agentleFS
wrg32786wrg32786/aigent-design-system/skills/cinematic-studio/SKILL.md

cinematic-studio

Skill4 starsChanged 3 months agoMITView on GitHub

Route a cinematic website from product context through asset production, runtime selection, implementation, and QA. Use when the request spans design direction, generated or sourced media, 3D, video, motion, or full Awwwards-style website production.

The file

We split this skill into the rules it gives an agent

7 rules. About 0 are common, 5 are distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈5

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 2

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Use this as the umbrella workflow for the repository.

    line 8
  2. Very specific:

    Use cinematic-web-director to determine:

    line 22
  3. Very specific:

    Use creative-asset-director when the required media does not exist.

    line 34
  4. Distinctive:

    Use HyperFrames when an existing website, HTML interface, design system, or agent-authored page should become deterministic video.

    line 44
  5. Distinctive:

    Use Remotion when a React-first composition is already the correct durable source.

    line 46
  6. Distinctive:

    no credentials, private URLs, or personal records

    line 84
  7. Distinctive:

    Do not declare a cinematic page complete when only prompts or asset suggestions exist.

    line 86

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 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

Cinematic Studio

Use this as the umbrella workflow for the repository.

Read first

  1. PRODUCT.md
  2. DESIGN.md
  3. the target project's product and design context
  4. creative-production/README.md
  5. integrations/catalog.json

Route the work

Direct

Use cinematic-web-director to determine:

  • surface mode
  • visitor success
  • product proof
  • visual world
  • dominant composition
  • one signature motion idea
  • anti-references

Produce

Use creative-asset-director when the required media does not exist.

It routes to:

  • video-asset-pipeline
  • web-3d-asset-pipeline
  • hyperframes-video
  • remotion-web-assets
  • Spline or Three.js scene production

Use HyperFrames when an existing website, HTML interface, design system, or agent-authored page should become deterministic video. Install and reuse the official upstream HyperFrames skills rather than recreating its composition and CLI rules.

Use Remotion when a React-first composition is already the correct durable source. Use a literal screen recording when authored motion and reusable variants do not earn their cost.

Build

Choose only the runtime the requirement earns:

  • native CSS and modules/motion.js
  • GSAP
  • model-viewer
  • Spline
  • Three.js
  • React Three Fiber
  • Rive

HyperFrames and Remotion are usually build-time media producers, not website runtime dependencies.

Verify

Use:

  • asset-provenance-audit
  • cinematic-site-qa
  • npm run assets
  • npm run catalogs
  • npm run audit
  • npm run smoke

Deliverable contract

A complete result includes:

  • product-specific page
  • production media or a clearly labeled replaceable demonstration asset
  • desktop and mobile states
  • reduced motion
  • source and license manifest
  • optimized web outputs
  • browser verification
  • no credentials, private URLs, or personal records

Do not declare a cinematic page complete when only prompts or asset suggestions exist. The page needs usable outputs in hand or an honest explicit placeholder contract.

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.