Index of every page on this site: llms.txt
All skills
asyrafhussin avatar

/laravel-ai-sdk

@1aa0ff7
Run it yourself

Laravel AI SDK for building AI-powered features. Use when creating agents, generating images or audio, working with embeddings, vector search, or testing AI features. Triggers on tasks involving laravel/ai, AI agents, tool-calling, structured output, streaming, embeddings, reranking, or AI faking in tests.

Use this Skill: https://skilld.dev/gh/asyrafhussin/agent-skills/laravel-ai-sdk

Nothing lands on disk. Nothing to clean up.

Fork this Skill

Edit a local copy. It keeps the author and licence.

SKILL.md

≈81 tokens for metadata: the name and description. ≈967 when used: this file. ≈26k more on demand in 20 files.

Description uses 4.0% of example budget

Before choosing a Skill, your Agent reads its name and description. All available Skills share that space.

  • A shorter description leaves more room for other Skills. This entry exceeds our 1% size suggestion.

In our Claude Code example, all Skill names and descriptions share 8,000 characters. This Skill uses ≈324 characters, or 4.0%.

The 1% threshold is a size suggestion. Longer descriptions can still fit.

Your model, settings, and other Skills decide how much text your Agent can read.

Example settings and source

The example uses a 200k-token context and default Claude Code settings. The count includes the name, description, separators, and when_to_use when present. Codex also counts local file paths.

Skit's source and limits: Codex 0.160.1, Claude Code 2.1.292.

Laravel AI SDK

Comprehensive guide for building AI-powered features with the Laravel AI SDK (laravel/ai). Contains 17 rules across 7 categories covering agents, tools, media generation, embeddings, vector stores, and testing.

When to Apply

Reference these guidelines when:

  • Creating AI agents with instructions, tools, and structured output
  • Prompting agents with conversation context
  • Streaming or queueing agent responses
  • Generating images, audio, or transcriptions
  • Creating and querying vector embeddings
  • Building RAG (retrieval-augmented generation) features
  • Testing AI features with fakes and assertions

Rule Categories by Priority

Priority Category Impact Prefix
1 Agents CRITICAL agent-
2 Tools HIGH tool-
3 Embeddings & Search HIGH embed-
4 Media Generation MEDIUM media-
5 Files & Storage MEDIUM files-
6 Infrastructure MEDIUM infra-
7 Testing HIGH test-

Quick Reference

1. Agents (CRITICAL)

  • agent-create-configure - Create agents with artisan, PHP attribute configuration
  • agent-prompting - Prompt agents, conversation context, RemembersConversations
  • agent-structured-output - Structured output with JSON schema
  • agent-streaming-async - Streaming, broadcasting, and queueing responses
  • agent-middleware - Agent middleware pipeline
  • agent-anonymous - Anonymous agents for quick interactions

2. Tools (HIGH)

  • tool-create - Create custom tools with schema and handle method
  • tool-provider - Provider tools: WebSearch, WebFetch, FileSearch, SimilaritySearch

3. Embeddings & Search (HIGH)

  • embed-generate-cache - Generate, store, and cache vector embeddings
  • embed-rerank - Rerank documents and collections by relevance

4. Media Generation (MEDIUM)

  • media-images - Generate, store, and queue images
  • media-audio-transcription - Text-to-speech and speech-to-text

5. Files & Storage (MEDIUM)

  • files-vector-stores - File storage and vector stores for RAG

6. Infrastructure (MEDIUM)

  • infra-failover - Automatic provider failover for resilience

7. Testing (HIGH)

  • test-agents - Fake agents, assert prompts, prevent stray prompts
  • test-media - Fake images, audio, and transcriptions
  • test-data - Fake embeddings, reranking, files, and vector stores

Essential Patterns

Creating an Agent

<?php

namespace App\Ai\Agents;

use Laravel\Ai\Contracts\Agent;
use Laravel\Ai\Promptable;

class SalesCoach implements Agent
{
    use Promptable;

    public function instructions(): string
    {
        return 'You are a sales coach, analyzing transcripts and providing feedback.';
    }
}

Prompting

use App\Ai\Agents\SalesCoach;

$response = SalesCoach::make()->prompt('Analyze this sales transcript...');

return (string) $response;

Generating Images

use Laravel\Ai\Image;

$image = Image::of('A donut sitting on the kitchen counter')
    ->landscape()
    ->generate();

$path = $image->store();

Generating Embeddings

use Illuminate\Support\Str;

$embeddings = Str::of('Napa Valley has great wine.')->toEmbeddings();

Testing

use App\Ai\Agents\SalesCoach;

SalesCoach::fake(['First response', 'Second response']);

SalesCoach::make()->prompt('Analyze this...');

SalesCoach::assertPrompted('Analyze this...');

How to Use

Read individual rule files for detailed explanations and code examples.

Each rule file contains:

  • YAML frontmatter with metadata (title, impact, tags)
  • Brief explanation of why it matters
  • Bad Example with explanation
  • Good Example with explanation
  • Laravel 13 and PHP 8.3 specific context and references

Full Compiled Document

For the complete guide with all rules expanded: AGENTS.md

Source: SKILL.md on GitHub

No rule matched.

skilld matched fixed text patterns in SKILL.md and file names. Patterns miss obfuscated code.

skilld run checks every file with the same patterns. It asks for approval before it loads a Skill with a behavior marked Needs approval.

1 warning2mo4 checks · Risk MEDIUM
  • Gen Agent Trust Hub2mo

    The skill provides a comprehensive guide for the Laravel AI SDK but contains deceptive metadata claiming authorship by the 'Laravel Community' despite being associated with the user 'asyrafhussin'. It also presents an indirect prompt injection surface by documenting patterns for ingesting untrusted data (such as transcripts and external URLs) while granting agents capabilities like file system storage and network access.

  • Socket2mo

    No alerts

  • Snyk2mo

    Risk: LOW · No issues

  • ZeroLeaks7mo

    Score: 93/100 · 2 sections analyzed

Signed by skilld at 1aa0ff7. This ties the file your Agent reads to that commit on GitHub. It does not review the instructions.

Last checked against GitHub last month.

Steadyupdated 8 months ago
Other metadata
metadata
{
  "author": "Laravel Community",
  "version": "1.0.0",
  "laravelVersion": "13.x",
  "phpVersion": "8.3+"
}

README badge

README badge for asyrafhussin/agent-skills/laravel-ai-sdk