agentleFS
etretr/groundwork/skills/source-ux-design-from-code/SKILL.md

source-ux-design-from-code

Skill45 starsChanged 4 days agoMITView on GitHub

Synchronize design system document with codebase changes. Usage /groundwork:source-ux-design-from-code

The file

Show its rules and text

We split this skill into the rules it gives an agent

24 rules. About 0 are common, 13 are distinctive, and 11 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈13

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 11

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    If effort is low or medium (i.e.

    line 18
  2. Distinctive:

    If you are not Sonnet or Opus, you MUST show the recommendation prompt - regardless of effort level.

    line 19
  3. Distinctive:

    If the user selects "Cancel — I'll switch first": output the switching commands above and stop.

    line 37
  4. Very specific:

    If yes → Is {{project_name}} non-empty?

    line 44
  5. Very specific:

    If empty → Invoke Skill(skill="groundwork:select-project") to select a project, then restart this skill.

    line 45
  6. Very specific:

    If set → Project is {{project_name}}, specs at {{specs_dir}}/.

    line 46
  7. Distinctive:

    If no → Continue (single-project repo).

    line 47
  8. Distinctive:

    If CWD is the repo root → fine, proceed.

    line 50
  9. Very specific:

    Check which project's path CWD falls inside (compare against all projects in .groundwork.yml).

    line 51
  10. Distinctive:

    If CWD is inside the selected project's path → fine, proceed.

    line 52
  11. Very specific:

    If CWD is inside a different project's path → warn via AskUserQuestion:

    line 53
  12. Very specific:

    If the user switches, invoke Skill(skill="groundwork:select-project").

    line 57
  13. Distinctive:

    If CWD doesn't match any project → proceed without warning (shared directory).

    line 58
  14. Distinctive:

    Detection: Check for single file first (takes precedence), then directory.

    line 68
  15. Distinctive:

    Apply Changes: - Update document with user approval

    line 84
  16. Distinctive:

    Detect spec format: - Check if design system is single file or directory

    line 216
  17. Distinctive:

    Update "Last updated" timestamp

    line 233
  18. Very specific:

    If {{specs_dir}}/ux-preview.html exists, regenerate it to reflect the updated design system decisions

    line 234
  19. Distinctive:

    Update "Status" if appropriate

    line 235
  20. Distinctive:

    Never reuse deleted decision IDs (maintain traceability)

    line 239
  21. Distinctive:

    When multiple sync commands run:

    line 298
  22. Very specific:

    Run /groundwork:source-product-specs-from-code first (product drives design)

    line 299
  23. Very specific:

    Run /groundwork:source-ux-design-from-code second (design supports product)

    line 300
  24. Very specific:

    Run /groundwork:source-architecture-from-code last (architecture implements both)

    line 301

≈ “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

Sync Design System Skill

Keeps {{specs_dir}}/design_system.md synchronized with design implementation decisions made during sessions.

Pre-flight: Model Recommendation

Your current effort level is {{effort_level}}.

Skip this step silently if effort is high, xhigh, or max (the scale is low < medium < high < xhigh < max, so xhigh and max are already above high) AND you are Sonnet or Opus. If effort is low or medium (i.e. below high), you MUST show the recommendation prompt — regardless of model. If you are not Sonnet or Opus, you MUST show the recommendation prompt - regardless of effort level.

Otherwise → use AskUserQuestion:

{
  "questions": [{
    "question": "Do you want to switch? Design token and pattern change categorization benefits from consistent reasoning.\n\nTo switch: cancel, run `/effort high` (and `/model sonnet` if on Haiku), then re-invoke this skill.",
    "header": "Recommended: Sonnet or Opus at high effort",
    "options": [
      { "label": "Continue" },
      { "label": "Cancel — I'll switch first" }
    ],
    "multiSelect": false
  }]
}

If the user selects "Cancel — I'll switch first": output the switching commands above and stop. Do not proceed with the skill.

Step 0: Resolve Project Context

Before loading specs, ensure project context is resolved:

  1. Monorepo check: Does .groundwork.yml exist at the repo root?
    • If yes → Is {{project_name}} non-empty?
      • If empty → Invoke Skill(skill="groundwork:select-project") to select a project, then restart this skill.
      • If set → Project is {{project_name}}, specs at {{specs_dir}}/.
    • If no → Continue (single-project repo).
  2. CWD mismatch check (monorepo only):
    • Skip if not in monorepo mode or if the project was just selected in item 1 above.
    • If CWD is the repo root → fine, proceed.
    • Check which project's path CWD falls inside (compare against all projects in .groundwork.yml).
    • If CWD is inside the selected project's path → fine, proceed.
    • If CWD is inside a different project's path → warn via AskUserQuestion:

      "You're working from <cwd> (inside [cwd-project]), but the selected Groundwork project is [selected-project] ([selected-project-path]/). What would you like to do?"

      • "Switch to [cwd-project]"
      • "Stay with [selected-project]" If the user switches, invoke Skill(skill="groundwork:select-project").
    • If CWD doesn't match any project → proceed without warning (shared directory).
  3. Proceed with the resolved project context. All {{specs_dir}}/ paths will resolve to the correct location.

File Locations

  • Target: Design system document (may be single file or directory)
    • Single file: {{specs_dir}}/design_system.md
    • Directory: {{specs_dir}}/design_system/ (content split across files)
  • Context: Current session history, codebase changes

Detection: Check for single file first (takes precedence), then directory.

When to Trigger

This skill should activate when:

  • User explicitly invokes /groundwork:source-ux-design-from-code
  • Session involved design token changes (colors, spacing, typography)
  • Component styling decisions were made
  • UX patterns were implemented or modified
  • Brand identity elements were added or changed

Workflow Overview

  1. Analyze Session - Review design-relevant changes this session
  2. Detect Changes - Identify design system implications
  3. Propose Updates - Draft decisions with appropriate IDs
  4. Apply Changes - Update document with user approval

Step 1: Analyze Session

Review the current session for:

Token Changes:

  • New CSS custom properties or design tokens added
  • Color values defined or modified
  • Spacing/sizing values established
  • Typography settings changed

Component Styling:

  • New component variants created
  • Styling patterns established
  • Hover/focus/active states defined
  • Responsive breakpoint adjustments

UX Pattern Implementations:

  • Loading state patterns implemented
  • Error handling UI added
  • Empty state designs created
  • Navigation patterns established
  • Form validation approaches implemented
  • Animation/motion added

Brand Identity:

  • Logo usage implemented
  • Color palette applied
  • Font selections made
  • Voice/tone established in UI copy

Step 2: Detect Change Categories

CategorySignalDesign System Section
Design principleExplicit "we should always..." statement§1.2 Design Principles
AccessibilityARIA labels, contrast fixes, focus states§1.1 Accessibility Requirements
Spacing tokenNew spacing value, padding/margin pattern§1.3 Token Categories (Spacing)
Elevation tokenShadow values, z-index decisions§1.3 Token Categories (Elevation)
Border radiusCorner radius decisions§1.3 Token Categories (Border Radius)
Color tokenNew color value, palette adjustment§2.1 Color System
TypographyFont family, size, weight decisions§2.2 Typography
Brand voiceUI copy patterns, tone decisions§2.4 Brand Voice
Visual atmosphereSurface treatments, textures, spatial character, tonal direction§2.5 Visual Atmosphere
NavigationNav structure, menu patterns§3.1 Navigation
Loading statesSkeleton, spinner, progress patterns§3.2 Loading States
Error handlingError display, validation feedback§3.3 Error Handling
Empty statesNo-data, first-run experiences§3.4 Empty States
Form patternsInput validation, form layout§3.5 Form Patterns
ResponsiveBreakpoint decisions, mobile adaptations§3.6 Responsive Behavior
MotionAnimation timing, transitions, entrance patterns, hover signatures§3.7 Motion & Interaction Character
ComponentNew component styling guidelines§4 Component Guidelines

Step 3: Propose Updates

For each detected change, propose a specific update:

## Proposed Design System Updates

### 1. New Design Principle

**Trigger:** You established that all interactive elements should have visible focus states.

**Proposed addition to §1.2 Design Principles:**

### DP-00X: Accessible Focus States

**Status:** Accepted
**Date:** [today]
**Context:** Implementing keyboard navigation revealed need for consistent focus indicators.

**Decision:** All interactive elements must have visible focus states with 3:1 contrast ratio.

**Rationale:** Supports keyboard-only users and WCAG 2.1 AA compliance.

---

### 2. New Color Token

**Trigger:** You added a new warning color for form validation.

**Proposed addition to §2.1 Color System:**

| Token | Value | Usage |
|-------|-------|-------|
| `--color-warning-light` | #FEF3C7 | Warning background |

**Proposed addition to §5 Decision Log (Brand Decisions):**

### BRD-00X: Warning Color Variant

**Status:** Accepted
**Date:** [today]
**Context:** Form validation needed softer warning background.

**Decision:** Added `--color-warning-light` (#FEF3C7) for warning backgrounds.

**Rationale:** Maintains warning semantic while providing softer background option.

---

### 3. UX Pattern Implementation

**Trigger:** You implemented skeleton loading screens for data tables.

**Proposed addition to §3.2 Loading States:**

**Data Tables:** Use skeleton rows matching table structure. Show 5 skeleton rows by default. Animate with subtle pulse.

**Proposed addition to §5 Decision Log (UX Decisions):**

### UXD-00X: Table Loading Pattern

**Status:** Accepted
**Date:** [today]
**Context:** Data tables needed loading feedback during API calls.

**Decision:** Use skeleton rows (5 default) with pulse animation for table loading states.

**Rationale:** Maintains layout stability and sets user expectations for content shape.

---

Approve these updates? (yes/no/modify)

Step 4: Apply Changes

On approval:

  1. Detect spec format - Check if design system is single file or directory
  2. Read current content:
    • Single file: Read {{specs_dir}}/design_system.md
    • Directory: Aggregate all .md files from {{specs_dir}}/design_system/
  3. Route updates to appropriate files:
    • Single file mode: Edit {{specs_dir}}/design_system.md directly
    • Directory mode: Route each update:
      • Design principles (DP-NNN) → {{specs_dir}}/design_system/01-foundations.md
      • Accessibility → {{specs_dir}}/design_system/01-foundations.md
      • Token changes → {{specs_dir}}/design_system/01-foundations.md
      • Color system (BRD-NNN) → {{specs_dir}}/design_system/02-brand-identity.md
      • Typography → {{specs_dir}}/design_system/02-brand-identity.md
      • Brand voice → {{specs_dir}}/design_system/02-brand-identity.md
      • UX patterns (UXD-NNN) → {{specs_dir}}/design_system/03-ux-patterns.md
      • Component guidelines → {{specs_dir}}/design_system/04-components.md
      • Decision log entries → {{specs_dir}}/design_system/05-decisions.md
  4. Maintain decision ID sequences (find highest DP/BRD/UXD-NNN, increment)
  5. Update "Last updated" timestamp
  6. If {{specs_dir}}/ux-preview.html exists, regenerate it to reflect the updated design system decisions
  7. Update "Status" if appropriate

Important:

  • New decisions get the next available ID in their prefix sequence
  • Never reuse deleted decision IDs (maintain traceability)
  • Preserve existing content - add to sections, don't replace unless correcting errors

Change Detection Heuristics

Strong signals (likely design system change):

  • New CSS custom properties or variables defined
  • Explicit design decisions ("let's use X for all buttons")
  • Accessibility fixes (contrast, ARIA, focus states)
  • New component variants with distinct styling
  • Animation/transition values established
  • Breakpoint or responsive behavior decisions

Weak signals (maybe design system change):

  • One-off styling for specific component
  • Temporary styling during development
  • Framework default overrides
  • Bug fixes to existing styles

Focus on strong signals. For weak signals, ask: "Is this a pattern we want to establish, or a one-time implementation detail?"

Session Summary Format

At session end, provide summary:

## Design System Sync Summary

**Session Date:** [date]

### Changes Detected:
1. [Change 1] → New principle DP-00X
2. [Change 2] → New color token BRD-00X
3. [Change 3] → UX pattern UXD-00X
4. [Change 4] → No design system impact (implementation detail)

### Design System Document:
- [X] Updated with approved changes
- [ ] No changes needed
- [ ] Changes pending user review

### Decision IDs Added/Modified:
- DP-00X (new)
- BRD-00X (new)
- UXD-00X (new)

### Open Items:
- [Any unresolved design questions from session]

Interaction with Other Skills

This skill works in concert with:

  • /groundwork:ux-design - For deliberate, interactive design system creation
  • /groundwork:source-product-specs-from-code - PRD changes may affect design requirements
  • /groundwork:source-architecture-from-code - Architecture changes may affect UX patterns

When multiple sync commands run:

  1. Run /groundwork:source-product-specs-from-code first (product drives design)
  2. Run /groundwork:source-ux-design-from-code second (design supports product)
  3. Run /groundwork:source-architecture-from-code last (architecture implements both)

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.