Agent skill
recipe-refine-visuals
Optional side-workflow for design experts to refine auto-derived Visual Tokens in brand-direction.md with professional judgment
Install this agent skill to your Project
npx add-skill https://github.com/shinpr/claude-code-discover/tree/main/skills/recipe-refine-visuals
SKILL.md
Context: Refine the Visual Tokens section of docs/product/design/brand-direction.md with design expertise. This recipe reads the existing brand direction (including auto-derived tokens from recipe-blueprint) and lets a design expert override specific values with professional judgment. The output is the same brand-direction.md file — downstream consumers (prototype-generator, UI Spec) read it without knowing which path produced the tokens.
When to Use
- After
recipe-blueprinthas completed andbrand-direction.mdexists with auto-derived Visual Tokens - When a design expert is available and wants to refine the visual system
- This recipe is entirely optional — auto-derived tokens are sufficient for prototype generation
Orchestrator Definition
Execution Protocol:
- Follow the refinement flow defined below
- Stop at every
[STOP — BLOCKING]marker — present findings and CANNOT proceed until user explicitly confirms
Workflow Overview
Input (existing brand-direction.md with auto-derived tokens)
↓
1. Context Reading → Read brand direction + design principles + personas
↓
2. Token Review → Present current tokens with their derivation rationale
↓
3. Expert Refinement → User specifies overrides [Stop: User confirms changes]
↓
Output: Updated Visual Tokens in docs/product/design/brand-direction.md
Execution Decision Flow
1. Context Reading
Gate: docs/product/design/brand-direction.md must exist with a Visual Tokens section. If missing → inform user to run recipe-blueprint first.
Read:
docs/product/design/brand-direction.md— current direction and auto-derived tokensdocs/product/design-principles.md— trade-off contextdocs/product/personas/— audience context- Reference Products listed in brand-direction — use WebSearch to inspect their current design if needed
2. Token Review
Present the current Visual Tokens organized by category, showing:
- Current value and its derivation source
- How it relates to the directional sections above it
- Any inconsistencies between tokens (e.g., contrast ratio issues between text and surface colors)
Highlight areas where expert judgment would have the most impact:
- Color harmony and palette coherence
- Font pairing quality
- Spacing scale appropriateness for the product's density target
3. Expert Refinement
Guide the expert through each token category:
Color Tokens
- Present current palette as a visual summary (hex values with role labels)
- Ask: which values to keep, which to override
- Validate contrast ratios:
--color-textagainst--color-surfacemust meet WCAG AA (4.5:1 for body text) - Validate color harmony across the full palette
Typography Tokens
- Present current font selections with Google Fonts links
- Ask: alternative font pairings, size adjustments, weight preferences
- Validate: heading/body contrast is sufficient for hierarchy
- Validate: selected fonts support the product's language(s)
Spacing Tokens
- Present current scale with the base unit
- Ask: base unit adjustment, scale ratio preferences
- Validate: scale produces enough differentiation between levels
For each override, record the expert's rationale in the Decisions Log.
[STOP — BLOCKING] Present the refined token set to user for confirmation:
- Side-by-side comparison: auto-derived vs. expert-refined values
- Rationale for each change
- Contrast and harmony validation results
CANNOT update the file until user explicitly confirms.
4. File Update
After user approval:
- Update the Visual Tokens section in
docs/product/design/brand-direction.md - Change Source field from
auto-derivedtoexpert-refined - Add override entries to the Brand Direction Decisions Log
Scope Boundaries
Included: Visual Token refinement (colors, typography, spacing) within the existing brand-direction.md Not included: Changing directional sections (Tone & Voice, Color Direction, etc.), adding new sections, component-level specifications, responsive breakpoints
Completion Criteria
- Existing brand-direction.md read with auto-derived tokens
- Current tokens reviewed with derivation context
- Expert overrides collected with rationale
- Contrast and harmony validated
- User confirmed refined tokens
- brand-direction.md updated with source marked as
expert-refined - Decisions logged in Brand Direction Decisions Log
Recommended Agent Skills
Expand your agent's capabilities with these related and highly-rated skills.
recipe-persona
Create or update personas with demographic, contextual, JTBD, and behavioral data
prd-standards
Defines PRD structure, user story format with 4 Risks assessment, EARS-format acceptance criteria, and delivery readiness thresholds. Use when writing PRDs, drafting user stories, defining acceptance criteria, or reviewing PRD quality and completeness.
recipe-vision
Define or update product vision, strategy, outcomes, and NSM
design-perspective
Integrates design principles, WCAG 2.2 AA accessibility, persona context, and state design into product decisions. Use when reviewing UX decisions, checking accessibility, applying design principles, or ensuring state coverage in acceptance criteria.
prototype-guide
Generates self-contained HTML prototypes with design context from project files. Read design principles, personas, and hypothesis files, then produce a working prototype for Usability and Value risk validation. Use when creating prototypes or validating through tangible artifacts.
recipe-validate
Orchestrate hypothesis validation through type-appropriate methods — prototypes, code analysis, market research, and expert review
Didn't find tool you were looking for?