borghei

Context management engine for AI coding agents. Handles context window optimization, persistent memory across sessions, context retrieval strategies, token budget allocation, and knowledge graph construction from codebases. Use when building agent memory systems, optimizing context windows, designing RAG pipelines for code, or managing multi-session agent state.

Navigate, manage, and optimize monorepos with Turborepo, Nx, pnpm workspaces, and Changesets. Covers cross-package impact analysis, selective builds, dependency graph visualization, remote caching, migration from multi-repo, and coordinated publishing. Use when working in monorepos, optimizing build times, or managing shared packages.

ISO 42001 AI Management System compliance automation. Assesses organizational readiness for AIMS certification, evaluates AI system impacts, validates governance structures, and checks Annex A controls. Use for ISO 42001 readiness assessments, AI governance planning, AI impact assessments, responsible AI implementation, and AIMS certification preparation.

Porter's Five Forces — analyze the competitive intensity and attractiveness of an industry. Use when evaluating a new market entry, understanding why margins are under pressure, designing a defensive strategy, or auditing strategic positioning at industry level.

Computer vision engineering skill for object detection, image segmentation, and visual AI systems. Covers CNN and Vision Transformer architectures, YOLO/Faster R-CNN/DETR detection, Mask R-CNN/SAM segmentation, and production deployment with ONNX/TensorRT. Includes PyTorch, torchvision, Ultralytics, Detectron2, and MMDetection frameworks. Use when building detection pipelines, training custom mode

Performs financial ratio analysis, DCF valuation, budget variance analysis, and rolling forecast construction for strategic decision-making

Build production-ready MCP (Model Context Protocol) servers with tool definitions, resource providers, prompt templates, and transport configuration. Covers OpenAPI-to-MCP conversion, TypeScript and Python implementations, testing strategies, authentication, and deployment. Use when exposing APIs to AI agents, building tool servers, or creating MCP integrations.

Define a sharp Ideal Customer Profile (ICP) — firmographics + behavioral signals + JTBD + trigger event + buyer persona — that marketing, sales, and product can all use. Use when defining a new ICP, refining an existing one based on actual closed customers, or auditing why pipeline / conversion is poor.

Generate complete production-ready SaaS boilerplate with authentication, database schemas, billing integration (Stripe), multi-tenancy, API routes, dashboard UI, and deployment configuration. Supports Next.js App Router, TypeScript, Tailwind, shadcn/ui, Drizzle ORM, and multiple auth/payment providers. Use when starting a new SaaS product, subscription app, or multi-tenant platform.

Strategyzer Value Proposition Canvas (Customer Profile + Value Map) with fit validation across problem-solution and product-market dimensions.

Agile product ownership for backlog management and sprint execution. Covers user story writing, acceptance criteria, sprint planning, and velocity tracking. Use for writing user stories, creating acceptance criteria, planning sprints, estimating story points, breaking down epics, or prioritizing backlog.

Analyze a codebase and generate comprehensive onboarding documentation including architecture overviews, key file maps, local setup guides, task runbooks, debugging guides, and contribution guidelines. Audience-aware output for junior, senior, or contractor developers. Use when onboarding new team members, open-sourcing, or documenting after a major refactor.