Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Delight pass — adds one or two memorable micro-interactions (copy specificity, hover choreography, state transitions, one signature detail) without decoration or confetti. Use when the UI works but feels generic, or when the user says "make it feel special" / "add some personality". Invoke when the user asks for delight on their UI, or mentions 'delight' alongside design / UI / frontend work.
.claude/skills/educlopez-delight/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-08 | ✗→✓ | ▲ Improved | -22% | 0% |
| case-11 | ✗→✓ | ▲ Improved | 21% | 0% |
| case-07 | ✓→✗ | ▼ Worse | -79% | 0% |
| case-12 | ✓→✗ | ▼ Worse | -87% | 0% |
| case-18 | ✓→✗ | ▼ Worse | -39% | 0% |
<!-- HARNESS MIRROR — do not edit here. Canonical source: skills/ or commands/. After editing source, copy into cli/assets/<harness>/ and repo-root harness mirrors. -->
Context: this sub-skill is one lens of the broader ui-craft skill. If the ui-craft skill is also installed, read its SKILL.md first for Discovery + Anti-Slop + Craft Test, then apply the specific lens below.
Add delight to the UI at $ARGUMENTS. Load the ui-craft skill.
Delight is specificity, not decoration. The goal is one or two moments a user would screenshot — not confetti, not bounce, not emoji.
Candidates, ordered by safety (start at the top):
Never add:
cubic-bezier(0.68, -0.55, 0.27, 1.55)) — flagged in anti-slop.Knob gating (MOTION_INTENSITY):
≤ 3 → copy-only delight. No animated delight. Candidate 1 only.4-7 → copy + hover + state transitions (candidates 1-3).8+ → all four, including the signature detail.References to read: references/motion.md (Decision Ladder + interaction rules), references/copy.md (microcopy voice), ../examples/animation-storyboard.md (if multi-stage).
Output: edit code directly. Print the Review Format table. Flag every candidate you chose not to add and why.
Next step: /finalize — delight is the last additive pass; gate it before shipping (rung 3).
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→fail | 5,745 | 26,456 | +361% | 1 | 1 | 0% | 228 | 996 | +337% | 0 | 0 | — |
case-02 | fail→fail | 49,017 | 6,130 | -87% | 1 | 1 | 0% | 8,258 | 853 | -90% | 0 | 0 | — |
case-03 | fail→fail | 35,048 | 5,277 | -85% | 1 | 1 | 0% | 8,264 | 773 | -91% | 0 | 0 | — |
case-04 | fail→fail | 4,788 | 8,201 | +71% | 1 | 1 | 0% | 176 | 1,018 | +478% | 0 | 0 | — |
case-05 | pass→pass | 17,908 | 8,047 | -55% | 1 | 1 | 0% | 2,460 | 2,050 | -17% | 0 | 0 | — |
case-06 | fail→fail | 27,508 | 7,365 | -73% | 1 | 1 | 0% | 6,013 | 870 | -86% | 0 | 0 | — |
case-07 | pass→fail | 31,913 | 6,932 | -78% | 1 | 1 | 0% | 4,450 | 946 | -79% | 0 | 0 | — |
case-08 | fail→pass | 50,239 | 29,923 | -40% | 1 | 1 | 0% | 8,236 | 6,448 | -22% | 0 | 0 | — |
case-09 | fail→fail | 36,923 | 5,578 | -85% | 1 | 1 | 0% | 7,803 | 809 | -90% | 0 | 0 | — |
case-10 | fail→fail | 36,606 | 7,503 | -80% | 1 | 1 | 0% | 8,235 | 989 | -88% | 0 | 0 | — |
case-11 | fail→pass | 17,585 | 18,143 | +3% | 1 | 1 | 0% | 3,678 | 4,439 | +21% | 0 | 0 | — |
case-12 | pass→fail | 41,139 | 5,476 | -87% | 1 | 1 | 0% | 6,148 | 794 | -87% | 0 | 0 | — |
case-13 | fail→fail | 21,184 | 8,446 | -60% | 1 | 1 | 0% | 3,856 | 1,203 | -69% | 0 | 0 | — |
case-18 | pass→fail | 9,213 | 5,062 | -45% | 1 | 1 | 0% | 1,198 | 736 | -39% | 0 | 0 | — |
case-14 | fail→fail | 40,345 | 6,656 | -84% | 1 | 1 | 0% | 8,240 | 1,097 | -87% | 0 | 0 | — |
case-15 | fail→fail | 51,356 | 5,817 | -89% | 1 | 1 | 0% | 8,243 | 790 | -90% | 0 | 0 | — |
case-16 | pass→fail | 10,321 | 4,531 | -56% | 1 | 1 | 0% | 2,085 | 901 | -57% | 0 | 0 | — |
case-17 | pass→fail | 19,005 | 5,345 | -72% | 1 | 1 | 0% | 2,992 | 856 | -71% | 0 | 0 | — |
case-19 | pass→fail | 15,120 | 5,825 | -61% | 1 | 1 | 0% | 2,961 | 878 | -70% | 0 | 0 | — |
case-20 | fail→fail | 28,985 | 7,142 | -75% | 1 | 1 | 0% | 4,949 | 816 | -84% | 0 | 0 | — |
case-21 | fail→fail | 26,617 | 20,665 | -22% | 1 | 1 | 0% | 4,123 | 3,631 | -12% | 0 | 0 | — |
case-22 | pass→fail | 20,266 | 4,017 | -80% | 1 | 1 | 0% | 3,225 | 756 | -77% | 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, and 4 counted toward the lift figure. The other 18 produced results that are not comparable between the two arms, so they are excluded from the headline rather than averaged into it. The headline lift of -23 percentage points is the difference between those two pass rates over the 4 comparable cases. 14 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.