cappyeo

Production-grade GenAI, Agentic Systems, RAG, and Evaluation pipelines. Use for LLM integration, multi-agent workflows, and rigorous testing.

Code review practices emphasizing technical rigor, verification gates, evidence-based claims, and security-focused differential review. Use when receiving feedback, completing tasks, reviewing PRs for security regressions, or before making completion/success…

prompt-engineer skill for AI-powered development.

Self-improving agent patterns: evolutionary skill discovery, feedback descent optimization, and automated capability gap analysis. Use for agent tuning, skill evolution, and prompt optimization loops.

Test planning, test cases, bug reporting, automation, and security auditing. Use for Unit/E2E/Security/Performance/Property-Based testing and supply chain audits. Upgraded with Trail of Bits security methodology.

UI/UX design intelligence with searchable database. 50+ styles, 161 color palettes, 57 font pairings, 161 product types, 99 UX guidelines. BM25 search engine for data-driven design decisions. Use for creating interfaces, visual identity, design systems, and…

Foundation for all frontend development. Use when implementing UI code, optimizing performance, or ensuring accessibility. Includes Vercel React performance rules and composition patterns.

Guide for creating production-grade MCP (Model Context Protocol) servers. Use when building MCP servers to integrate external APIs, databases, or services ??whether in TypeScript (MCP SDK) or Python (FastMCP). Covers architecture, tool design, security,…

Main application building orchestrator. Creates full-stack applications from natural language requests. Determines project type, selects tech stack, coordinates agents.

Requirements analysis, technical specs, agile documentation. Use for bridging business goals to technical implementation.

UI/UX design intelligence with searchable database. 50+ styles, 161 color palettes, 57 font pairings, 161 product types, 99 UX guidelines. BM25 search engine for data-driven design decisions. Use for creating interfaces, visual identity, design systems, and…

CI/CD, multi-cloud infrastructure, and observability. Use for AWS/GCP/Azure, Docker, Kubernetes, and SRE practices.

High-stakes technical decisions, system design, cloud infrastructure. Use for Microservices/Monolith, ADRs, RFCs, and scalability.

Project planning, roadmapping, requirements, prioritization, and skill management. Use for PRDs, user stories, RICE/Kano, discovery, and process automation. Upgraded with Dean Peters product management frameworks.

Test planning, test cases, bug reporting, automation, and security auditing. Use for Unit/E2E/Security/Performance/Property-Based testing and supply chain audits. Upgraded with Trail of Bits security methodology.

Generates production-quality SVG technical diagrams from text descriptions. Use when asked to create, draw, visualize, or illustrate any technical diagram — architecture, flowchart, sequence, agent system, data flow, ER, UML, mind map, network topology, or…

Analyzes codebase structure using blast-radius tracing, hub/bridge detection, and risk scoring. Use when reviewing code changes, assessing refactoring impact, understanding project architecture, or preparing for code review.

Quick review of only changes since last commit using blast-radius detection. Token-efficient delta review. Use for fast iteration reviews during development, checking if recent edits broke anything, or reviewing a single commit.

Performs full PR review with blast-radius analysis and structured output. Use when reviewing a complete pull request, checking merge readiness, or assessing multi-commit changes against a base branch.

Builds or updates the code knowledge graph. Use before first-time code review, after major refactoring, or when analysis seems stale. With shell scripts, the graph is built implicitly on each run — no separate build step needed.