All skills
asyrafhussin avatar

/laravel-ai-sdk

@7221662

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

This session only. Nothing lands on disk.

README.md

≈510 tokens on demand. Your agent reads this file only when SKILL.md points to it.

Laravel AI SDK

Comprehensive guide for building AI-powered features with the Laravel AI SDK (laravel/ai). 17 rules across 7 categories.

Version: 1.0.0

Overview

This skill provides guidance for:

  • Creating and configuring AI agents
  • Building custom tools and using provider tools
  • Generating images, audio, and transcriptions
  • Creating and querying vector embeddings
  • Managing files and vector stores for RAG
  • Testing AI features with fakes and assertions

Categories

1. Agents (Critical)

Create agents with instructions, tools, structured output, streaming, and middleware.

2. Tools (High)

Build custom tools with JSON schemas. Use provider tools like WebSearch, WebFetch, FileSearch.

3. Embeddings & Search (High)

Generate embeddings, cache them, query with pgvector, and rerank results.

4. Media Generation (Medium)

Generate images and audio. Transcribe speech to text.

5. Files & Storage (Medium)

Store files with AI providers. Create vector stores for retrieval-augmented generation.

6. Infrastructure (Medium)

Automatic provider failover for resilience.

7. Testing (High)

Fake agents, images, audio, embeddings, and vector stores. Assert prompts and generations.

Rules

Rule Category Impact
agent-create-configure Agents CRITICAL
agent-prompting Agents CRITICAL
agent-structured-output Agents HIGH
agent-streaming-async Agents HIGH
agent-middleware Agents MEDIUM
agent-anonymous Agents MEDIUM
tool-create Tools HIGH
tool-provider Tools HIGH
embed-generate-cache Embeddings & Search HIGH
embed-rerank Embeddings & Search MEDIUM
media-images Media Generation MEDIUM
media-audio-transcription Media Generation MEDIUM
files-vector-stores Files & Storage MEDIUM
infra-failover Infrastructure MEDIUM
test-agents Testing HIGH
test-media Testing HIGH
test-data Testing HIGH

Source: SKILL.md on GitHub

1 warning16d4 checks · Risk MEDIUM
  • Gen Agent Trust Hub16d

    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.

  • Socket16d

    No alerts

  • Snyk16d

    Risk: LOW · No issues

  • ZeroLeaks5mo

    Score: 93/100 · 2 sections analyzed

Signed by skilld at 7221662. 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 7 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