Premium Visual Reference Library
Use this skill to pick reference sources before designing a premium website.
Workflow
- Identify the site category: product/devtool, luxury/editorial, portfolio, hospitality, commerce, personal, agency, or content/media.
- Read sources.md for the relevant source clusters.
- When the user names a creator, asks for many examples, or uses a style shorthand, also read creator-and-pattern-index.md and creator-methods-evidence.md.
- When Viktor Oddy or MotionSites is named, read motionsites-viktor-evidence.md and refresh any count or catalog claim that matters to the current project.
- Select enough distinct references for the open decision; 3–7 is a broad direction-study option, not a quota for a supplied exact reference.
- Extract concrete patterns: type, layout, density, media, motion, CTA, proof, navigation, section rhythm, and mobile behavior.
- State what not to copy.
- When implementation is in scope, add selected traits to the shared build spec; a reference-only request ends with the source-backed study.
For systematic direction work, consult references/style-playbooks.json, references/reference-example-patterns.json, references/creator-method-cards.json, and references/viktor-visual-studies.json. They contain 50 author-created direction playbooks, 100 primary-source implementation leads with generalized mechanism interpretations, 22 dated creator-method interpretations, and 20 historical visual-study records whose repeated study text is generic synthesis. The 172 URLs across the first three catalogs passed a live reachability check on 2026-08-16; refresh mutable URLs before consequential reuse.
Source Fidelity
Preserve exact user-supplied or user-owned prompts when requested. Otherwise use references to understand quality and label independent reconstructions accurately; do not claim third-party brand assets, copy, or unobserved behavior as owned or verified.
Read catalog provenance overlay before item-level evidence claims. Raw catalogs retain all original text/URLs unchanged. The overlay separates dated claims, generalized defaults and currently recoverable evidence. Generic repeated study text is not independently observed per-item evidence. Inspect exact selected references when reusing them; do not recrawl every catalog or assume all historical image paths still resolve.
1---2name: premium-visual-reference-library3description: Find references, Viktor Oddy and MotionSites.4---56# Premium Visual Reference Library78Use this skill to pick reference sources before designing a premium website.910## Workflow11121. Identify the site category: product/devtool, luxury/editorial, portfolio, hospitality, commerce, personal, agency, or content/media.132. Read [sources.md](references/sources.md) for the relevant source clusters.143. When the user names a creator, asks for many examples, or uses a style shorthand, also read [creator-and-pattern-index.md](references/creator-and-pattern-index.md) and [creator-methods-evidence.md](references/creator-methods-evidence.md).154. When Viktor Oddy or MotionSites is named, read [motionsites-viktor-evidence.md](references/motionsites-viktor-evidence.md) and refresh any count or catalog claim that matters to the current project.165. Select enough distinct references for the open decision; 3–7 is a broad direction-study option, not a quota for a supplied exact reference.176. Extract concrete patterns: type, layout, density, media, motion, CTA, proof, navigation, section rhythm, and mobile behavior.187. State what not to copy.198. When implementation is in scope, add selected traits to the shared build spec; a reference-only request ends with the source-backed study.2021For systematic direction work, consult `references/style-playbooks.json`, `references/reference-example-patterns.json`, `references/creator-method-cards.json`, and `references/viktor-visual-studies.json`. They contain 50 author-created direction playbooks, 100 primary-source implementation leads with generalized mechanism interpretations, 22 dated creator-method interpretations, and 20 historical visual-study records whose repeated study text is generic synthesis. The 172 URLs across the first three catalogs passed a live reachability check on 2026-08-16; refresh mutable URLs before consequential reuse.2223## Source Fidelity2425Preserve exact user-supplied or user-owned prompts when requested. Otherwise use references to understand quality and label independent reconstructions accurately; do not claim third-party brand assets, copy, or unobserved behavior as owned or verified.2627Read [catalog provenance overlay](references/catalog-provenance-overlay.json) before item-level evidence claims. Raw catalogs retain all original text/URLs unchanged. The overlay separates dated claims, generalized defaults and currently recoverable evidence. Generic repeated study text is not independently observed per-item evidence. Inspect exact selected references when reusing them; do not recrawl every catalog or assume all historical image paths still resolve.
