ultracite
Ultracite multi-provider linting/formatting (Biome, ESLint, Oxlint). Use for v6/v7 setup, provider selection, Git hooks, MCP integration, AI hooks, migrations, or encountering configuration, type-aware linting, monorepo errors.
What this skill does
# Ultracite Skill
**Fast, zero-config linting and formatting for modern JavaScript/TypeScript projects**
## Overview
Ultracite is a unified linting and formatting solution that supports multiple providers: **Biome** (default, Rust-based), **ESLint+Prettier+Stylelint**, and **Oxlint+Oxfmt**. It provides framework-specific presets and zero-configuration defaults, replacing traditional ESLint+Prettier setups with a faster, simpler alternative. Ultracite operates invisibly in the background, automatically formatting code and applying fixes on every save.
**Version 7 Changes**: Multi-provider architecture, preset path migration, MCP server support, AI hooks
**Version 6 Changes**: Framework-specific presets introduced (React, Next.js, Vue, Svelte, etc.)
### Core Goals
1. **Lightning-Fast Performance**: Leverages Biome's Rust implementation for instant linting/formatting
2. **Zero-Config Design**: Ships with 200+ sensible defaults optimized for modern TypeScript development
3. **Simplicity & Invisibility**: Operates with minimal user interaction
4. **Type Safety**: Enforces TypeScript strict mode and comprehensive null/undefined handling
5. **Tool Compatibility**: Works alongside other development tools without conflicts
### Key Benefits vs Alternatives
**vs ESLint + Prettier:**
- 10-100x faster performance (Rust vs JavaScript)
- Single tool instead of two
- Zero configuration needed
- Auto-fixes on save by default
- Built-in TypeScript strict mode
**vs Biome alone:**
- 200+ preconfigured rules
- Framework-specific presets (React, Next.js, Vue, Svelte)
- AI editor integration (Cursor, Claude Code, Copilot)
- Git hook integrations
- Migration tooling
## When to Use This Skill
### ✅ Ideal Projects
Use Ultracite when:
- Starting a new JavaScript/TypeScript project
- Building with React, Next.js, Vue, Svelte, or other modern frameworks
- Working in monorepos (Turborepo, Nx, Lerna)
- Teams want consistent formatting without bikeshedding
- Performance is critical (large codebases, CI/CD optimization)
- Migrating from ESLint + Prettier to a faster solution
- Using AI coding assistants (Cursor, Claude Code, Windsurf)
- TypeScript projects requiring strict type safety
- Projects with accessibility requirements (ARIA, semantic HTML)
### ⚠️ Consider Alternatives When
**Limited framework support:**
- Need Angular/Ember-specific rules (Biome support is basic)
- Require advanced CSS linting (Stylelint still recommended)
**Specialized requirements:**
- Need specific ESLint plugins not replicated in Biome
- Require property ordering in CSS (Stylelint feature)
- Team has extensive custom ESLint configurations
**Legacy projects:**
- Large codebases with custom ESLint rules (migration effort required)
- Projects with extensive Prettier customization
**For detailed limitations and workarounds, see**: `references/limitations-and-workarounds.md`
## Interactive Components
This skill provides interactive commands and autonomous agents for streamlined workflows:
### Commands
- `/ultracite:doctor` - Validate project setup, check for v6→v7 preset paths, detect conflicts
- `/ultracite:migrate` - Interactive migration wizard (ESLint/Prettier → Ultracite, v6→v7 upgrade)
### Agents
- `config-validator` - Analyze biome.jsonc for syntax, preset paths, rule conflicts, performance
- `migration-assistant` - Guide ESLint/Prettier migrations with rule mapping and gap analysis
**See README.md for complete interactive features documentation.**
## Choosing a Provider
Ultracite v7 supports three linting providers. Choose based on your needs:
### 🚀 Biome (Default) - **Recommended for most projects**
- **Speed**: Fastest (10-100x faster than ESLint)
- **Setup**: Zero-config with 200+ preset rules
- **Best for**: New projects, TypeScript-first development, performance-critical builds
- **Limitations**: Fewer rules than ESLint, basic CSS/SCSS support
### 🔧 ESLint + Prettier + Stylelint - **Recommended for maximum compatibility**
- **Speed**: Slower but mature ecosystem
- **Setup**: Requires more configuration
- **Best for**: Projects with existing ESLint plugins, advanced CSS/SCSS linting needs
- **Limitations**: JavaScript-based (slower), requires multiple tools
### ⚡ Oxlint + Oxfmt - **Recommended for maximum speed**
- **Speed**: Fastest linting (even faster than Biome for linting only)
- **Setup**: Type-aware linting with TypeScript integration
- **Best for**: Large TypeScript codebases, type-safety-critical projects
- **Limitations**: Newer ecosystem, fewer rules than ESLint
**Provider selection** during init:
```bash
bun x ultracite init --linter biome # Default
bun x ultracite init --linter eslint # ESLint + Prettier + Stylelint
bun x ultracite init --linter oxlint # Oxlint + Oxfmt
```
**Load provider-specific documentation**:
- Biome: `references/provider-biome.md`
- ESLint: `references/provider-eslint.md`
- Oxlint: `references/provider-oxlint.md`
## Version Migration Guide
### Upgrading from v6 to v7
**Breaking Change**: Preset paths have changed in v7.
**v6 paths (old)**:
```jsonc
{
"extends": ["ultracite/core", "ultracite/react"]
}
```
**v7 paths (new)**:
```jsonc
{
"extends": ["ultracite/biome/core", "ultracite/biome/react"]
}
```
**Migration steps**:
1. Update `ultracite` package: `bun update ultracite`
2. Update preset paths in `biome.jsonc` (add `/biome/` segment)
3. Run `npx ultracite doctor` to validate configuration
4. Test linting: `npx ultracite check .`
**New v7 features**:
- Multi-provider support (Biome, ESLint, Oxlint)
- MCP server integration for AI assistants
- AI hooks (auto-format after AI edits)
- Type-aware linting (Oxlint)
- `ultracite doctor` diagnostics command
**Load full v7 migration guide**: `references/v7-migration.md`
### Upgrading from v5 to v6
**Key Change**: Framework-specific presets introduced.
**v5 approach (old)**:
```jsonc
{
"extends": ["ultracite/core"]
}
```
**v6 approach (new)**:
```jsonc
{
"extends": ["ultracite/core", "ultracite/react"] // Framework preset
}
```
**Load full v6 migration guide**: `references/v6-migration.md`
### Project Suitability Assessment
When this skill is invoked, scan the project and assess:
1. **Check existing tooling:**
```bash
# Check for ESLint
ls -la .eslintrc* eslint.config.* package.json | grep eslint
# Check for Prettier
ls -la .prettierrc* prettier.config.* package.json | grep prettier
# Check for Biome
ls -la biome.json* package.json | grep biome
```
2. **Identify framework:**
- Check `package.json` for `react`, `next`, `vue`, `svelte`, etc.
- Recommend appropriate preset
3. **Assess project size:**
- Large projects (1000+ files) benefit most from Rust performance
- Small projects may not notice speed difference
4. **Check TypeScript config:**
- If `tsconfig.json` exists, note that Ultracite requires `strictNullChecks: true`
- Warn if disabled (will generate many warnings)
5. **Recommend or warn:**
```
✅ RECOMMENDED: This TypeScript + React project is ideal for Ultracite
- 500+ files will benefit from Rust performance
- React preset available
- Can replace existing ESLint + Prettier setup
⚠️ CONSIDER: This project uses advanced ESLint plugins
- Custom rule: eslint-plugin-custom-security
- May need to retain ESLint for these specific rules
- Could use Ultracite for formatting only
```
## Installation & Setup
### Prerequisites
- Node.js v14.18+ (v18+ recommended)
- Package manager: Bun (preferred), npm, pnpm, or yarn
- `package.json` file in project root
### Quick Start (Interactive)
```bash
# Using Bun (preferred for speed)
bun x ultracite init
# With provider selection (v7+)
bun x ultracite init --linter biome # Default, fastest
bun x ultracite init --linter eslint # ESLint + Prettier + Stylelint
bun x ultracite init --linter oxlint # Oxlint + Oxfmt (type-aware)
# Using npm
npx ultracite init
# Using pnpm
pnpm dlx ultracite init
# Using yarn
yarn dlx ultracite init
```Related in AI Agents
skill-development
IncludedComprehensive meta-skill for creating, managing, validating, auditing, and distributing Claude Code skills and slash commands (unified in v2.1.3+). Provides skill templates, creation workflows, validation patterns, audit checklists, naming conventions, YAML frontmatter guidance, progressive disclosure examples, and best practices lookup. Use when creating new skills, validating existing skills, auditing skill quality, understanding skill architecture, needing skill templates, learning about YAML frontmatter requirements, progressive disclosure patterns, tool restrictions (allowed-tools), skill composition, skill naming conventions, troubleshooting skill activation issues, creating custom slash commands, configuring command frontmatter, using command arguments ($ARGUMENTS, $1, $2), bash execution in commands, file references in commands, command namespacing, plugin commands, MCP slash commands, Skill tool configuration, or deciding between skills vs slash commands. Delegates to docs-management skill for official documentation.
reprompter
IncludedTransform messy prompts into well-structured, effective prompts — single or multi-agent. Use when: "reprompt", "reprompt this", "clean up this prompt", "structure my prompt", rough text needing XML tags and best practices, "reprompter teams", "repromptception", "run with quality", "smart run", "smart agents", multi-agent tasks, audits, parallel work, anything going to agent teams. Don't use when: simple Q&A, pure chat, immediate execution-only tasks. See "Don't Use When" section for details. Outputs: Structured XML/Markdown prompt, quality score (before/after), optional team brief + per-agent sub-prompts, agent team output files. Success criteria: Single mode quality score ≥ 7/10; Repromptception per-agent prompt quality score 8+/10; all required sections present, actionable and specific.
adaptive-compaction
IncludedAdaptive add-on policy and recovery layer that decides WHEN to compact, prune, snapshot, or fork -- replacing fixed-percent auto-compaction across Claude Code, Codex, and MCP-capable hosts. Trigger on auto-compact timing or damage: "when should I compact", "is it safe to compact now or start a fresh session", "auto-compact fires too early/mid-task", "switching to an unrelated task but the window still has space", "context rot", "answers get worse the longer the session runs", "the agent forgot the plan or my decisions after it summarized", "add a layer on top that manages context without changing the agent", raising autoCompactWindow to give the policy room, or installing/tuning a cross-tool compaction policy or PreCompact hook -- even when "compaction" is never said but the problem is context-window pressure or post-summarization memory loss. Do NOT use to summarize a conversation, build RAG, write a summarization prompt (decides WHEN not HOW), or answer max-context-length trivia.
agent-skill-creator
IncludedCreate cross-platform agent skills from workflow descriptions. Activates when users ask to create an agent, automate a repetitive workflow, create a custom skill, or need advanced agent creation. Triggers on phrases like create agent for, automate workflow, create skill for, every day I have to, daily I need to, turn process into agent, need to automate, create a cross-platform skill, validate this skill, export this skill, migrate this skill. Supports single skills, multi-agent suites, transcript processing, template-based creation, interactive configuration, cross-platform export, and spec validation.
llm-wiki
IncludedUse when building or maintaining a persistent personal knowledge base (second brain) in Obsidian where an LLM incrementally ingests sources, updates entity/concept pages, maintains cross-references, and keeps a synthesis current. Triggers include "second brain", "Obsidian wiki", "personal knowledge management", "ingest this paper/article/book", "build a research wiki", "compound knowledge", "Memex", or whenever the user wants knowledge to accumulate across sessions instead of being re-derived by RAG on every query.
skill-master
IncludedAgent Skills authoring, evaluation, and optimization. Create, edit, validate, benchmark, and improve skills following the agentskills.io specification. Use when designing SKILL.md files, structuring skill folders (references, scripts, assets), ingesting external documentation into skills, running trigger evals, benchmarking skill quality, optimizing descriptions, or performing blind A/B comparisons. Keywords: agentskills.io, SKILL.md, skill authoring, eval, benchmark, trigger optimization.