Install any skill in seconds. Free to start, no credit card required.
Get Started Free →When the user wants to optimize post-signup onboarding, user activation, first-run experience, or time-to-value. Also use when the user mentions "onboarding flow," "activation rate," "user activation," "first-run experience," "empty states," "onboarding checklist," "aha moment," or "new user experience." For signup/registration optimization, see signup-flow-cro. For ongoing email sequences, see email-sequence.
.claude/skills/davila7-onboarding-cro/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✗→✓ | ▲ Improved | 79% | 0% |
| case-12 | ✗→✓ | ▲ Improved | 102% | 0% |
| case-14 | ✗→✓ | ▲ Improved | 59% | 0% |
| case-15 | ✗→✓ | ▲ Improved | 106% | 0% |
| case-22 | ✗→✓ | ▲ Improved | 103% | 0% |
You are an expert in user onboarding and activation. Your goal is to help users reach their "aha moment" as quickly as possible and establish habits that lead to long-term retention.
Before providing recommendations, understand:
The action that correlates most strongly with retention:
Examples by product type:
Options:
Whatever you choose:
When to use:
Best practices:
Checklist item structure:
Example:
☐ Connect your first data source (2 min)
Get real-time insights from your existing tools
[Connect Now]Empty states are onboarding opportunities, not dead ends.
Good empty state:
Structure:
When to use:
When to avoid:
Best practices:
Types:
Best practices:
Trigger-based emails:
Email should:
Loop structure: Trigger → Action → Variable Reward → Investment
Examples:
Track drop-off at each step:
Signup → Step 1 → Step 2 → Activation → Retention
100% 80% 60% 40% 25%Identify biggest drops and focus there.
For each issue:
Reduce Friction
Step Sequencing
Progress & Motivation
Product Tours
CTA Optimization
User Segmentation
Dynamic Content
Time-to-Value
Support & Help
Onboarding Emails
Feedback Loops
If you need more context:
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→pass | 19,264 | 17,826 | -7% | 1 | 1 | 0% | 3,173 | 5,679 | +79% | 0 | 0 | — |
case-02 | pass→pass | 12,209 | 12,126 | -1% | 1 | 1 | 0% | 2,103 | 4,502 | +114% | 0 | 0 | — |
case-03 | pass→pass | 14,680 | 16,080 | +10% | 1 | 1 | 0% | 2,423 | 5,418 | +124% | 0 | 0 | — |
case-04 | pass→pass | 13,195 | 11,546 | -12% | 1 | 1 | 0% | 2,795 | 5,137 | +84% | 0 | 0 | — |
case-05 | pass→pass | 13,609 | 14,481 | +6% | 1 | 1 | 0% | 2,169 | 4,859 | +124% | 0 | 0 | — |
case-06 | pass→pass | 11,287 | 11,880 | +5% | 1 | 1 | 0% | 1,764 | 4,549 | +158% | 0 | 0 | — |
case-07 | pass→pass | 13,596 | 13,810 | +2% | 1 | 1 | 0% | 2,192 | 5,054 | +131% | 0 | 0 | — |
case-08 | fail→fail | 14,721 | 15,383 | +4% | 1 | 1 | 0% | 2,324 | 5,116 | +120% | 0 | 0 | — |
case-09 | pass→pass | 13,858 | 14,257 | +3% | 1 | 1 | 0% | 2,337 | 5,017 | +115% | 0 | 0 | — |
case-10 | pass→pass | 12,625 | 10,834 | -14% | 1 | 1 | 0% | 2,058 | 4,136 | +101% | 0 | 0 | — |
case-11 | pass→pass | 10,883 | 9,662 | -11% | 1 | 1 | 0% | 1,897 | 4,181 | +120% | 0 | 0 | — |
case-12 | fail→pass | 18,407 | 19,286 | +5% | 1 | 1 | 0% | 2,798 | 5,661 | +102% | 0 | 0 | — |
case-13 | pass→pass | 13,410 | 9,754 | -27% | 1 | 1 | 0% | 2,181 | 3,898 | +79% | 0 | 0 | — |
case-14 | fail→pass | 20,448 | 15,635 | -24% | 1 | 1 | 0% | 3,377 | 5,379 | +59% | 0 | 0 | — |
case-15 | fail→pass | 16,538 | 17,729 | +7% | 1 | 1 | 0% | 2,817 | 5,801 | +106% | 0 | 0 | — |
case-16 | pass→pass | 15,223 | 16,144 | +6% | 1 | 1 | 0% | 2,562 | 5,004 | +95% | 0 | 0 | — |
case-17 | pass→pass | 15,104 | 19,257 | +27% | 1 | 1 | 0% | 2,436 | 5,546 | +128% | 0 | 0 | — |
case-18 | pass→pass | 14,915 | 18,540 | +24% | 1 | 1 | 0% | 2,604 | 5,664 | +118% | 0 | 0 | — |
case-19 | pass→pass | 13,451 | 15,028 | +12% | 1 | 1 | 0% | 2,113 | 4,935 | +134% | 0 | 0 | — |
case-20 | pass→pass | 15,061 | 16,554 | +10% | 1 | 1 | 0% | 2,749 | 5,333 | +94% | 0 | 0 | — |
case-21 | pass→pass | 14,295 | 13,653 | -4% | 1 | 1 | 0% | 2,340 | 4,963 | +112% | 0 | 0 | — |
case-22 | fail→pass | 14,021 | 14,906 | +6% | 1 | 1 | 0% | 2,485 | 5,046 | +103% | 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 +23 percentage points is the difference between those two pass rates over the 22 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.