agentleFS
TheGoat395TheGoat395/Codex-Skills/skills/premium-visual-reference-library/SKILL.md

premium-visual-reference-library

Skill136 starsChanged 5 months agoMITView on GitHub

Find references, Viktor Oddy and MotionSites.

The file

We split this skill into the rules it gives an agent

6 rules. About 0 are common, 6 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈6

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Use this skill to pick reference sources before designing a premium website.

    line 8
  2. Distinctive:

    Read sources.md for the relevant source clusters.

    line 13
  3. Distinctive:

    When the user names a creator, asks for many examples, or uses a style shorthand, also read creator-and-pattern-index.md and …

    line 14
  4. Distinctive:

    When Viktor Oddy or MotionSites is named, read motionsites-viktor-evidence.md and refresh any count or catalog claim that matters to the …

    line 15
  5. Distinctive:

    When implementation is in scope, add selected traits to the shared build spec.

    line 19
  6. Distinctive:

    Use the bundled read-only helper from any working directory:

    line 23

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Premium Visual Reference Library

Use this skill to pick reference sources before designing a premium website.

Workflow

  1. Identify the site category: product/devtool, luxury/editorial, portfolio, hospitality, commerce, personal, agency, or content/media.
  2. Read sources.md for the relevant source clusters.
  3. 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.
  4. 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.
  5. Select enough distinct references for the open decision; 3–7 is a broad direction-study option, not a quota for a supplied exact reference.
  6. Extract concrete patterns: type, layout, density, media, motion, CTA, proof, navigation, section rhythm, and mobile behavior.
  7. State what not to copy.
  8. When implementation is in scope, add selected traits to the shared build spec; a reference-only request ends with the source-backed study.

Retrieve only the selected material

Use the bundled read-only helper from any working directory:

python3 "<skill-root>/scripts/query_catalog.py" --search "reorder" --limit 5
python3 "<skill-root>/scripts/query_catalog.py" --id M-01

Resolve <skill-root> to this skill's actual installation. Search returns bounded discovery results; exact ID returns the original record with its provenance and limitations. The helper checks source fingerprints against the overlay, makes no external requests and writes nothing. If Python is unavailable, search the named JSON file for the selected ID and read that record plus its matching overlay record; no helper installation is required.

The four raw catalogs preserve 50 author-created style playbooks, 100 implementation leads, 22 dated creator-method interpretations and 20 historical video-study records. Repeated mechanism text is generic inference, not verified example code; repeated video-study text is synthesis, not independent per-video observation. Fixed palette, timing, target-size, frame-time and DPR values are illustrative starting choices, not universal standards or measured budgets. Inspect the selected live source and current technical documentation before relying on its actual behavior. Do not load or recrawl every catalog for one reference.

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.

Use the matching record in the catalog provenance overlay before item-level evidence claims; the exact-ID helper includes it. 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.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.