laravel-brainstorming
Use when creating or developing Laravel features, before writing code or implementation plans - refines rough ideas into fully-formed Laravel designs through collaborative questioning, alternative exploration, and incremental validation.
- Installs
- 95
- Last 24h
- —
- Trending rank
- —
- Security
- Not audited
Install
Works with every agent the skills CLI supports.
npx skills add https://github.com/iserter/laravel-claude-agents --skill laravel-brainstorming- 01
Install
Run the command in your project. The CLI asks which agents to install for.
- 02
Describe the task
Ask your agent for something this skill covers. It loads laravel-brainstorming automatically when relevant.
- 03
Review the result
The agent follows the SKILL.md steps, scripts and references bundled with the skill.
SKILL.md
The instructions your agent reads when the skill is triggered.
Brainstorming Laravel Ideas Into Designs
Overview
Help turn Laravel feature ideas into fully formed designs and specs through natural collaborative dialogue, focusing on Laravel best practices and ecosystem patterns.
Start by understanding the current Laravel project context, then ask questions one at a time to refine the idea. Once you understand what you're building, present the design in small sections (200-300 words), checking after each section whether it looks right so far.
The Process
Understanding the idea:
- Check out the current Laravel project state first (routes, models, migrations, recent commits)
- Ask questions one at a time to refine the idea
- Prefer multiple choice questions when possible, but open-ended is fine too
- Only one question per message - if a topic needs more exploration, break it into multiple questions
- Focus on understanding: purpose, Laravel patterns, constraints, success criteria
Example Questions:
- "Should this be a queue job or run synchronously?"
- "Which authentication approach: Sanctum, Passport, or custom?"
- "Will this need real-time updates via broadcasting?"
- "Should we use Eloquent events or explicit service calls?"
Exploring approaches:
- Propose 2-3 different Laravel approaches with trade-offs
- Present options conversationally with your recommendation and reasoning
- Lead with your recommended option and explain why
Example:
For the notification system, I see three approaches:
1. Laravel Notifications with database channel (recommended)
- Built-in, follows Laravel conventions
- Easy to add email/Slack later
- Simple to mark as read
Trade-off: Less flexible for complex notification logic
2. Custom Event/Listener system
- Maximum flexibility
- Can add complex rules
Trade-off: More code to maintain
3. Third-party package (like Laravel Echo)
- Real-time out of the box
Trade-off: External dependency, overkill if not needed
I'd recommend #1 for most cases - start simple, Laravel's notification system is excellent and you can always extend it later if needed.
Which approach feels right for your use case?
Presenting the design:
- Once you believe you understand what you're building, present the design
- Break it into sections of 200-300 words
- Ask after each section whether it looks right so far
- Cover: database schema, models & relationships, routes & controllers, services/actions, queues/events, API resources, validation, testing
- Be ready to go back and clarify if something doesn't make sense
Laravel-Specific Design Sections
1. Database Schema
First, let's look at the database design:
We'll need three tables:
1. `posts` - title, slug, content, status, published_at
2. `tags` - name, slug
3. `post_tag` - pivot table for many-to-many
The posts table will have a foreign key to users, indexed on status and published_at for common queries. We'll use an enum for status (draft, published, archived) to keep it clean.
Does this schema structure make sense for what we're building?
2. Models & Relationships
For the models, we'll have:
Post model with:
- belongsTo relationship to User
- belongsToMany relationship to Tag
- Scopes: published(), draft(), recent()
- Casts: published_at as datetime, metadata as array
- Factory for testing
Tag model with:
- belongsToMany relationship to Post
- Slug auto-generation on save
Should we add soft deletes to posts, or will hard deletes work?
3. API Design
For the API endpoints, following RESTful conventions:
GET /api/posts - List posts (paginated)
POST /api/posts - Create post
GET /api/posts/{post} - Show post
PUT /api/posts/{post} - Update post
DELETE /api/posts/{post} - Delete post
Authentication via Sanctum, rate limited to 60 requests/minute.
API resources will transform the output, hiding sensitive data.
Does this API structure cover your needs?
4. Business Logic
The posting workflow:
When a post is published:
1. PostService validates the post is ready (has title, content)
2. Sets published_at timestamp
3. Dispatches NotifySubscribers job to queue
4. Fires PostPublished event for other listeners
5. Clears related caches
We'll use a service class to keep controllers thin, and queues for email notifications so publishing is fast.
Is this flow what you had in mind?
After the Design
Documentation:
- Write the validated design to
docs/designs/YYYY-MM-DD-<feature>-design.md - Include: feature overview, database schema, API endpoints, business logic flow
- Commit the design document to git
Implementation (if continuing):
- Ask: "Ready to set up for implementation?"
- Create implementation checklist
- Consider using test-driven development approach
Key Principles
- One question at a time - Don't overwhelm with multiple questions
- Multiple choice preferred - Easier to answer than open-ended when possible
- YAGNI ruthlessly - Remove unnecessary features, keep it simple
- Laravel conventions first - Use built-in Laravel features before custom solutions
- Explore alternatives - Always propose 2-3 approaches before settling
- Incremental validation - Present design in sections, validate each
- Be flexible - Go back and clarify when something doesn't make sense
Laravel-Specific Considerations
When brainstorming Laravel features, consider:
Architecture:
- Will this be a monolith or need microservices?
- What design patterns fit best (repository, service layer, actions)?
- How will this scale?
Database:
- What relationships are needed?
- What indexes for performance?
- Should we use polymorphic relationships?
Performance:
- Should this use queues?
- What caching strategy?
- Eager loading requirements?
Testing:
- What factories are needed?
- Feature tests vs unit tests?
- How to test jobs/events?
Security:
- Authorization via policies or gates?
- What validation rules?
- Rate limiting needs?
Example Brainstorming Session
Claude: I see you want to add a comment system. Let me understand the requirements.
First question: Should comments be nested (replies to replies) or just one level deep (replies to posts only)?
User: Just one level - comments on posts.
Claude: Got it. And for moderation, which approach:
A) All comments published immediately
B) Comments from new users require approval
C) All comments require approval
User: B - new users need approval.
Claude: Perfect. For notifications when someone comments:
A) Real-time via Laravel Echo and WebSockets
B) Email only
C) In-app notifications (database)
User: In-app notifications.
Claude: Excellent. Let me present the design...
[Design sections follow]
Common Laravel Brainstorming Topics
- Authentication flow (SPA vs traditional)
- API design (REST vs GraphQL)
- Real-time features (Pusher vs Socket.io vs Reverb)
- File upload strategy (local vs S3)
- Multi-tenancy approach
- Payment integration (Stripe, Paddle, Cashier)
- Search implementation (Scout, Elasticsearch)
- Admin panel (Nova, Filament, custom)
Remember
The goal is to arrive at a clear, actionable Laravel design that:
- Follows Laravel conventions
- Uses appropriate Laravel ecosystem packages
- Is testable and maintainable
- Solves the actual problem without over-engineering
- Can be implemented incrementally
Ask questions until you understand, then design in small validatable chunks.
FAQ
What does the laravel-brainstorming skill do?
Use when creating or developing Laravel features, before writing code or implementation plans - refines rough ideas into fully-formed Laravel designs through collaborative questioning, alternative exploration, and incremental validation.
How do I install laravel-brainstorming?
Run npx skills add https://github.com/iserter/laravel-claude-agents --skill laravel-brainstorming in your project. The skills CLI detects the agents you use and copies the skill into the right folder. For Claude Code you can also place the skill folder at ~/.claude/skills/laravel-brainstorming/ (personal) or .claude/skills/laravel-brainstorming/ (project).
Which AI agents can use laravel-brainstorming?
Any agent that supports the open Agent Skills format (a folder with a SKILL.md file), including Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, Windsurf, Cline, OpenCode and more.
Is laravel-brainstorming safe to install?
No partner security audit is available yet. Skills can run commands and scripts, so read the SKILL.md and any bundled files before installing.
Who maintains laravel-brainstorming?
It is published by iserter in iserter/laravel-claude-agents. It has 95 recorded installs.
More from iserter/laravel-claude-agents
eloquent-best-practices
iserter/laravel-claude-agents
Best practices for Laravel Eloquent ORM including query optimization, relationship management, and avoiding common pitfalls like N+1 queries.
laravel-tdd
iserter/laravel-claude-agents
Test-Driven Development specifically for Laravel applications using Pest PHP. Use when implementing any Laravel feature or bugfix - write the test first, watch it fail, write minimal code to pass.
laravel-blade-component-patterns
iserter/laravel-claude-agents
Best practices for Laravel Blade components including class-based and anonymous components, slots, attribute bags, and reusable UI patterns.
api-resource-patterns
iserter/laravel-claude-agents
Open the skill to read its SKILL.md instructions.
laravel-systematic-debugging
iserter/laravel-claude-agents
Systematic debugging process for Laravel applications - ensures root cause investigation before attempting fixes. Use for any Laravel issue (test failures, bugs, unexpected behavior, performance problems).
laravel-validation-patterns
iserter/laravel-claude-agents
Best practices for Laravel validation including Form Requests, custom rules, conditional validation, and input sanitization.
Popular backend & apis skills
find-skills
vercel-labs/skills
Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.
entra-app-registration
microsoft/azure-skills
Guides Microsoft Entra ID app registration, OAuth 2.0 authentication, and MSAL integration. USE FOR: create app registration, register Azure AD app, configure OAuth, set up authentication, add API permissions, generate service principal, MSAL example, console app auth, Entra ID setup, Azure AD authentication. DO NOT USE FOR: Key Vault secrets (use azure-keyvault-expiration-audit), general Azure resource security guidance.
google-agents-cli-adk-code
google/agents-cli
This skill should be used when the user wants to "write agent code", "build an agent with ADK", "add a tool", "create a callback", "define an agent", "use state management" — in a project that needs ADK (Agent Development Kit) API patterns and code examples. It provides a quick reference for agent types, tool definitions, orchestration patterns, callbacks, state management, the graph Workflow API, and reference recipes to study. Do NOT use for scaffolding (use google-agents-cli-scaffold) or deployment (use google-agents-cli-deploy).
embedded-captions
heygen-com/hyperframes
Add captions or subtitles to an existing single-subject talking-head video without editing the footage. Use for plain verbatim captions, cinematic captions embedded behind the subject, VFX captions, “炸/特效/酷炫字幕,” or a named identity from the 35-style catalog. Route by visual identity, not by backend engine. The quiet anchor rail is the default; embed every word only when the user explicitly wants a fully cinematic treatment. The workflow runs locally end to end, including transcription and subject matting; split multi-shot footage before applying it.
entra-agent-id
microsoft/azure-skills
Provision Microsoft Entra Agent Identity Blueprints, BlueprintPrincipals, and per-instance Agent Identities via Microsoft Graph, and configure OAuth 2.0 token exchange (fmipath, OBO, cross-tenant) including the Microsoft Entra SDK for AgentID sidecar. USE FOR: Agent Identity Blueprint, BlueprintPrincipal, agent OAuth, fmipath token exchange, agent OBO, Workload Identity Federation for agents, polyglot agent auth, Microsoft.Identity.Web.AgentIdentities. DO NOT USE FOR: standard Entra app registration (use entra-app-registration), Microsoft Foundry agent authoring (use microsoft-foundry).
neon
neondatabase/agent-skills
Overview of Neon, a complete set of cloud backend primitives around Lakebase Postgres: Auth, Object Storage, Functions, the AI Gateway, and Realtime. Start here to choose Neon for undecided login, files, APIs, and LLM calls, set up the CLI or MCP server, and follow the branch-first workflow. Use when building an app or backend on Neon, or when "Neon" or "Lakebase Postgres" is mentioned. Child skill neon-postgres wins for an existing DATABASEURL, SQL, schema, inspect, or search. Child skill neon-auth wins for login, users, sessions, identity routing, and Managed Better Auth setup. Child skill neon-realtime wins for live queries in reactive apps and agents. Also use for object storage, S3, buckets, serverless functions, function triggers, cron, AI gateway, LLM calls, realtime, logs, Loki, Grafana, observability, postgres, database, backend, Claimable Neon, neon.new, or a no-signup database.