AI-powered upgrade intelligence platform. Multi-agent council analyzes your codebase across 8 dimensions, produces confidence-scored suggestions with visual impact heatmaps, upgrade roadmaps, framework-specific deep dives, and before/after impact previews. Features innovation radar, tech debt forecasting, and coordinated upgrade bundles.
npx claudepluginhub markus41/claude --plugin upgrade-suggestionAI-powered upgrade intelligence. Spawns a council of specialist agents (performance, security, architecture, UX, DX) that analyze your codebase in parallel, vote on findings with confidence scores, and present a visual impact dashboard with heatmaps, sparklines, and before/after previews.
Deep-dive analysis of a single upgrade. Produces a full impact report with risk assessment, implementation plan with numbered steps, affected file list, test strategy, rollback plan, and before/after code previews.
Generates a prioritized, sequenced upgrade roadmap showing what to implement first, dependency chains between upgrades, estimated effort, and cumulative impact curves. Visualizes the optimal implementation path as a directed graph.
Council specialist focused on code architecture, patterns, and structural improvements
Synthesizes findings from all council specialists into weighted, deduplicated recommendations
Council specialist focused on developer experience, tooling, and workflow improvements
Council specialist focused on performance optimization opportunities
Council specialist focused on security vulnerabilities and hardening opportunities
Fast single-agent analyzer for quick mode — covers all dimensions in one pass
Council specialist focused on user experience, accessibility, and UI innovation
> Patterns from "Agentic Design Patterns" (Gulli & Sauco, 2025) applied to AI-powered codebase upgrade intelligence
Identifies cutting-edge, innovative upgrade opportunities based on tech stack and industry trends
Deep project fingerprinting for tech stack detection, architecture analysis, and quality assessment
Core analysis patterns, detection heuristics, and scoring algorithms for the upgrade intelligence system
Comprehensive skill pack with 66 specialized skills for full-stack developers: 12 language experts (Python, TypeScript, Go, Rust, C++, Swift, Kotlin, C#, PHP, Java, SQL, JavaScript), 10 backend frameworks, 6 frontend/mobile, plus infrastructure, DevOps, security, and testing. Features progressive disclosure architecture for 50% faster loading.
Comprehensive PR review agents specializing in comments, tests, error handling, type design, code quality, and code simplification
Complete collection of battle-tested Claude Code configs from an Anthropic hackathon winner - agents, skills, hooks, rules, and legacy command shims evolved over 10+ months of intensive daily use
Upstash Context7 MCP server for up-to-date documentation lookup. Pull version-specific documentation and code examples directly from source repositories into your LLM context.
Comprehensive startup business analysis with market sizing (TAM/SAM/SOM), financial modeling, team planning, and strategic research
Semantic search for Claude Code conversations. Remember past discussions, decisions, and patterns.