Create or update a professional Figma design system from a codebase.
This appears to be a prompt-only, open-source skill with no declared secrets, remote endpoints, local code execution, or direct data access in the provided materials. Given the GitHub source and strong community adoption, overall risk is low, though its effective behavior should still be considered alongside the companion `figma-use` skill.
The materials explicitly state that no keys or environment variables are required, and the README does not request any API keys, tokens, or account credentials. For this skill itself, there is no evident credential collection, storage, or misuse path.
The system flags it as prompt-only, and the declared remote endpoint host is none. The documentation only describes design-system workflow orchestration and companion-skill usage, with no factual indication of user data being sent to third-party or unknown endpoints.
This skill itself is instructional content that guides the sequencing and method of `use_figma` calls. It does not describe spawning local processes, running scripts, or directly invoking system capabilities, so there is no standalone code-execution surface in the provided materials.
The materials do not declare any direct ability to read or write local files, databases, or system resources; the content is primarily process knowledge for building Figma design systems. While it mentions analyzing a codebase and inspecting a Figma file, that access capability is not provided by this skill itself.
The source is the open-source GitHub repository `openai/skills` with strong community adoption (about 22k stars), both of which are clear risk-reducing signals. Although the license is unspecified and maintenance status is unknown, those are governance gaps rather than red flags; there is no sign of a closed-source, untrustworthy, or suspiciously injected supply-chain issue.
Copy the install command and let the AI configure it · recommended for beginners
Please install the "figma-generate-library" skill from askskill: 1. Download https://raw.githubusercontent.com/openai/skills/main/skills/.curated/figma-generate-library/SKILL.md 2. Save it as ~/.claude/skills/figma-generate-library/SKILL.md 3. Reload skills and tell me it's ready
Build professional-grade design systems in Figma that match code. This skill orchestrates multi-phase workflows across 20–100+ use_figma calls, enforcing quality patterns from real-world design systems (Material 3, Polaris, Figma UI3, Simple DS).
Prerequisites: The figma-use skill MUST also be loaded for every use_figma call. It provides Plugin API syntax rules (return pattern, page reset, ID return, font loading, color range). This skill provides design system domain knowledge and workflow orchestration.
Always pass skillNames: "figma-generate-library" when calling use_figma as part of this skill. This is a logging parameter — it does not affect execution.
This is NEVER a one-shot task. Building a design system requires 20–100+ use_figma calls across multiple phases, with mandatory user checkpoints between them. Any attempt to create everything in one call WILL produce broken, incomplete, or unrecoverable results. Break every operation to the smallest useful unit, validate, get feedback, proceed.
Every design system build follows this phase order. Skipping or reordering phases causes structural failures that are expensive to undo.
Phase 0: DISCOVERY (always first — no use_figma writes yet)
0a. Analyze codebase → extract tokens, components, naming conventions
0b. Inspect Figma file → pages, variables, components, styles, existing conventions
0c. Search subscribed libraries → use search_design_system for reusable assets
0d. Lock v1 scope → agree on exact token set + component list before any creation
0e. Map code → Figma → resolve conflicts (code and Figma disagree = ask user)
✋ USER CHECKPOINT: present full plan, await explicit approval
Phase 1: FOUNDATIONS (tokens first — always before components)
1a. Create variable collections and modes
1b. Create primitive variables (raw values, 1 mode)
1c. Create semantic variables (aliased to primitives, mode-aware)
1d. Set scopes on ALL variables
1e. Set code syntax on ALL variables
1f. Create effect styles (shadows) and text styles (typography)
→ Exit criteria: every token from the agreed plan exists, all scopes set, all code syntax set
✋ USER CHECKPOINT: show variable summary, await approval
Phase 2: FILE STRUCTURE (before components)
2a. Create page skeleton: Cover → Getting Started → Foundations → --- → Components → --- → Utilities
2b. Create foundations documentation pages (color swatches, type specimens, spacing bars)
→ Exit criteria: all planned pages exist, foundations docs are navigable
✋ USER CHECKPOINT: show page list + screenshot, await approval
Phase 3: COMPONENTS (one at a time — never batch)
For EACH component (in dependency order: atoms before molecules):
3a. Create dedicated page
3b. Build base component with auto-layout + full variable bindings
3c. Create all variant combinations (combineAsVariants + grid layout)
3d. Add component properties (TEXT, BOOLEAN, INSTANCE_SWAP)
3e. Link properties to child nodes
3f. Add page documentation (title, description, usage notes)
3g. Validate: get_metadata (structure) + get_screenshot (visual)
3h. Optional: lightweight Code Connect mapping while context is fresh
→ Exit criteria: variant count correct, all bindings verified, screenshot looks right
✋ USER CHECKPOINT per component: show screenshot, await approval before next component
Phase 4: INTEGRATION + QA (final pass)
4a. Finalize all Code Connect mappings
4b. Accessibility audit (contrast, min touch targets, focus visibility)
4c. Naming audit (no duplicates, no unnamed nodes, consistent casing)
4d. Unresolved bindings audit (no hardcoded fills/strokes remaining)
4e. Final review screenshots of every page
✋ USER CHECKPOINT: complete sign-off
Plugin API basics (from use_figma skill — enforced here too):
…
Review Python, JS/TS, and Go code for security best practices.
Build, review, refactor, and architect modern ASP.NET Core web applications.
Capture full-screen, window, or region screenshots at the operating system level.
Analyze a codebase for threats, abuse paths, and mitigations in Markdown.
Interact with persistent browsers and Electron apps for fast iterative UI debugging.
Prepare agendas, pre-reads, and meeting materials using Notion context and research.
Turn code or page descriptions into full Figma screens using design systems.
Generate custom design system rules for your codebase and Figma-to-code workflow.
Convert Figma designs into production-ready UI code with pixel-perfect fidelity.
Map Figma design components to code components for consistent implementation.
Connect Figma files to extract data, capture screens, and generate code.
Use natural language to create, review, fix, and sync designs in Figma.