Visual Style Direction

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 — a statement supported by a standard, first-party technical document, or institutional source.
• Research finding — a result from a cited empirical study; apply only within the study's limits.
• Production heuristic — a practical rule of thumb. Treat it as a testable default, not a law.

Keep these categories distinct in the direction packet. Never present taste, convention, or a provider behavior as a standard.

Deliverable contract

Produce a visual direction packet that is usable without access to the original conversation. It must contain:

1. brief interpretation and unresolved assumptions;
2. a one-sentence direction thesis;
3. reference ledger and originality analysis;
4. invariants, controlled variables, and explicit anti-patterns;
5. palette, contrast pairs, typography, layout, texture/material, lighting, camera/lens, and motion systems;
6. continuity rules for recurring subjects, locations, graphics, and shots;
7. accessibility and rights constraints;
8. portable design tokens plus non-token production rules;
9. image and video adaptation rules, including aspect-ratio behavior;
10. representative proof-frame or proof-shot specifications;
11. handoff metadata, acceptance tests, and a repair log.

Do not bury decisions in prose. Every consequential choice needs a stable name, rationale, allowed range, and test.

Scope boundaries

Use this skill to decide what the work should look and move like across tools. Hand the resulting system to image-generation, video-generation, animation, editing, layout, or finishing skills.

Do not:

• prescribe a provider, endpoint, model identifier, seed syntax, or provider-specific prompt grammar;
• substitute a mood board for a production specification;
• promise that a generated sample guarantees continuity across a batch;
• infer permission to use brand assets, likenesses, locations, fonts, footage, or reference works;
• claim legal clearance. Surface the facts and request review when risk is material.

Start with constraints, not aesthetics

Extract the following before proposing a direction:

| Area | Questions to resolve | |---|---| | Communication | What must the viewer understand, feel, remember, or do? | | Audience | Who is included, excluded, represented, or potentially misread? | | Brand | Which supplied assets and rules are authoritative? Which are only examples? | | Deliverables | Still, sequence, film, social cutdowns, thumbnails, UI, print; required ratios and durations? | | Production | Live action, generated media, 2D/3D, compositing, edit, or a hybrid? What can actually be controlled downstream? | | Continuity | Which subjects, products, spaces, props, wardrobe, marks, and facts recur? | | Accessibility | Captions, audio description, reduced-motion version, text alternatives, contrast target, reading conditions? | | Rights | Source, owner, license, territory, term, model/property releases, trademark constraints, synthetic-media disclosure? | | Color | SDR/HDR, display/print targets, working space, output transform, embedded profile, review environment? | | Approval | Who approves the route, proof frames, continuity sheet, and final master? |

If a missing answer changes the direction materially, ask. If it only changes an implementation detail, state a reversible assumption and continue.

Analyze references without imitating them

Build a reference ledger

Record every reference with:

• identifier and source;
• who supplied it;
• known owner and usage permission;
• intended use: content, mood, composition, material, lighting, optical, motion, typography, or production technique;
• observed evidence: what is visibly or audibly present;
• interpretation: the effect that evidence creates;
• transferable mechanism: an abstract rule that can be reused;
• identity-bearing details to exclude: protected artwork, distinctive character design, logo, trade dress, exact layout, signature motif, unique prop, recognizable sequence, or artist-specific combination;
• confidence and unresolved questions.

Use descriptions such as “low-key side light with rapid falloff and a small warm practical in the background,” not “cinematic like Reference A.”

Decompose at four levels

1. Purpose — what communication job is the reference doing?
2. Mechanism — how do hierarchy, rhythm, contrast, staging, or camera choices perform that job?
3. Surface — which palette, texture, type, props, and motifs make it recognizable?
4. Identity — which exact expressive choices or brand signals belong to that source?

Transfer purpose and general mechanisms. Rebuild surface choices from the new brief. Exclude identity-bearing details unless supplied and licensed for use.

Research finding: Controlled design-fixation experiments found that examples can cause designers to reproduce example features and narrow conceptual output. The finding originated in engineering-design tasks, so use it as a warning about reference exposure, not proof that every mood board causes fixation. Counter it by analyzing multiple functionally different sources, delaying surface decisions until the brief is stated, and documenting exclusions. See Jansson and Smith, “Design Fixation,” Design Studies 12(1), 1991 (DOI page90003-F)).

Run an originality pass before route approval

Ask:

• If the reference were hidden, would the proposed system still follow from the brief?
• Are its distinctive composition, palette relationship, motif, typography, and camera sequence all retained together? If so, redesign.
• Does one reference dominate more than one identity-bearing layer?
• Can each major choice be justified by audience, message, production, or brand evidence?
• Is the result likely to imply affiliation with another source or brand?
• Could a reviewer point to a particular frame or work and identify copied expressive details?

Documented fact, U.S. context: The U.S. Copyright Office notes that style standing alone is generally not protected by copyright, while original pictorial and graphic expression can be protected and permission may be needed to use another person's work. That distinction does not make imitation risk-free: individual expressive elements, derivative-work rights, contract, publicity, and trademark issues remain. The USPTO explains that confusing similarity can arise from appearance, meaning, or overall commercial impression. Use this as a risk screen, not legal advice. See the Copyright Office Digital Replicas report, Copyright for Visual and Graphic Artists, and USPTO likelihood-of-confusion guidance.

When a user names a living artist or asks for a near-copy, decline the identity-bearing imitation and offer a mechanism-based direction using broader era, medium, lighting, composition, material, and emotional attributes.

Create contrastive routes, then converge

Propose two to four routes that solve the same communication problem through meaningfully different systems. Change at least three structural dimensions across routes, such as:

• hierarchy and information density;
• spatial organization and negative space;
• chroma/value strategy;
• material logic;
• lighting logic;
• optical distance and camera behavior;
• motion energy and transition logic;
• typography role.

Do not make “Route B” a color swap of Route A.

For each route, provide:

• name and one-sentence thesis;
• three governing principles;
• signature move;
• proof-frame description;
• likely strength;
• likely failure mode;
• cost/complexity implication;
• reference mechanisms used and identity details excluded.

Recommend one route against the brief. Preserve rejected routes as decision history; do not silently blend them into the approved route.

Write the direction thesis and grammar

The thesis must contain a communication intent, a visual tension, and a behavioral rule.

Weak: “Premium, modern, cinematic.”

Strong: “Make technical precision feel tactile: rigid editorial geometry contains warm, imperfect materials, while the camera moves only when a relationship becomes clearer.”

Translate the thesis into:

• invariants — must remain stable across every asset;
• controlled variables — may change within named ranges;
• exceptions — allowed only in stated narrative conditions;
• anti-patterns — tempting moves that would break the direction.

Invariant/variable test

| Element | Invariant | Controlled variable | Failure signal | |---|---|---|---| | Subject | recognizable silhouette, product geometry | pose, crop, expression | anatomy/mark changes between shots | | Composition | one dominant mass, upper-left text reserve | subject scale 35–60% frame height | equal-weight clutter | | Light | large cool key, narrow warm practical | key angle ±15°, practical position | flat frontal fill or mixed-white imbalance | | Motion | purposeful translation, no idle drift | amplitude by beat importance | constant motion with no information role |

Encode a portable token layer

Use tokens for reusable atomic and semantic values. Use prose or structured ledgers for relationships that are not reducible to a value, such as “camera movement must reveal causality.”

Separate:

1. primitive tokens — raw color, dimension, duration, typeface, weight;
2. semantic tokens — color.text.primary, color.surface.hero, motion.duration.emphasis;
3. application rules — “hero text uses color.text.on-dark only over surfaces passing the target contrast test.”

Avoid names tied to a current value (blue-500) when the role matters (accent-action). Keep source values and output-space values distinct.

When a color token carries redundant representations such as numeric components and a fallback hex, validate that they encode the same color in the declared color space. Prefer one authoritative representation over contradictory convenience fields. Run a token parser or color-conversion check before handoff; a syntactically valid token with mismatched values is not portable.

Documented fact: The Design Tokens Community Group describes tokens as a platform-agnostic way to exchange design decisions. Its first stable format, 2025.10, uses typed tokens with $value, supports groups and references, and defines types including color, typography, dimension, duration, stroke, gradient, and shadow. Verified 2026-07-09. Follow the stable specification when interchange is required; keep camera, lighting, composition, and continuity ledgers beside it rather than inventing nonstandard token types. See DTCG Format Module 2025.10.

Example: portable DTCG token excerpt

This is an example, not a mandatory palette.

{
  "color": {
    "ink": {
      "$type": "color",
      "deep": {
        "$value": {
          "colorSpace": "srgb",
          "components": [0.055, 0.071, 0.09],
          "hex": "#0E1217"
        }
      }
    },
    "text": {
      "$type": "color",
      "on-dark": {
        "$value": {
          "colorSpace": "srgb",
          "components": [0.957, 0.941, 0.902],
          "hex": "#F4F0E6"
        }
      }
    }
  },
  "motion": {
    "duration": {
      "$type": "duration",
      "settle": { "$value": { "value": 420, "unit": "ms" } }
    }
  },
  "type": {
    "title": {
      "$type": "typography",
      "$value": {
        "fontFamily": ["Approved Display Family", "sans-serif"],
        "fontSize": { "value": 64, "unit": "px" },
        "fontWeight": 650,
        "lineHeight": 1.02
      }
    }
  }
}

Also provide a human-readable token table with role, value, allowed use, prohibited use, contrast partners, and fallback.

Label numeric layout, type, motion, and safe-area ranges as proof-set starting points until they have been tested against the actual regulated copy, device sizes, platform UI, viewing distance, and encoded deliverables. Promote them to approved constraints only after the relevant proof gate passes.

Build the color and contrast system

Define color by function and relationship:

• canvas/surface hierarchy;
• primary text and secondary text;
• brand/accent roles;
• semantic states;
• data-series colors;
• skin/product protection ranges if relevant;
• highlight/shadow hue bias;
• saturation budget;
• monochrome fallback;
• output color space and review transform.

Specify dominant/support/accent proportions as flexible ranges, not decorative arithmetic. Test all important pairs on actual textured, graded, and moving backgrounds—not only flat swatches.

Documented fact: WCAG 2.2 Level AA specifies at least 4.5:1 contrast for normal text, 3:1 for large text, and 3:1 for graphical objects needed to understand content. It also states that color must not be the only visual means of conveying information. These are web-content criteria, not a universal cinema-grading standard; use them as minimum acceptance tests for web/UI overlays, captions, diagrams, and related assets, then test in the real delivery environment. See WCAG 2.2 §§1.4.1, 1.4.3, 1.4.11.

For moving footage, evaluate worst-case frames. Add a backing plate, local darkening, outline, shadow, repositioning, or alternate color token when a pair fails. Never “solve” contrast solely by making everything white or black if hierarchy is lost.

Color-management handoff

Record:

• source and working color spaces;
• transfer function/gamma where applicable;
• display/view transform used for approvals;
• target deliverable space and peak luminance where applicable;
• embedded ICC profile or equivalent metadata;
• LUT/look-transform name, version, and whether it is creative or technical;
• review-monitor assumptions;
• SDR/HDR trim strategy;
• gamut and clipping checks.

Documented fact: ICC profiles connect color encodings across devices, and embedded profiles support interpretation of image data across systems. ACES separates a creative Look Transform from an Output Transform for a specific display and viewing condition; ACES Metadata Files can track input, look, and output transforms. Do not bake an unknown display look into source assets and call it portable. See the ICC profile-format introduction, ACES system overview, ACES Look Transforms, and ACES Output Transforms.

Specify typography as behavior

For each role—display, heading, body, caption, data label, supers, legal—specify:

• approved family and licensed files;
• fallback stack;
• supported scripts/languages and missing-glyph plan;
• weight, width, optical size, case, tracking, leading;
• minimum rendered size at each delivery resolution;
• maximum line length/line count;
• alignment and rag behavior;
• background treatment;
• safe-area behavior;
• entrance, hold, emphasis, and exit behavior for time-based work;
• localization expansion tolerance.

Do not describe a typeface only as “bold sans.” Test the exact family at final pixel size, compression, motion, and viewing distance. Keep essential copy editable until final render; generation systems are not reliable typesetters.

For captions,

…

Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

• Author: calesthio
• Source: calesthio/generative-media-skills
• License: MIT
• Homepage: https://github.com/calesthio/OpenMontage

Install and usage instructions live in the source repository linked above.