visual-style-direction
Translate a creative brief, brand system, or reference set into an original, portable visual-direction system for image and video production. Use for art direction, reference analysis without imitation, design tokens, palette and contrast, typography, composition, texture and material, lighting, lens and camera language, motion language, cross-shot continuity, accessibility, production handoff, visual review, and repair; do not use for provider-specific API syntax or model-specific prompt recipes.
npx skills add calesthio/generative-media-skills --skill visual-style-direction --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
What it does
Directs the creation of a visual-direction system that an agent can execute repeatedly, translating a brief into observable rules, portable artifacts, and a proofed system for image and video production.
How it works
- Requires building a visual direction packet containing interpretation, thesis, reference ledger, invariants, tokens, production rules, and proof frames.
- Specifies to decompose references into four levels (Purpose, Mechanism, Surface, Identity) and to run an originality pass that questions retention of brief-driven identity when references are removed.
- Proposes creating two to four divergent routes with names, theses, governing principles, signature moves, proof-frame descriptions, and risk/complexity analyses, then selecting one route.
- Instructs encoding a portable token layer with primitive and semantic tokens plus application rules, plus a human-readable token table and proof-set ranges.
- Mandates a color and contrast system influenced by WCAG 2.2 and to document color management handoff details (spaces, transforms, LUTs, ICC profiles).
- Requires typography by role with family, fallback, and language support, and explicit design-token governance.
- Prohibits provider-specific syntax and brand asset permission assumptions; emphasizes not imitating references and maintaining anti-patterns.
When to use it
Use to decide what the work should look and move like across tools, and to hand off a fully specified system to image-generation, video-generation, animation, editing, layout, or finishing skills. Triggered when a brand brief requires a portable, testable visual grammar rather than output edits.
What it can touch
- Design tokens: primitive tokens, semantic tokens, application rules.
- Visual-direction artifacts: thesis, invariants, controlled variables, exceptions, anti-patterns, proof-frames, and handoff metadata.
- Color and typography systems, contrast rules, and accessibility constraints.
- Reference ledger and originality analysis constructs.
Caveats
- Do not prescribe provider endpoints or model prompts; stay within a direction packet scope.
- Ensure decisions are traceable with a documented fact-based rationale; avoid identity-bearing imitation of references unless licensed.
- Contains explicit discussions of copyright risk and anti-patterns; apply as risk screening rather than legal advice.
# Direct the visual system Create a visual grammar that another production agent can execute repeatedly, not a pile of adjectives and not a clone of a reference. Translate intent into observable rules, encode the rules in portable artifacts, prove them on representative frames or shots, and repair the system rather than patching isolated outputs. ## Evidence labels used here - **Documented fact**
What does the visual-style-direction skill do?
Translate a creative brief, brand system, or reference set into an original, portable visual-direction system for image and video production. Use for art direction, reference analysis without imitation, design tokens, palette and contrast, typography, composition, texture and material, lighting, lens and camera language, motion language, cross-shot continuity, accessibility, production handoff, visual review, and repair; do not use for provider-specific API syntax or model-specific prompt recipes.
How do I install it?
Run `npx skills add calesthio/generative-media-skills --skill visual-style-direction --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From calesthio/generative-media-skills, a repository with 112 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.