General development guidelines, architecture patterns, conventions, and engineering practices for AI coding agents.
Safely commit uncommitted changes with proper branch management and semantic commit messages.
Open a pull request on GitHub using the GitHub MCP, following the repo's PR template.
Create a skeleton loading component that mirrors a target component's layout to prevent layout shift.
Expert architecture reviewer that first detects the project platform, then audits code against the matching platform-specific guidelines (when available) and fixes violations. Use when reviewing code for architecture compliance, checking naming conventions, validating module placement, auditing imports, verifying component structure, or ensuring adherence to project conventions before merging.
Build skeleton loading components that mirror existing UI layout. Use when creating skeleton loaders, loading placeholders, Suspense fallbacks, Next.js loading.tsx files, or any visual placeholder that must match the final layout to prevent layout shift.
Storybook stories specialist for reviewing, editing, and creating stories that align with project conventions and visual regression goals. Use when writing new stories, improving existing stories, or auditing stories for quality and coverage.
Next.js application guidelines, architecture, conventions, and engineering patterns. Use when writing or refactoring code, adding modules or components, answering questions about architecture, deciding when to use feature flags, applying naming and placement conventions, or answering which technologies and libraries the project uses.
Create skeleton loading components that mirror existing UI layout. Use when creating skeleton loaders, loading placeholders, Suspense fallbacks, Next.js loading.tsx files, or any visual placeholder that must match the final layout to prevent layout shift.
Storybook story authoring guidelines — when to create stories, variant policy, file placement, title convention, decorators, MSW mocking, and mock data. Use when writing or reviewing Storybook stories, deciding which variants to add, configuring Next.js navigation in stories, or mocking API calls with MSW.
Use the Switchboard CLI to manage Powerhouse Switchboard drives, documents, folders, mutations, exports/imports, analytics, real-time subscriptions, and raw GraphQL. Apply when the user wants to work with Switchboard from the terminal, create/edit document models, query or mutate documents, run arbitrary GraphQL, watch changes, or move data between instances.
Uses power tools
Uses Bash, Write, or Edit tools
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
AI agent plugin with platform guidelines, architecture, conventions, and engineering patterns. Compatible with Claude Code and Cursor.
| Type | Name | Description |
|---|---|---|
| Skill | nextjs-guidelines | Architecture, conventions, data & GraphQL, feature flags, and tech stack rules for Next.js apps |
| Skill | storybook-stories | Storybook story authoring rules: when to create stories, variants, decorators, MSW mocks, and mock data |
| Skill | skeleton-loading | Skeleton loading patterns and component guidelines |
| Agent | skeleton-builder | Builds skeleton loading components following platform patterns |
| Agent | stories-builder | Reviews, edits, and creates Storybook stories using the storybook-stories skill |
| Agent | architecture-compliance | Audits code against platform guidelines and fixes violations |
| Command | skeleton | Create a skeleton loading component |
/plugin marketplace add YasielCabrera/addg-guidelines-skills
/plugin install addg@addg
Or load locally:
claude --plugin-dir /path/to/addg-guidelines-skills
Local development (test plugins locally):
Clone this repo (or use your existing checkout path).
Symlink the repository root (the folder that contains .cursor-plugin/) into Cursor’s local plugins directory:
mkdir -p ~/.cursor/plugins/local
ln -sfn /path/to/addg-guidelines-skills ~/.cursor/plugins/local/addg
Use ln -sfn so re-running the command updates an existing symlink.
Reload Cursor (Command Palette → Developer: Reload Window, or restart the app).
Confirm under Settings → Plugins that the plugin is listed.
If the plugin does not appear after reload, some Cursor versions do not follow symlinks under ~/.cursor/plugins/local/; copy the repo instead: cp -R /path/to/addg-guidelines-skills ~/.cursor/plugins/local/addg (related issue).
npx skills add https://github.com/YasielCabrera/addg-guidelines-skills --skill nextjs-guidelines
MIT
npx claudepluginhub yasielcabrera/addg-guidelines-skills --plugin addgValidation and quality enforcement for gluestack-ui projects with component patterns, accessibility, and theming skills. Includes MCP server for component discovery and source code retrieval.
Reusable UI component patterns for implementing common features across different frameworks and tech stacks
Create skills from documentation folders and project codebases. Review, test, and package Anthropic Agent Skills for Claude.ai and Claude Code. 13 commands including from-docs, from-project, beginner tutorial, interactive wizard, templates, quality auditing, and distribution packaging.
High-intelligence Claude Code copilot with deep code reasoning, evidence-driven planning, orchestration-first execution, model routing, context budgeting, CI/CD integration, enterprise security, plugin development, prompt engineering, performance profiling, agent teams, channels (event-driven autonomy with CI webhook, mobile approval relay, Discord bridge, and fakechat dev profile), interactive tutorials, LSP integration, security-hardened hook script library, MCP Prompts coverage, common workflow packs, runtime selection guide, computer-use patterns, checkpointing, scheduled-task blueprints, repo bootstrap scanner, hook policy engine (8 installable packs), layered memory deployment, role-based subagent packs (implementer, debugger, migration-lead, dependency-auditor, release-coordinator), 5 agent-team topology kits, autonomy operating mode (4 profiles + 3 gates), and a queryable 15-tool MCP documentation server with autonomy advisor.
better-chatbot project conventions and standards. Use for contributing code, following three-tier tool system (MCP/Workflow/Default), or encountering server action validators, repository patterns, component design errors.
Custom commands, skills, agents, rules, hooks, and output styles for Claude Code - session continuity and modern CLI tooling for real-world development workflows