ant-design
Decision guide for antd 6.x, Ant Design Pro 5/ProComponents, Ant Design X v2, and the offline `@ant-design/cli`. Use for component selection, theming/tokens, SSR, a11y, performance, routing/access/CRUD, AI/chat UI patterns, local API lookup, debugging, migration, and usage analysis.
What this skill does
# Ant Design
## S - Scope
- Target: `antd@^6` + React 18-19, with `ant-design-pro@^5` / `@ant-design/pro-components` and `@ant-design/x@^2` when needed.
- Tooling: `@ant-design/cli` for offline component metadata, demos, changelogs, migrations, linting, doctor checks, and usage analysis.
- Focus: decision guidance only; no end-user tutorials.
- Source policy: official docs only; no undocumented APIs or internal `.ant-*` coupling.
### Default assumptions
- Language: TypeScript.
- Styling: tokens first, then `classNames`/`styles`; avoid global overrides.
- Provider: one root `ConfigProvider` unless strict isolation is required.
### Mandatory rules
- Before writing or changing antd component code, query the component API first with `antd info <Component> --format json`. Do not rely on memory when the CLI can answer it offline.
- Always use `--format json` with `antd` CLI commands.
- If the project version matters, match it with `--version <x.y.z>` or let the CLI auto-detect from local `node_modules`.
- After changing antd code, run `antd lint <changed-path> --format json`.
- If an `antd` CLI command crashes, returns wrong data, or violates its documented behavior, prepare an `antd bug-cli` preview for user confirmation instead of silently working around it.
- For component questions, first map the component name to the official route slug `{components}` (lowercase kebab-case, e.g. `TreeSelect -> tree-select`, `Button -> button`), then request docs in this order (CN first, EN fallback):
1. `https://ant.design/components/{components}-cn`
2. `https://ant.design/components/{components}`
- Examples: `tree-select-cn -> tree-select`, `button-cn -> button`.
- Use only documented antd/Pro/X APIs.
- Do not invent props/events/component names.
- Do not rely on internal DOM or `.ant-*` selectors.
- Theme priority: global tokens -> component tokens -> alias tokens.
## P - Process
### 1) Classify
- Identify layer: core antd, Pro, or X.
- Confirm version, rendering mode (CSR/SSR/streaming), data scale, and whether `@ant-design/cli` should be the primary lookup path.
### 2) Query authoritative sources
- Prefer local `@ant-design/cli` first for structured lookup:
- `antd info` for props/API
- `antd demo` for a working baseline
- `antd doc` for full docs
- `antd token` / `antd semantic` for theming and styling hooks
- `antd doctor`, `antd lint`, `antd usage`, `antd migrate`, `antd changelog` when debugging or upgrading
- Then request the official component docs (`-cn` first, EN fallback) when narrative docs or cross-checking are needed.
### 3) Decide
- Provider baseline: CSR -> `ConfigProvider`; SSR -> `ConfigProvider` + `StyleProvider`.
- Theming baseline: global tokens -> component tokens -> `classNames`/`styles`.
- Output recommendation + risk + verification points (SSR/a11y/perf), citing CLI findings when used.
## O - Output
- Provide short decision rationale (1-3 sentences).
- Include minimal provider/theming strategy.
- Include concrete SSR/a11y/perf checks.
- For Pro: include route/menu/access and CRUD schema direction.
- For X: include message/tool schema and streaming state direction.
## References
| File | Use when |
| --- | --- |
| `references/antd-cli.md` | You need the exact offline CLI workflow for API lookup, demos, linting, doctor checks, migration, changelog review, usage analysis, or bug reporting. |
## Regression checklist
- [ ] One root `ConfigProvider`; SSR style order/hydration verified.
- [ ] Tokens first; no broad global `.ant-*` overrides.
- [ ] Table has stable `rowKey`; sort/filter/pagination entry is unified.
- [ ] Select remote mode disables local filter when using remote search.
- [ ] Upload controlled/uncontrolled mode is explicit with failure/retry path.
- [ ] Pro route/menu/access remain consistent with backend enforcement.
- [ ] X streaming supports stop/retry and deterministic tool rendering.
- [ ] If `antd` CLI was used, commands ran with `--format json` and any CLI defect was escalated via `antd bug-cli` preview.
Related in Design
contribute
IncludedLocal-only OSS contribution command center. Auto-refreshes the user's in-flight PR and issue state on invoke so conversations start with full context — no need to brief Claude on what's in flight. Helps the user find issues to contribute to on GitHub, builds per-repo dossiers of what each upstream expects (CLA, DCO, branch convention, AI policy, draft-first, review bots, issue templates), runs deterministic gates before any external action so AI-assisted contributions don't reach maintainers as slop. State is markdown-only: candidate files at ~/.contribute-system/candidates/, repo dossiers at ~/.contribute-system/research/, append-only event log at ~/.contribute-system/log.jsonl. No database, no cloud calls. Use when the user asks about their PRs / issues / contributions, wants to find new work to take on, claim an issue, build/refresh a repo's dossier, or draft a Design Issue or PR. Trigger with "/contribute", "what's my PR status", "find a contribution", "claim issue X", "draft a Design Issue for Y", "refresh dossier for Z".
architectural-analysis
IncludedUser-triggered deep architectural analysis of a codebase or scoped subtree across eight modes — information architecture, data flow, integration points, UI surfaces, interaction patterns, data model, control flow, and failure modes. This skill should be used when the user asks to "diagram this codebase," "map the architecture," "show the data flow," "give me an ERD," "trace control flow," "find the integration points," "verify the layout pattern," "audit the UX architecture," or any similar request whose primary deliverable is mermaid diagrams plus cited reports under docs/architecture/. Dispatches haiku/sonnet sub-agents in parallel for per-mode exploration, then verifies every citation mechanically before any node lands in a diagram. Not for one-off prose explanations of code (use code-explanation) or for high-level system design from scratch (use system-design).
mcp
IncludedModel Context Protocol (MCP) server development and tool management. Languages: Python, TypeScript. Capabilities: build MCP servers, integrate external APIs, discover/execute MCP tools, manage multi-server configs, design agent-centric tools. Actions: create, build, integrate, discover, execute, configure MCP servers/tools. Keywords: MCP, Model Context Protocol, MCP server, MCP tool, stdio transport, SSE transport, tool discovery, resource provider, prompt template, external API integration, Gemini CLI MCP, Claude MCP, agent tools, tool execution, server config. Use when: building MCP servers, integrating external APIs as MCP tools, discovering available MCP tools, executing MCP capabilities, configuring multi-server setups, designing tools for AI agents.
react-native-skia
IncludedDesign, build, debug, and optimise high-polish animated graphics in React Native or Expo using @shopify/react-native-skia, Reanimated, and Gesture Handler. Use when the user wants canvas-driven UI, shaders, paths, rich text, image filters, sprite fields, Skottie, video frames, snapshots, web CanvasKit setup, or performance tuning for custom motion-heavy elements such as loaders, hero art, cards, charts, progress indicators, particle systems, or gesture-driven surfaces. Also use when the user asks for fluid, glow, glass, blob, parallax, 60fps/120fps, or GPU-friendly animated effects in React Native, even if they do not explicitly say "Skia". Do not use for ordinary form/layout work with standard views.
plaid
IncludedProduct Led AI Development — guides founders from idea to launched product. Six capabilities: Idea (discover a product idea), Validate (pressure-test the idea against fatal flaws, problem reality, competition, and 2-week MVP feasibility), Plan (vision intake + document generation), Design (translate image references into a design.md spec), Launch (go-to-market strategy), and Build (roadmap execution). Use when someone says "PLAID", "plaid idea", "help me find an idea", "product idea", "idea from my business", "idea from my expertise", "plaid validate", "validate my idea", "pressure-test", "is this idea good", "find fatal flaws", "validate the problem", "plan a product", "define my vision", "generate a PRD", "product strategy", "plaid design", "design from image", "translate image to design", "create design.md", "extract design tokens", "plaid launch", "go-to-market", "launch plan", "GTM strategy", "launch playbook", "plaid build", "build the app", "start building", or "execute the roadmap".
nextjs-framer-motion-animations
IncludedAdds production-safe Motion for React or Framer Motion animations to Next.js apps, including reveal, hover and tap micro-interactions, whileInView, stagger, AnimatePresence, layout and layoutId transitions, reorder, scroll-linked UI, and lightweight route-content transitions. Use when the user asks to add, refactor, or debug Motion or Framer Motion in App Router or Pages Router codebases, especially around server/client boundaries, reduced motion, LazyMotion, bundle size, hydration, or route transitions. Avoid for GSAP-style timelines, WebGL or 3D scenes, heavy scroll storytelling, or CSS-only effects unless Motion is explicitly requested.