Build RAG pipelines for document Q&A and chatbots by chunking large docs, generating embeddings, storing in vector DBs, and retrieving context to reduce hallucinations. Engineer and optimize LLM prompts using chain-of-thought, few-shot examples, constitutional AI, meta-prompting, and validation workflows.
Provides chunking strategies for RAG systems. Generates chunk size recommendations (256-1024 tokens), overlap percentages (10-20%), and semantic boundary detection methods. Validates semantic coherence and evaluates retrieval precision/recall metrics. Use when building retrieval-augmented generation systems, vector databases, or processing large documents.
Provides workflows to write, debug, and optimize prompts for LLMs, including few-shot example selection, chain-of-thought structuring, system prompt design, and template composition. Use when the user asks to write or improve a prompt, wants help with few-shot examples, chain-of-thought, system prompts, prompt templates, or asks how to get better results from an LLM.
Implements document chunking, embedding generation, vector storage, and retrieval pipelines for Retrieval-Augmented Generation systems. Use when building RAG applications, creating document Q&A systems, or integrating AI with knowledge bases.
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.
A modular plugin system of reusable skills, agents, and commands for automating development tasks in Claude Code
Listed on:
Developer Kit for Claude Code teaches Claude how to perform development tasks in a repeatable way across multiple languages and frameworks. Built as a modular marketplace, you can install only the plugins you need.
# Install from marketplace (recommended)
/plugin marketplace add giuseppe-trisciuoglio/developer-kit
# Or install from local directory
/plugin install /path/to/developer-kit
Claude Desktop: Enable Skills in Settings
Developer Kit is organized as a modular marketplace with 11 independent plugins:
plugins/
├── developer-kit-core/ # Core agents/commands/skills (required)
├── developer-kit-java/ # Java/Spring Boot/LangChain4J/AWS SDK/GraalVM Native Image
├── developer-kit-typescript/ # NestJS/React/React Native/Next.js/Drizzle/Monorepo
├── developer-kit-python/ # Python development/AWS Lambda
├── developer-kit-php/ # PHP/WordPress/AWS Lambda
├── developer-kit-aws/ # AWS CloudFormation/AWS Architecture
├── developer-kit-ai/ # Prompt Engineering/RAG/Chunking
├── developer-kit-devops/ # Docker/GitHub Actions
├── developer-kit-project-management/ # LRA workflow/Meetings
├── developer-kit-tools/ # Additional development tools and MCP integrations
└── github-spec-kit/ # GitHub specification integration
Current marketplace totals: 116 skills, 43 agents, and 44 commands across the 11 plugin manifests.
Language plugins (Java, TypeScript, Python, PHP) include coding rules (rules/ directory) that auto-activate via globs: path-scoped matching to enforce naming conventions, project structure, language best practices, and error handling patterns. They also include LSP server configurations (.lsp.json) for real-time code intelligence, diagnostics, and navigation features.
The Developer Kit follows a systematic development workflow that ensures high-quality, well-documented features from idea to implementation:
Command: /devkit.brainstorm [idea-description]
Start here when you have a new feature idea. This command guides you to create a functional specification (WHAT the system should do, not HOW):
Output: Functional specification saved to docs/specs/YYYY-MM-DD--feature-name.md
Example:
/devkit.brainstorm Add user authentication with JWT tokens
Next step: After specification, continue with /devkit.spec-to-tasks
Command: /devkit.spec-to-tasks [--lang=java|spring|typescript|nestjs|react|python|general] [spec-file]
Converts the functional specification into atomic, executable tasks:
Output: Task list saved to docs/specs/[id]/tasks/TASK-XXX.md with complexity scores
Example:
/devkit.spec-to-tasks docs/specs/001-user-auth/
/devkit.spec-to-tasks --lang=spring docs/specs/001-user-auth/
Next step: Review task complexity and manage tasks with /devkit.task-manage
Command: /devkit.task-manage --action=[list|split|add|mark-optional|update|regenerate-index] [options]
Manage tasks after generation to ensure they're appropriately sized and prioritized:
AWS infrastructure and CloudFormation expertise
External tools integration skills for CLI utilities, APIs, and third-party services
Core agents and commands required by all Developer Kit plugins
Project management and workflow commands
Python development capabilities
npx claudepluginhub giuseppe-trisciuoglio/developer-kit --plugin developer-kit-aiCore agents and commands required by all Developer Kit plugins
Spec-driven development workflow system with structured phases: Requirements → Design → Tasks → Implementation
LLM application development with RAG, embeddings, LangChain, and prompt engineering
Production-ready Claude Code configuration with role-based workflows (PM→Lead→Designer→Dev→QA), safety hooks, 44 commands, 19 skills, 8 agents, 43 rules, 30 hook scripts across 19 events, auto-learning pipeline, hook profiles, and multi-language coding standards
Expert Prompt Engineer with Context Engineering, Meta-Prompting, Chain-of-Thought, Few-Shot, Agent Design, 50+ Template Library, and A/B Testing
PROJECT.md-first autonomous development with hybrid auto-fix documentation. 8-agent pipeline, auto-orchestration, docs auto-update on commit (true vibe coding). Knowledge base system with 90% faster repeat research. Strict mode enforces SDLC best practices automatically. Works for ANY Python/JavaScript/TypeScript/Go project.