laravel-boost
Use when setting up or configuring Laravel Boost for AI-assisted development — package installation, MCP server configuration, guideline customization, skill authoring, documentation API integration. Trigger conditions: install Laravel Boost, configure MCP for IDE, create custom AI guidelines, write project-specific skills, verify MCP tool connectivity, update Boost after dependency changes, extend Boost for custom agents.
What this skill does
# Laravel Boost
## Overview
Laravel Boost is an official Laravel package that accelerates AI-assisted development by providing composable guidelines, on-demand agent skills, an MCP (Model Context Protocol) server, and a documentation API with semantic search across 17,000+ Laravel-specific knowledge pieces. It bridges AI coding tools and the Laravel ecosystem, ensuring that AI agents generate high-quality, convention-compliant Laravel code.
Apply this skill when setting up, configuring, or extending Laravel Boost in a project, or when integrating AI agents with a Laravel application.
## Multi-Phase Process
### Phase 1: Assessment
1. Confirm Laravel version compatibility (10.x, 11.x, 12.x)
2. Identify the AI IDE or agent in use (Cursor, Claude Code, Codex, Gemini CLI, GitHub Copilot, Junie)
3. Check if an MCP configuration already exists (`.mcp.json`)
4. Review existing guideline and skill customizations in `.ai/`
> **STOP — Do NOT install Boost without confirming Laravel version compatibility and target IDE.**
### Phase 2: Installation and Configuration
1. Install the package and run the installer
2. Configure MCP server for the target IDE
3. Set up automatic updates via Composer hooks
4. Verify MCP tools are accessible from the AI agent
> **STOP — Do NOT proceed until MCP server connectivity is verified with at least one tool call.**
### Phase 3: Customization
1. Add project-specific guidelines in `.ai/guidelines/`
2. Create domain-specific skills in `.ai/skills/`
3. Override built-in guidelines or skills where project conventions differ
4. Register custom agents if extending to unsupported IDEs
> **STOP — Do NOT override built-in guidelines unless project conventions genuinely differ from Laravel defaults.**
### Phase 4: Validation
1. Confirm MCP server responds to tool calls (Application Info, Database Schema, Search Docs)
2. Verify guidelines load in the AI agent's context window
3. Test skill activation for domain-relevant tasks
4. Check that `boost:update` keeps resources current after dependency changes
## IDE Setup Decision Table
| IDE / Agent | Setup Method | Configuration File |
|---|---|---|
| **Claude Code** | CLI command | `.mcp.json` (auto-generated) |
| **Codex** | CLI command | `.mcp.json` |
| **Gemini CLI** | CLI command | `.mcp.json` |
| **Cursor** | Command Palette GUI | `.cursor/mcp.json` |
| **GitHub Copilot** | Command Palette GUI | `.mcp.json` |
| **Junie** | Settings GUI | `.mcp.json` |
| **Custom / Unsupported** | Custom agent class | Manual MCP config |
## Installation
```bash
# Install as a development dependency
composer require laravel/boost --dev
# Run the installer — generates .mcp.json, guideline files, and boost.json
php artisan boost:install
```
The installer generates:
- `.mcp.json` — MCP server configuration for IDE integration
- Guideline files (`CLAUDE.md`, `AGENTS.md`, etc.) tailored to detected packages
- `boost.json` — Boost configuration file
### IDE-Specific MCP Setup
| IDE / Agent | Setup Command or Action |
|---|---|
| **Claude Code** | `claude mcp add -s local -t stdio laravel-boost php artisan boost:mcp` |
| **Codex** | `codex mcp add laravel-boost -- php "artisan" "boost:mcp"` |
| **Gemini CLI** | `gemini mcp add -s project -t stdio laravel-boost php artisan boost:mcp` |
| **Cursor** | Command Palette -> "Open MCP Settings" -> toggle on `laravel-boost` |
| **GitHub Copilot** | Command Palette -> "MCP: List Servers" -> select `laravel-boost` -> "Start server" |
| **Junie** | Shift-Shift -> "MCP Settings" -> check `laravel-boost` -> Apply |
### Manual MCP Configuration
```json
{
"mcpServers": {
"laravel-boost": {
"command": "php",
"args": ["artisan", "boost:mcp"]
}
}
}
```
### Keeping Resources Updated
```bash
# Manual update after dependency changes
php artisan boost:update
# Automatic updates — add to composer.json scripts
{
"scripts": {
"post-update-cmd": [
"@php artisan boost:update --ansi"
]
}
}
```
## MCP Server Tools
Laravel Boost exposes the following tools through its MCP server, giving AI agents direct access to application context:
| Tool | Purpose | Typical Use |
|---|---|---|
| **Application Info** | Read PHP and Laravel versions, database engine, ecosystem packages, Eloquent models | Context discovery at session start |
| **Database Schema** | Read full database schema | Migration planning, model generation |
| **Database Query** | Execute queries against the database | Data inspection, debugging |
| **Database Connections** | Inspect available database connections | Multi-database configuration |
| **Search Docs** | Semantic search across Laravel documentation API | Finding best practices, API references |
| **Last Error** | Read the most recent application log error | Debugging workflow |
| **Read Log Entries** | Read last N log entries | Monitoring, debugging |
| **Browser Logs** | Read logs and errors from browser | Frontend debugging |
| **Get Absolute URL** | Convert relative path URIs to absolute URLs | Link generation |
## AI Guidelines
Guidelines are composable instruction files loaded upfront into the AI agent's context, providing broad conventions and best practices.
### Available Built-in Guidelines
| Package | Versions Supported |
|---|---|
| Laravel Framework | Core, 10.x, 11.x, 12.x |
| Livewire | Core, 2.x, 3.x, 4.x |
| Flux UI | Core, Free, Pro |
| Inertia | React, Vue, Svelte (1.x-3.x) |
| Tailwind CSS | Core, 3.x, 4.x |
| Pest | Core, 3.x, 4.x |
| PHPUnit, Pint, Sail, Pennant, Volt, Wayfinder, Folio, Herd, MCP | Core |
### Custom Guidelines
Create `.blade.php` or `.md` files in `.ai/guidelines/`:
```
.ai/guidelines/team-conventions.md
.ai/guidelines/billing/stripe-patterns.blade.php
```
Override a built-in guideline by matching its path:
```
.ai/guidelines/inertia-react/2/forms.blade.php
```
### Third-Party Package Guidelines
Package authors can ship guidelines at:
```
resources/boost/guidelines/core.blade.php
```
## Agent Skills
Skills are on-demand knowledge modules activated only when relevant, reducing context window bloat.
### Available Built-in Skills
| Skill | Domain |
|---|---|
| `livewire-development` | Livewire components and reactivity |
| `inertia-react-development` | Inertia.js with React |
| `inertia-vue-development` | Inertia.js with Vue |
| `inertia-svelte-development` | Inertia.js with Svelte |
| `pest-testing` | Pest test patterns |
| `fluxui-development` | Flux UI components |
| `folio-routing` | Folio page-based routing |
| `tailwindcss-development` | Tailwind CSS utility classes |
| `volt-development` | Volt single-file Livewire components |
| `pennant-development` | Pennant feature flags |
| `wayfinder-development` | Wayfinder type-safe routing |
| `mcp-development` | MCP server/tool development |
### Custom Skills
Create `.ai/skills/{skill-name}/SKILL.md`:
```markdown
---
name: invoice-management
description: Build and work with invoice features including PDF generation and payment tracking.
---
# Invoice Management
## When to use this skill
Use when working with the invoicing module...
```
### Guidelines vs Skills Decision Table
| Question | Guidelines | Skills |
|---|---|---|
| When is it loaded? | Always — upfront context | On-demand — when the task matches |
| How broad is the scope? | Foundational conventions | Focused implementation patterns |
| Impact on context window? | Constant (always present) | Minimal (loaded only when needed) |
| Best for? | Coding standards, package versions | Step-by-step implementation guides |
| Content changes often? | Rarely (stable conventions) | Frequently (evolving patterns) |
| Team-wide applicability? | High (everyone follows) | Varies (domain-specific) |
## Documentation API
Boost provides semantic search across 17,000+ documentation pieces covering:
| Package | Versions |
|---|---|
| Laravel Framework | 10.x, 11.x, 12.x |
| Filament | 2.x, 3.x, 4.x, 5.x |
| Flux UI Related in Backend & APIs
jfrog
IncludedInteract with the JFrog Platform via the JFrog CLI and REST/GraphQL APIs. Use this skill when the user wants to manage Artifactory repositories, upload or download artifacts, manage builds, configure permissions, manage users and groups, work with access tokens, configure JFrog CLI servers, search artifacts, manage properties, set up replication, manage JFrog Projects, run security audits or scans, look up CVE details, query exposures scan results from JFrog Advanced Security, manage release bundles and lifecycle operations, aggregate or export platform data, or perform any JFrog Platform administration task. Also use when the user mentions jf, jfrog, artifactory, xray, distribution, evidence, apptrust, onemodel, graphql, workers, mission control, curation, advanced security, exposures, or any JFrog product name.
cupynumeric-migration-readiness
IncludedPre-migration readiness assessor for porting NumPy to cuPyNumeric. Use BEFORE substantial porting work begins when the user asks whether code will scale on GPU, whether they should migrate to cuPyNumeric, which NumPy patterns transfer cleanly, what must be refactored before porting, or mentions pre-port assessment, scaling analysis, or refactor planning. Inspect the user's source code, look up NumPy usage, cross-reference the cuPyNumeric API support manifest, and distinguish distributed-scaling-friendly patterns from blockers such as unsupported APIs, scalar synchronization, host round-trips, Python/object-heavy control flow, shape/data-dependent branching, and in-place mutation hazards. Produce a verdict of READY, LIGHT REFACTOR, SIGNIFICANT REFACTOR, or NOT RECOMMENDED, with concrete refactor pointers.
alibabacloud-data-agent-skill
IncludedInvoke Alibaba Cloud Apsara Data Agent for Analytics via CLI to perform natural language-driven data analysis on enterprise databases. Data Agent for Analytics is an intelligent data analysis agent developed by Alibaba Cloud Database team for enterprise users. It automatically completes requirement analysis, data understanding, analysis insights, and report generation based on natural language descriptions. This tool supports: discovering data resources (instances/databases/tables) managed in DMS, initiating query or deep analysis sessions, real-time progress tracking, and retrieving analysis conclusions and generated reports. Use this Skill when users need to query databases, analyze data trends, generate data reports, ask questions in natural language, or mention "Data Agent", "data analysis", "database query", "SQL analysis", "data insights".
token-optimizer
IncludedReduce OpenClaw token usage and API costs through smart model routing, heartbeat optimization, budget tracking, and native 2026.2.15 features (session pruning, bootstrap size limits, cache TTL alignment). Use when token costs are high, API rate limits are being hit, or hosting multiple agents at scale. The 4 executable scripts (context_optimizer, model_router, heartbeat_optimizer, token_tracker) are local-only — no network requests, no subprocess calls, no system modifications. Reference files (PROVIDERS.md, config-patches.json) document optional multi-provider strategies that require external API keys and network access if you choose to use them. See SECURITY.md for full breakdown.
resend-cli
IncludedUse this skill when the task is specifically about operating Resend from an AI agent, terminal session, or CI job via the official resend CLI: installing/authenticating the CLI, sending/listing/updating/cancelling emails, batch sends, domains and DNS, webhooks and local listeners, inbound receiving, contacts, topics, segments, broadcasts, templates, API keys, profiles, or debugging Resend CLI/API failures. Trigger on mentions of Resend CLI, `resend`, `resend doctor`, `resend emails send`, `resend domains`, `resend webhooks listen`, `resend emails receiving`, or agent-friendly terminal automation.
alibabacloud-odps-maxframe-coding
IncludedUse this skill for MaxFrame SDK development and documentation navigation on Alibaba Cloud MaxCompute (ODPS). Helps answer MaxFrame API, concept, official example, and supported pandas API questions; create data processing programs; read/write MaxCompute tables; debug jobs (remote or local); and build custom DPE runtime images. Trigger when users mention MaxFrame, MaxCompute with MaxFrame, ODPS table processing, DPE runtime, MaxFrame docs/examples, DataFrame/Tensor operations, or GPU runtime setup. Works for both English and Chinese queries about Alibaba Cloud data processing with MaxFrame.