agent-skills
AGENTS.md72 starsChanged 8 months agoMITView on GitHub
This repository contains comprehensive skills for AI coding agents, optimized for: - React + Vite - React + TypeScript - Laravel 13 + Inertia.js + React - Tailwind CSS - React Query + Zustand - PHP 8.x - Clean Code & Design Patterns Skills in skills/ directory follow the Agent Skills format. Each skill has: - SKILL.md - Main instructions with YAML frontmatter - rules/ - Detailed rules (loaded on demand) When adding new rules: 1. Follow the existing rule…
Where files are headingNew AGENTS.md files have more rules about keeping secrets out of the code, and fewer about code style.
Of the AGENTS.md files we read, the 31,439 first seen in the last six months, against the older ones: the kind of rule that gained most share, and the kind that lost most. About files like this in general, not this one, and an estimate, since a kind is a pattern in the words.
In this repositoryOne other file it gives its agents.
- CLAUDE.mdCLAUDE.md
The file
We split this AGENTS.md into the rules it gives an agent
3 rules. About 0 are common, 2 are distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈2
Distinctive · estimate
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 44
When adding new rules:
- Very specific: line 45
Follow the existing rule template in rules/_template.md
- Distinctive: line 48
Add appropriate priority level
≈ “Common” is an estimate: at least 1 in 5 of the 40,246 AGENTS.md files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Agent Skills Repository
This repository contains comprehensive skills for AI coding agents, optimized for:
- React + Vite
- React + TypeScript
- Laravel 13 + Inertia.js + React
- Tailwind CSS
- React Query + Zustand
- PHP 8.x
- Clean Code & Design Patterns
Skills Overview
| Skill | Rules | Priority Focus |
| api-design-patterns | 38 | REST, error handling, pagination |
| clean-code-principles | 23 | SOLID, DRY, design patterns |
| git-workflow | 31 | Commits, branching, PRs |
| laravel-ai-sdk | 17 | Agents, tools, embeddings, testing |
| laravel-best-practices | 31 | Architecture, Eloquent, security |
| laravel-database-optimization | 33 | Eloquent queries, indexing, caching, N+1 |
| laravel-inertia-react | 24 | Page components, forms |
| laravel-mcp | 7 | MCP servers, tools, prompts, resources |
| laravel-owasp-security | 8 | OWASP Top 10, secure coding, auth |
| laravel-testing | 24 | Pest PHP 4 & PHPUnit 12, HTTP tests, factories, faking, AI SDK |
| php-best-practices | 51 | PHP 8.x, PSR, SOLID |
| prd-writing | 25 | PRD workflow, feature specs, requirements |
| react-vite-best-practices | 23 | Build optimization, code splitting |
| seo-best-practices | 31 | Meta tags, structured data, Core Web Vitals, SEO audit |
| state-management | 26 | React Query, Zustand |
| tailwind-best-practices | 29 | Responsive, dark mode |
| testing-best-practices | 34 | Unit tests, mocking, coverage |
| typescript-react-patterns | 33 | Type safety, generics |
| web-design-guidelines | 23 | Accessibility, UX, WCAG audit |
Usage
Skills in skills/ directory follow the Agent Skills format. Each skill has:
SKILL.md- Main instructions with YAML frontmatterrules/- Detailed rules (loaded on demand)
Contributing
When adding new rules:
- Follow the existing rule template in
rules/_template.md - Include incorrect and correct code examples
- Explain the "why" not just the "what"
- Add appropriate priority level
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.