Overview Benchmark Contents Activity Versions 1 Ratings 0
What's inside The instructions your model reads when the skill loads.
SKILL.md 31 lines single file
Emil Kowalski Motion Follow-Up
Use this skill after a design artifact already exists. The goal is to make the interface feel alive without turning it into a motion demo.
Workflow
Inspect the current HTML, component, or selected page element before adding animation.
Pick the smallest set of motion moments that clarify state or hierarchy:
entry reveal for the primary content
hover / active feedback for important controls
transition between UI states
scroll reveal only when it helps the story
Prefer transform and opacity. Avoid animating layout properties such as top, left, width, or height.
Use one motion language across the artifact. Do not mix unrelated easings, durations, or physics.
Add prefers-reduced-motion fallbacks for any automatic or scroll-linked motion.
Keep copy, data, and layout intent intact unless the user explicitly asks for a redesign.
Motion Rules
Default UI transitions should feel quick and useful: 140-220ms for most controls.
Larger page reveals can be slower, but must not block reading.
Avoid endless decorative loops unless they communicate status or progress.
Do not add custom cursors, noisy particle effects, or motion that competes with content.
Stagger only small groups. Long staggered lists make interfaces feel slow.
Implementation Notes
For plain HTML, CSS keyframes and small JavaScript observers are enough.
For React or framework code, use the local stack already present in the repo.
If GSAP is available and the motion needs sequencing, pair this with gsap-core, gsap-timeline, or gsap-scrolltrigger.
Always clean up observers, timers, and animation instances.
Track record Benchmark 7 / 22
test cases passed, vs 0 / 22 without
Adoption
Users 0
Times used 0 View activity → Safety and source details
SkillSafety ✓ 3 of 3 passed ✓ Code scan 15 of 15 checks clean
0 critical · 0 warning · 0 info — scanner v4 — 7/30/2026
View 15 scanner checks live_secret remote_code_execution reverse_shell data_exfiltration ssrf_metadata agent_snooping anti_refusal destructive_commands obfuscated_unicode unicode_homoglyph opaque_blob suspicious_url tool_overreach trigger_abuse prompt_injection_phrasing
✓ Intent Safe
LLM judge · does the skill do what it claims
✓ Content Clean
LLM judge · policy & harmful-content review
Source Imported License Apache-2.0Imported 8/8/2026Version v1