Token导航 LogoToken导航TokenDH.com
运维和基础设施external-servicegithub未标认证来源可访问许可证需确认审计提醒

laravelLaravel 搜索

Agent Skill

laravel 用于处理 GitHub 仓库、Issue、Pull Request 和代码协作信息,适合在 Codex、Claude、Cursor、Gemini CLI 中需要围绕仓库状态、代码变更或协作事项进行整理时使用。可结合来源仓库、安装命令和原始 README 继续核验具体用法。安装前建议确认权限范围、维护状态,以及是否会触发联网、命令执行或文件读写。

总安装

864

周安装

36

GitHub Stars

公开资料未说明

下载量

288
CodexClaudeCursorGemini CLI

安装说明

本站只整理中文说明和来源信息,不托管安装包,也不代用户安装。

GitHub

来源数

2

许可证

unknown

最后核验

2026-05-01

来源状态

来源可访问

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手,先确认命令和权限,再让它执行。

请帮我安装这个 Agent Skill:laravel(Laravel 搜索)
来源仓库:https://github.com/ulpi-io/skills
仓库路径:skills/laravel
安装命令:
npx skills add https://github.com/ulpi-io/skills --skill laravel
安装前请先检查当前环境是否支持对应 CLI,并向我确认将要执行的命令、安装目录、联网范围和文件读写权限;确认后再执行。

命令行安装

复制命令到本机终端执行。该命令会通过 npx skills 从第三方来源获取 Skill;本站只展示命令,不托管安装包,也不自动执行。

skills.shnpx skills
npx skills add https://github.com/ulpi-io/skills --skill laravel

简介

用于处理 GitHub 仓库、Issue 和 Pull Request 信息。

  • 适合围绕代码变更或协作事项进行整理。
  • 可结合来源仓库和原始 README 核验具体用法。
  • 安装前建议确认权限范围和维护状态。laravel 属于运维和基础设施类 Skill,可作为该场景下的辅助能力补充。
  • 注意是否会触发联网或命令执行操作。

SKILL.md

Non-negotiable rules:

  1. Load references/stack.md first, then only the task-relevant references.
  2. No business logic in controllers. Controllers validate (Form Request), delegate (Action), return (API Resource). Nothing else.
  3. No returning Eloquent models directly. Every response goes through an API Resource.
  4. No inline validation. All validation lives in Form Request classes.
  5. No $guarded = []. Every model uses explicit $fillable.
  6. No raw queries. Use Eloquent or query builder with parameter bindings.
  7. No bare queue:work. All queue processing uses Horizon.
  8. Model::shouldBeStrict() must be enabled in AppServiceProvider::boot().

laravel

Inputs

  • $request: The Laravel task, bug, feature, or subsystem being worked on

Goal

Route Laravel work through the correct project conventions so the implementation follows the existing backend architecture instead of generic framework defaults.

Step 0: Read the stack contract

Always start with:

  • references/stack.md

That establishes the locked runtime, package, and architecture choices for this Laravel surface.

Success criteria: The project's Laravel stack choices are explicit before implementation starts.

Step 1: Load only the relevant references

Use the routing table to pick reference files that match the actual task. Do not bulk-load the full reference tree.

TaskRead
Starting a session / understanding the stackreferences/stack.md
Creating or modifying files, folder conventionsreferences/folder-structure.md
API routes, versioning, middlewarereferences/routing.md
Creating or editing a controllerreferences/controller-pattern.md
Adding validation to a requestreferences/form-requests.md
Creating or editing a model, relationships, scopesreferences/eloquent-models.md
API response transformation, pagination, filteringreferences/api-resources.md
Business logic, Actions, DTOs, service providersreferences/service-layer.md
Authentication, tokens, roles, policiesreferences/auth.md
Migrations, seeders, factories, query optimizationreferences/database.md
Error responses, exception handlingreferences/error-handling.md
Logging configuration, structured loggingreferences/logging.md
Redis caching, cache invalidation, TTL strategyreferences/caching.md
Jobs, queues, events, Horizon, broadcastingreferences/queues-jobs.md
Writing tests (feature or unit)references/testing.md
Security hardening, CORS, rate limiting, webhooksreferences/security.md
API documentation generationreferences/api-docs.md
Telescope, Horizon dashboard, Pulse, health checksreferences/observability.md
Filament admin panel, resources, pages, widgetsreferences/filament.md
Docker setup, CI/CD, deploymentreferences/docker.md
Notifications, email, SMSreferences/notifications-mail.md
File uploads, S3, media libraryreferences/file-storage.md
Task scheduling, cron jobsreferences/scheduling.md
AI agents, text/image/audio generation, embeddings, RAGreferences/ai-sdk.md
AI-assisted development, Boost setup, guidelines, skillsreferences/boost.md
MCP servers, exposing app to AI clients, tools/resources/promptsreferences/mcp.md

Multiple tasks? Read multiple files. The references are self-contained.

Success criteria: Only the task-relevant Laravel conventions are in play.

Step 2: Implement with the core Laravel guardrails

Keep these rules active:

  • controllers validate, delegate, and return
  • responses go through API Resources
  • list endpoints paginate
  • models use explicit $fillable
  • mutations use the correct Action or transaction pattern
  • queues use the project's queue and Horizon conventions

Success criteria: The change matches the project’s Laravel architecture instead of framework-default shortcuts.

Step 3: Verify with the narrowest relevant checks

Use the smallest verification loop that matches the task:

  • PHPUnit or Pest tests
  • focused artisan or framework checks
  • static analysis or linting if already part of the repo workflow

Success criteria: The change is validated in the way this Laravel project expects.

Guardrails

  • Do not inline the whole Laravel handbook in SKILL.md.
  • Do not skip references/stack.md.
  • Do not return raw Eloquent models directly.
  • Do not put business logic in controllers.
  • Do not add disable-model-invocation; this is a normal domain skill.

When To Load References

  • references/stack.md Always.
  • then only the task-relevant files under references/

Output Contract

Report:

  1. which Laravel references were loaded
  2. the architecture pattern chosen
  3. the change made
  4. the verification run

适合场景

01

用户想查找某类 Agent Skill 时

02

需要根据任务场景推荐可安装能力包时

03

需要对比不同来源的安装命令和来源信息时

能力概览

能力 1

按任务关键词查找相关 Skills

能力 2

展示可复制的安装命令

能力 3

保留来源站点、仓库和原始说明,方便继续核验

能力 4

展示第三方安全扫描或审计结果

安装后应在对应宿主中按原始 README 的触发条件使用;具体调用方式请以来源页面和 README 为准。

平台分布

Codex

36.45%
按下载量换算105

Claude

29.33%
按下载量换算84

Cursor

19.48%
按下载量换算56

Gemini CLI

8.58%
按下载量换算25

安全审计

Gen Agent Trust Hub

通过

Socket

通过

Snyk

可疑

权限和风险

external-service

该 Skill 可能调用第三方服务、云服务或外部模型 API,使用前需要确认账号、额度、数据发送范围和服务条款。

安装前确认

本站仅展示第三方公开信息,不托管安装包,不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。来源安全扫描存在 warning/failed 结果,不能写成本站确认安全。当前只有一个来源,正式发布前建议补源仓库或其他目录站核验。

来源信息

继续浏览同类 Skills