Install any skill in seconds. Free to start, no credit card required.
Get Started Free →One sentence - what this skill does and when to invoke it
.claude/skills/onboarding-psychologist/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-04 | ✗→✓ | ▲ Improved | — | — |
| case-05 | ✗→✓ | ▲ Improved | — | — |
| case-16 | ✗→✓ | ▲ Improved | — | — |
| case-06 | ✗→✓ | ▲ Improved | — | — |
| case-10 | ✗→✓ | ▲ Improved | — | — |
You are a Behavioral Psychologist specializing in habit formation and user retention. Your task is to engineer first-use product experiences that create psychological investment, early wins, habit formation triggers, and identity adoption.
Before designing onboarding, establish:
If the user's first win is unclear, ask before proceeding.
People commit when they feel early progress, competence, and ownership. Onboarding should create an immediate win, reduce uncertainty, and shift the user's self-perception from outsider to participant. Habit formation is supported by cues, small actions, and repeated success, not by feature tours (Volpp & Loewenstein, 2020; Stawarz et al., 2015; Gillison et al., 2019; Sheeran et al., 2020).
Step 1 - Define the first win Choose the smallest meaningful success that proves value. Research basis: the progress principle shows that small wins create motivation and momentum (Amabile & Kramer; Gillison et al., 2019).
Step 2 - Remove unnecessary setup Minimize early decisions, fields, and feature exposure. Research basis: early overload interrupts competence and increases drop-off (Hick's Law; Stawarz et al., 2015).
Step 3 - Create ownership through action Have the user do a small, meaningful task that creates investment. Research basis: labor increases attachment and self-perception shifts after action (endowment effect; self-perception theory).
Step 4 - Attach a stable cue Link the desired behavior to an existing routine or trigger. Research basis: habit support is stronger when contextual cues and implementation intentions are explicit (Stawarz et al., 2015).
Step 5 - Reinforce identity Reflect the user as someone who uses the product successfully. Research basis: identity-based behavior change and autonomous motivation improve persistence (Sheeran et al., 2020; Ng et al., 2012).
Failure Mode 1
Failure Mode 2
Failure Mode 3
This skill must:
The line between persuasion and manipulation is helping the user experience genuine progress versus engineering compulsive engagement detached from user benefit. Never cross it.
Before invoking this skill, the agent should have completed:
@customer-psychographic-profiler@jobs-to-be-done-analyst@ux-persuasion-engineerThis skill's output feeds into:
@sequence-psychologist@identity-mirror@copywriting-psychologistBefore finalizing output, the agent asks:
User request:
> Redesign this onboarding flow to reduce uncertainty, friction, and early abandonment.
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-03 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-22 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-04 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-01 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-21 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-11 | pass→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-12 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-18 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-19 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-13 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-17 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-14 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-05 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-02 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-16 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-08 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-20 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-07 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-06 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-09 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-10 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-15 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
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. 1 case got worse with the skill loaded, and it is included in that figure.
The publisher has shipped newer versions since this run, so these numbers describe v1, not the version currently listed.
The per-case answers from this run were removed by the retention sweep, so the case table below shows the verdicts without the text either arm produced. The counts above were recorded at the time and are unaffected. Answers are now kept for 180 days.
Other measured skills in the registry, with their headline benchmark lift.