Skip to content

xinetzone/SpecWeave / .agents/skills/design-library-creator

design-library-creator

Flagged

Create, expand, and refine professional Design Libraries / Design Systems with structured token architecture. ONLY invoke when user EXPLICITLY mentions design-system terminology: 'Design Library', 'Design System', '设计系统', '设计库', 'token system', 'design tokens', '组件库规范', or provides a parsed design-spec bundle (ZIP/Figma export). Also covers creating a new theme / color theme as a design-system deliverable (创建主题/新建暖色主题/深色主题等 — tokens + palette + component styling). Do NOT route here for: '素材库', '全套素材', '素材合集', '物料库', '生成素材', '做一套设计', '做几张图', '设计一套页面', '帮我出图', page/poster/landing-page creation, or any visual-asset generation intent where the user does not demonstrate knowledge of design-system concepts. Those belong to solo-design.

FileKindSize
SKILL.mdskill md19.3 KB
aesthetics/dark-mode.mdmarkdown1.8 KB
aesthetics/index.mdmarkdown33.8 KB
aesthetics/navigation-footer.mdmarkdown2.2 KB
aesthetics/screen-craft.mdmarkdown9.2 KB
aesthetics/self-check.mdmarkdown24.9 KB
examples/templates/component-dispatch-rules.mdmarkdown9.1 KB
examples/templates/figma-token-gen.mdmarkdown50.3 KB
examples/templates/incremental.mdmarkdown5.7 KB
examples/templates/phase-2-analysts.mdmarkdown6.8 KB
examples/templates/phase-2-structured-spec.mdmarkdown8.8 KB
examples/templates/phase-2.5-intent-synthesis.mdmarkdown31.0 KB
examples/templates/phase-3-4-component.mdmarkdown9.0 KB
examples/templates/phase-4-ui-kit.mdmarkdown39.3 KB
examples/templates/phase-5-docs.mdmarkdown12.5 KB
examples/templates/scratch-token-gen.mdmarkdown14.4 KB
examples/templates/specimen-reference.htmlother6.0 KB
file-specs/css-json.mdmarkdown9.5 KB
file-specs/css-tokens.mdmarkdown33.6 KB
file-specs/design-library-output.mdmarkdown10.3 KB
file-specs/design-spec-bundle.mdmarkdown5.9 KB
file-specs/documentation.mdmarkdown12.3 KB
file-specs/preview-pages.mdmarkdown28.0 KB
file-specs/ui-kit.mdmarkdown28.5 KB
operation-policies/agent-orchestration.mdmarkdown20.2 KB
operation-policies/bundle-exploration.mdmarkdown9.0 KB
operation-policies/decision-rules.mdmarkdown10.7 KB
operation-policies/quality-gates.mdmarkdown10.5 KB
operation-policies/user-output-policy.mdmarkdown7.8 KB
scripts/check-design-library-phase.mjsscript85.1 KB
scripts/copy-bundle-assets.mjsscript12.3 KB
scripts/css-to-json.mjsscript53.1 KB
scripts/css-utils.mjsscript748 B
scripts/extract-components-css.mjsscript10.3 KB
scripts/generate-uikit-plan.mjsscript27.5 KB
scripts/jsonl-utils.mjsscript7.3 KB
scripts/validate-design-library-output.mjsscript3.1 KB
scripts/validate-intent.mjsscript7.3 KB
scripts/validate-token-input.mjsscript4.0 KB
scripts/validate-uikit-plan.mjsscript13.6 KB
skill-release-manifest.jsonconfig202 B
workflows/create-from-scratch.mdmarkdown22.5 KB
workflows/create-from-structured-spec.mdmarkdown17.5 KB
workflows/create-library.mdmarkdown53.0 KB
workflows/expand-components.mdmarkdown9.0 KB
workflows/generate-additional-kit.mdmarkdown4.9 KB
workflows/refine-library.mdmarkdown9.7 KB

file-specs/design-spec-bundle.md

View on GitHub
# Input Bundle Structure Reference

## Overview

A **DesignSpecBundle** is a multi-file bundle (Markdown + SVG + binary assets), NOT a single JSON blob. It is extracted from Figma and organized into a directory structure optimized for incremental reading by AI agents.

## Directory Tree

A typical bundle follows this structure:

```
<library-name>.design-spec/
├── METADATA.md                       # Start here: stats, navigation, quick brand context
├── README.md                         # Explorer guide and actual bundle tree
├── tokens/
│   ├── variables-index.md            # Master index of variables, modes, and navigation hints
│   ├── colors-full*.md               # ALL color variables by set/mode (primary color data source)
│   ├── typography*.md                # Font families + type scale + raw styles
│   ├── spacing.md                    # Radius + spacing + float variables
│   ├── shadows*.md                   # Shadow tokens, when present
│   └── grids.md                      # Grid definitions, when present
├── components/
├── assets/
│   ├── icons/index.md                # Icon inventory
│   ├── icons/<prefix-slug>.md        # Icon names by prefix group; may paginate
│   ├── icons/*.svg                    # Reconstructed SVG files, when vector paths exist
│   ├── images*.md                    # Embedded image catalog; binaries optional
│   └── fonts.md                      # Font family list and usage details
├── pages/
│   ├── index.md                      # Page/frame inventory
│   └── primitives*.md                # All primitives with page assignment; may paginate
├── annotations/
│   ├── index.md                      # Annotation summary
│   ├── ui-copies*.md                 # All UI text/copy extracted; may paginate
│   ├── by-component*.md              # Notes grouped by component, when present
│   └── by-page*.md                   # Notes grouped by page, when present
├── context/
│   ├── import-context.md             # Library name, source file, selected frames
│   ├── selected-frames-full.md       # Full selected frame list, when needed
│   ├── data-integrity.md             # Warnings about missing/incomplete data
│   ├── summary.md                    # Design system summary
│   ├── brand-clues.md                # Brand/product inference data
│   ├── component-page-matrix.md      # Page → component reverse mapping
│   ├── design-system-type.md         # Structural analysis
│   ├── variable-aliases.md           # Token hierarchy and alias chains, when present
│   └── variables-raw*.md             # Raw Figma variables, when present
└── generated/                            # Machine-generated structured data (JSONL format)
    ├── bundle-manifest.jsonl              # Aggregated index: stats, shortlist, file manifest (START HERE)
    ├── design-tokens.jsonl                # Core token data: colors, typography, spacing, radius, shadows
    ├── brand-input.jsonl                  # Brand analysis input: UI copies, color signals, font usage
    ├── annotations-summary.jsonl          # Designer notes and UI copy summary
    ├── uikit-planning-input.jsonl         # Component candidates for UIKit planning
    └── components/
        ├── index.jsonl                    # Component category index with variant counts
        └── <slug>.jsonl                   # Per-category evidence/render contract data
```

## JSONL Format Convention

All `generated/*.jsonl` files use a self-describing line-based format:

- **Line 0 (meta)**: `{"_type":"meta", "format":"<name>/v1", "lines":[...]}` — describes file contents with actual data values. Read this FIRST to understand what each line contains without loading the full file.
- **Line 1+**: Each line is a self-contained JSON object with `_type` field identifying its role.
- **Selective reading**: Use meta line descriptions to determine which lines contain relevant data, then read only those lines (by offset/limit).
- **Example**: A component evidence file's meta line lists each variant by name and size, allowing the agent to target specific variants without loading all structural data.

### Reading Strategy for JSONL

1. **Read line 0 (meta)** — understand structure and content overview
2. **Decide what you need** — meta descriptions include counts, names, and key values
3. **Read specific lines** — use offset/limit to read only the lines you need
4. **Each line is independent** — parse one line at a time, no cross-line dependencies

## Pagination Rules

- **Maximum file size**: 16 KB per file
- When content exceeds 16 KB, it is split with a `-part1.md`, `-part2.md` suffix pattern
- Example: `colors-full-part1.md`, `colors-full-part2.md`, `buttons-part1.md`
- The index file for each directory always references all parts

## Reading Strategy

Follow a progressive disclosure approach:

1. **Overview** — Read `METADATA.md` + `README.md` + `context/import-context.md` + `context/data-integrity.md` first
2. **Detail** — Read relevant index files such as `tokens/variables-index.md` and `pages/index.md`
3. **Deep-dive** — Read assigned token/component/page/annotation files only as needed

### Critical Rules

- **NEVER** load the entire bundle into memory at once. Read files incrementally.
- **`selectedFrameNames`** in METADATA are focus hints indicating which frames the user cares about most. They are NOT destructive filters — other data in the bundle is still valid and usable.
- **If `data-integrity.md` reports warnings**, acknowledge the gaps explicitly in your output. Never fabricate data to fill missing information.
- Start with context files to understand the brand before diving into tokens or components.
- Cross-reference `annotations/ui-copies.md` when generating realistic content for previews.
brainstormingobra/superpowersYou MUST use this before any creative work - creating features, building components, adding functionality, modifying behavior, or planning anything new, in software or out of it (a talk, a business, a renovation).Stars: 322kUpdated Claude CodeCodexVerifiedInstall
brand-guidelinesanthropics/skillsApplies Anthropic's official brand colors and typography to any sort of artifact that may benefit from having Anthropic's look-and-feel. Use it when brand colors or style guidelines, visual formatting, or company design standards apply.Stars: 198kUpdated Claude CodeCodexVerifiedInstall
frontend-designanthropics/skillsGuidance for distinctive, intentional visual design when building new UI or reshaping an existing one. Helps with aesthetic direction, typography, and making choices that don't read as templated defaults.Stars: 198kUpdated Claude CodeCodexVerifiedInstall
mcp-builderanthropics/skillsGuide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).Stars: 198kUpdated Claude CodeCodexVerifiedInstall