By v1truv1us
Scaffold agent applications across multiple harnesses, create Claude Code and OpenCode plugins, commands, agents, skills, and custom tools with AI assistance, and validate plugin structure.
Create a new OpenCode agent with AI assistance. Uses agent-creator for intelligent agent generation.
Create a new OpenCode command with AI assistance. Uses command-creator for intelligent command generation.
Guided end-to-end plugin creation workflow for OpenCode extensions. Creates plugins, commands, agents, skills, and custom tools with AI assistance. Follows systematic 8-phase process from discovery to documentation.
Create a new OpenCode skill with AI assistance. Uses skill-creator for intelligent skill generation.
Create a new OpenCode custom tool with AI assistance. Uses tool-creator for intelligent TypeScript tool generation.
AI-assisted agent generation for Claude Code and OpenCode. Creates properly formatted agent files for either platform. Use when user asks to "create an agent", "generate an agent", "make an agent that...", or describes agent functionality needed.
Expert AI agent developer specializing in building production-grade AI agents, MCP servers, and A2A protocol implementations. Implements tool/function calling, agent orchestration, memory systems, and multi-agent coordination patterns. Use PROACTIVELY for AI agent development, MCP server creation, tool integration, or agent orchestration.
AI-assisted command generation for Claude Code and OpenCode. Creates properly formatted command files for either platform. Use when user asks to "create a command", "make a command", "build a command that...", or needs command development assistance.
Validates OpenCode plugin structure, formats, and best practices. Use after creating components or when user asks to "validate", "check", or "verify" plugin structure. Works with both OpenCode and Claude Code components.
AI-assisted skill creation for Claude Code and OpenCode. Creates properly formatted skills with progressive disclosure. Use when user asks to "create a skill", "add a skill", "write a new skill", "build a skill that...", or needs skill development guidance.
Unified agent application scaffolding across 5 harnesses: Anthropic, Cursor, OpenAI, OpenCode, and Pi. Interactive project generator with live SDK docs, per-harness code patterns, and built-in verification. Use when someone says "create an agent app", "new SDK project", "build with [harness] SDK", "scaffold agent", or wants to verify an existing agent setup.
Design or review CLIs so coding agents can run them reliably: non-interactive flags, fast actionable errors, idempotency, dry-run, layered --help. Use when building a CLI or adding commands.
Build Gemini-backed agent workflows and adapters. Use for Google Gemini API/ADK-style runners, Gemini CLI workflow parity, tool calling, structured outputs, or adding a Gemini variant beside Cursor/OpenCode/Claude runners.
Recursively initialize AGENTS.md in monorepo subdirectories with smart detection. Creates hierarchical agent context files with proper linking to root CLAUDE.md and parent AGENTS.md. Use for setting up multi-package projects, microservices, or any project with important subdirectories that need AI agent guidance.
This skill should be used when creating extensions for Claude Code or OpenCode, including plugins, commands, agents, skills, and custom tools. Covers both platforms with format specifications, best practices, and the ai-eng-system build system.
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 engineering workflow toolkit for Claude Code and OpenCode with namespaced commands, 38 specialized agents, and reusable skills covering the full development lifecycle from idea to production.
This repository ships three npm packages:
@ai-eng-system/core - shared library and content-loading helpers@ai-eng-system/toolkit - generated Claude Code, OpenCode, Cursor, Gemini, Pi, and marketplace assets@ai-eng-system/cli - executable installer and command-line workflowsThe repo root package is private and is never published.
Scheduled Research Runner (Pi cron on your VPS): docs/deploy/coolify.md
Optional docs site: docs-site/DEPLOYMENT.md
npm install -g @ai-eng-system/cli
# Install commands, agents, and skills into the current project
ai-eng install --scope project
# Or install globally for OpenCode
ai-eng install --scope global
/plugin marketplace add v1truv1us/ai-eng-system
/plugin install ai-eng-system@ai-eng-marketplace
{
"$schema": "https://opencode.ai/config.json",
"plugin": ["opencode-skills", "ai-eng-system"]
}
OpenCode learning automation now surfaces toast-based suggestions for /ai-eng/decision-journal and /ai-eng/quality-gate, then waits for explicit /ai-eng/learning-approve, /ai-eng/learning-dismiss, or /ai-eng/learning-snooze consent. Local policy and state live under .ai-context/learning/.
pi install npm:@ai-eng-system/toolkit
Pi loads skills from .pi/skills/ and command prompts from .pi/prompts/ in the toolkit package.
See docs/cursor-setup.md. Install @ai-eng-system/toolkit and use the generated .cursor-plugin bundle (skills, agents, and rules/cursor/).
See docs/gemini-cli-setup.md. Install @ai-eng-system/toolkit and copy the generated .gemini/ bundle (skills and commands).
| Phase | Command | Purpose |
|---|---|---|
| Research | /ai-eng/research | Multi-phase codebase and external research |
| Specify | /ai-eng/specify | Feature/spec generation with TCRO structure |
| Plan | /ai-eng/plan | Implementation planning |
| Work | /ai-eng/work | Guided execution with quality gates |
| Verify | /verify | Lint, typecheck, test, build gate |
| Review | /ai-eng/review | Multi-agent code review |
Shorthand lifecycle entrypoints:
| Shorthand | Canonical Command |
|---|---|
/spec | /ai-eng/specify |
/build | /ai-eng/work |
/ai-eng/plan and /ai-eng/review are direct lifecycle entrypoints with no separate shorthand file.
Related commands:
/ai-eng/ralph-wiggum - iterative full-cycle workflow/ai-eng/simplify - code reuse, quality, and efficiency simplificationai-eng/ namespace plus shorthand lifecycle entrypointsSelected commands beyond the core workflow:
/ai-eng/create-plugin, /ai-eng/create-agent, /ai-eng/create-command, /ai-eng/create-skill, /ai-eng/create-tool/ai-eng/code-review, /ai-eng/agent-analyzer, /ai-eng/fact-check, /ai-eng/deep-research, /ai-eng/content-optimize/ai-eng/deploy, /ai-eng/docker, /ai-eng/cloudflare, /ai-eng/github, /ai-eng/k8s, /ai-eng/monitoring, /ai-eng/security-scan/ai-eng/context, /ai-eng/knowledge-capture, /ai-eng/knowledge-architecture, /ai-eng/decision-journal, /ai-eng/quality-gate, /ai-eng/maintenance-review, /ai-eng/learning-approve, /ai-eng/learning-dismiss, /ai-eng/learning-snooze, /ai-eng/init, /ai-eng/seoClaude marketplace packaging note:
ai-eng-core keeps the core plan/work/review workflowai-eng-learning now packages /ai-eng/knowledge-architecture, /ai-eng/decision-journal, /ai-eng/quality-gate, /ai-eng/maintenance-review, /ai-eng/learning-approve, /ai-eng/learning-dismiss, and /ai-eng/learning-snooze/ai-eng/knowledge-capture remains outside that plugin groupSee docs/reference/commands.md for the full command list.
The generated outputs now preserve namespaced skill paths.
Examples:
skills/ai-eng/simplify/SKILL.md -> /ai-eng/simplifyskills/workflow/ralph-wiggum/SKILL.md -> /ai-eng/ralph-wiggumskills/comprehensive-research/SKILL.md -> /ai-eng/researchskills/knowledge-architecture/SKILL.md -> /ai-eng/knowledge-architectureSee docs/reference/skills.md for the full skill inventory.
npx claudepluginhub p/v1truv1us-ai-eng-plugin-dev-plugins-ai-eng-plugin-devContent optimization, SEO, and communication tools
Infrastructure, deployment, and DevOps automation
Curated collection of engineering tools, agents, and workflows. Comprehensive system for AI-assisted software engineering and DevOps.
Core workflow: plan, work, review cycle with research and context engineering
Learning workflows for knowledge mapping, decisions, quality gates, and maintenance reviews
Unified capability management center for Skills, Agents, and Commands.
Ultra-compressed communication mode. Cuts 65% of output tokens (measured) while keeping full technical accuracy by speaking like a caveman.
Comprehensive UI/UX design plugin for mobile (iOS, Android, React Native) and web applications with design systems, accessibility, and modern patterns
Multi-model consensus engine integrating OpenAI Codex CLI, Gemini CLI, and Claude CLI for collaborative code review and problem-solving.
Standalone image generation plugin using Nano Banana MCP server. Generates and edits images, icons, diagrams, patterns, and visual assets via Gemini image models. No Gemini CLI dependency required.
Write feature specs, plan roadmaps, and synthesize user research faster. Keep stakeholders updated and stay ahead of the competitive landscape.