ai-orchestrator

Use the codebase knowledge graph for structural code queries. Triggers on: explore the codebase, understand the architecture, what functions exist, show me the structure, who calls this function, what does X call, trace the call chain, find callers of, show dependencies, impact analysis, dead code, unused functions, high fan-out, refactor candidates, code quality audit, graph query syntax, Cypher query examples, edge types, how to use search_graph.

UI/UX design intelligence for web and mobile. Includes 50+ styles, 161 color palettes, 57 font pairings, 161 product types, 99 UX guidelines, and 25 chart types across 10 stacks (React, Next.js, Vue, Svelte, SwiftUI, React Native, Flutter, Tailwind, shadcn/ui, and HTML/CSS). Actions: plan, build, create, design, implement, review, fix, improve, optimize, enhance, refactor, and check UI/UX code. Projects: website, landing page, dashboard, admin panel, e-commerce, SaaS, portfolio, blog, and mobile app. Elements: button, modal, navbar, sidebar, card, table, form, and chart. Styles: glassmorphism, claymorphism, minimalism, brutalism, neumorphism, bento grid, dark mode, responsive, skeuomorphism, and flat design. Topics: color systems, accessibility, animation, layout, typography, font pairing, spacing, interaction states, shadow, and gradient. Integrations: shadcn/ui MCP for component search and examples.

any input (code, docs, papers, images) → knowledge graph → clustered communities → HTML + JSON + audit report

Provides comprehensive code review guidance for React 19, Vue 3, Rust, TypeScript, Java, Python, and C/C++. Helps catch bugs, improve code quality, and give constructive feedback. Use when: reviewing pull requests, conducting PR reviews, code review, reviewing code changes, establishing review standards, mentoring developers, architecture reviews, security audits, checking code quality, finding bugs, giving feedback on code.

CI/CD pipeline design with GitHub Actions, Docker, Kubernetes, Helm, and GitOps patterns

AWS cloud patterns for Lambda, ECS, S3, DynamoDB, and Infrastructure as Code with CDK/Terraform

CI/CD pipeline patterns for GitHub Actions, GitLab CI, testing strategies, and deployment automation

MCP server development including tool design, resource endpoints, prompt templates, and transport configuration

Systematically trace problems (bugs, incidents, performance regressions) back to their fundamental, actionable causes using the 5-Whys methodology. Trigger when the user asks: "find the root cause", "почему это произошло", "найди причину бага", "debug this issue", "排查问题", "why did this happen", "root cause analysis", "RCA", or when diagnosing CI/CD failures.

REST API design with resource naming, pagination, versioning, and OpenAPI spec generation

Prompt engineering patterns including structured prompts, chain-of-thought, few-shot learning, and system prompt design

Authentication and authorization patterns including OAuth2, JWT, RBAC, session management, and PKCE flows

Docker best practices including multi-stage builds, compose patterns, image optimization, and security

LLM integration patterns including API usage, streaming, function calling, RAG pipelines, and cost optimization

Web performance optimization including bundle analysis, lazy loading, caching strategies, and Core Web Vitals

Application security covering input validation, auth, headers, secrets management, and dependency auditing

Kubernetes operations including manifests, Helm charts, operators, troubleshooting, and resource management

Microservices design patterns including service mesh, event-driven architecture, saga pattern, and API gateway

Real-time communication patterns with WebSocket, Socket.io, Server-Sent Events, and scaling strategies

Advanced git workflows including worktrees, bisect, interactive rebase, hooks, and recovery techniques

Systematically decompose complex problems into fundamental truths and reason up from there, avoiding the trap of reasoning by analogy. Trigger when the user asks: "analyze from first principles", "第一性原理", "think from scratch", "is this the right approach", "challenge assumptions", "проанализируй архитектуру", "правильно ли мы это делаем?", "есть вариант лучше?", or when making major architectural decisions.

Write, review, debug, and improve bash/shell scripts for any context: CI/CD pipelines (GitHub Actions, GitLab CI, Bitrise), DevOps automation, macOS/Linux system tasks, file processing, and data transformation. Use this skill whenever the user asks to write a shell script, improve an existing one, debug a bash error, or automate any task via command line — even if they just say "make a script that does X" or paste a broken script without explanation. Also trigger for requests involving cron jobs, entrypoints, deploy scripts, migration scripts, or any .sh file.

Write, review, debug, and improve Python code across any context: CLI scripts, automation, data processing, REST APIs (FastAPI/Flask), async code, testing, packaging, and CI/CD tooling. Use this skill whenever the user asks to write a Python script, debug a Python error, improve existing code, set up a project, work with virtual environments, type hints, decorators, async/await, dataclasses, Pydantic models, or asks about Python best practices. Also trigger for requests involving requirements.txt, pyproject.toml, pytest, pandas, httpx, or any .py file.

Write, review, debug, and improve TypeScript code across any context: React SPAs, Node.js tooling, CLI scripts, automation, monorepos, and API backends. Use this skill whenever the user asks about TypeScript types, generics, tsconfig, type errors, Zod validation, type narrowing, mapped/conditional types, path aliases, project references, JS-to-TS migration, or typed React components and hooks. Also trigger when the user pastes a TypeScript error they don't understand, or asks how to type something specific