 0 | — |
case-03 | pass→pass | 11,423 | 9,875 | -14% | 1 | 1 | 0% | 1,911 | 2,128 | +11% | 0 | 0 | — |
case-04 | pass→pass | 9,780 | 11,524 | +18% | 1 | 1 | 0% | 1,755 | 2,258 | +29% | 0 | 0 | — |
case-05 | pass→pass | 14,490 | 11,669 | -19% | 1 | 1 | 0% | 2,324 | 2,269 | -2% | 0 | 0 | — |
case-06 | pass→pass | 6,667 | 2,675 | -60% | 1 | 1 | 0% | 1,055 | 843 | -20% | 0 | 0 | — |
case-07 | pass→pass | 7,156 | 4,389 | -39% | 1 | 1 | 0% | 1,189 | 1,144 | -4% | 0 | 0 | — |
case-08 | pass→pass | 7,572 | 4,425 | -42% | 1 | 1 | 0% | 1,208 | 1,077 | -11% | 0 | 0 | — |
case-09 | pass→pass | 12,619 | 14,925 | +18% | 1 | 1 | 0% | 2,152 | 2,696 | +25% | 0 | 0 | — |
case-10 | pass→pass | 13,973 | 15,751 | +13% | 1 | 1 | 0% | 2,347 | 2,933 | +25% | 0 | 0 | — |
case-11 | fail→fail | 8,715 | 10,358 | +19% | 1 | 1 | 0% | 1,444 | 2,127 | +47% | 0 | 0 | — |
case-12 | pass→pass | 15,670 | 14,226 | -9% | 1 | 1 | 0% | 2,565 | 2,781 | +8% | 0 | 0 | — |
case-14 | pass→pass | 11,413 | 11,601 | +2% | 1 | 1 | 0% | 1,860 | 2,261 | +22% | 0 | 0 | — |
case-15 | pass→pass | 10,186 | 10,859 | +7% | 1 | 1 | 0% | 1,815 | 2,091 | +15% | 0 | 0 | — |
case-16 | pass→pass | 9,216 | 7,559 | -18% | 1 | 1 | 0% | 1,605 | 1,677 | +4% | 0 | 0 | — |
case-17 | pass→pass | 11,008 | 12,195 | +11% | 1 | 1 | 0% | 1,848 | 2,459 | +33% | 0 | 0 | — |
case-18 | pass→pass | 7,690 | 6,872 | -11% | 1 | 1 | 0% | 1,274 | 1,482 | +16% | 0 | 0 | — |
case-19 | pass→pass | 7,056 | 5,150 | -27% | 1 | 1 | 0% | 1,350 | 1,205 | -11% | 0 | 0 | — |
case-20 | pass→pass | 8,386 | 9,102 | +9% | 1 | 1 | 0% | 1,404 | 1,969 | +40% | 0 | 0 | — |
case-21 | pass→pass | 13,685 | 8,752 | -36% | 1 | 1 | 0% | 1,737 | 2,017 | +16% | 0 | 0 | — |
case-22 | pass→pass | 11,554 | 13,774 | +19% | 1 | 1 | 0% | 2,274 | 2,855 | +26% | 0 | 0 | — |
case-23 | pass→pass | 10,492 | 9,327 | -11% | 1 | 1 | 0% | 2,400 | 2,410 | +0% | 0 | 0 | — |
case-24 | pass→pass | 5,070 | 6,040 | +19% | 1 | 1 | 0% | 1,268 | 1,801 | +42% | 0 | 0 | — |
case-25 | pass→pass | 13,044 | 10,744 | -18% | 1 | 1 | 0% | 2,749 | 2,641 | -4% | 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. 25 cases were attempted. The headline lift of +4 percentage points is the difference between those two pass rates over the 25 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.