Content
92%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
A highly actionable, concise code skill with a clear init sequence and QA validation checklist. Its only weakness is progressive disclosure: it is a single large file with no bundle references, where some recipe sections could be split out.
Suggestions
Move the longer recipe sections (e.g., Pinned Scroll Scenes, Hover/Cursor/Layer recipes) into reference files under references/ and link to them one level deep from SKILL.md to reduce the monolithic body.
Consider extracting the Base Tokens table and Choreography/Performance rules into a references/tokens-and-rules.md so the main body stays a concise overview.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Lean and efficient: it assumes Claude knows GSAP/Lenis, never explains what the libraries are, and every section delivers token-tuned values or executable code with minimal prose ('Eases: power3.out', 'scrub: 0.8 to 1.4'). | 3 / 3 |
Actionability | Fully executable, copy-paste-ready code throughout — Setup initialization, splitWords/splitLines, revealPresets map, parallax/pin timelines, quickTo magnetic hover, plus a concrete Init Order sequence. Specific numeric tokens make recipes directly applicable. | 3 / 3 |
Workflow Clarity | Clear sequence via the 'Init Order' section listing all init functions in order with a final ScrollTrigger.refresh(), plus a 'QA Checklist' providing explicit verification checkpoints (JS-disabled visibility, reduced-motion, touch-disabled interactions, no animated layout properties). | 3 / 3 |
Progressive Disclosure | Well-organized with clear section headers and a helpful 'Use When' overview, but the ~610-line skill is monolithic — no references/, scripts/, or assets/ bundle files exist, so detailed recipe sections that could live in separate one-level-deep files are all inline. Not a level-3 split-across-files structure; not a level-1 wall of text either. | 2 / 3 |
Total | 11 / 12 Passed |