agentic-rag-ecommerce

Firecrawl gives AI agents and apps fast, reliable web context with strong search, scraping, and interaction tools. One install command sets up three skill segments: live CLI tools, app-integration build skills, and outcome-focused workflow skills. Route the reader to the right usage path after install.

Generate conventional commit messages - use when creating commits, writing commit messages, or asking for git commit help.

Create a decision history record in the history/ directory. Use before writing any implementation code for a new feature, architecture change, or significant technical decision.

Full development workflow from planning through deployment for AI Agent features. Use when developing new features, making significant architecture changes, or starting work on any non-trivial implementation.

Test execution workflow - run unit tests, linting, and type checking. Use when verifying code quality, running the full test suite, or checking before a commit.

Code review checklist - use for checking Python code quality, bugs, security issues, and best practices. Use when a user asks for a code review, needs to assess whether a change is safe to merge, or needs to review AI-agent code for production risk.

Debugging patterns and strategies - use when debugging issues, errors, or unexpected behavior. Use when a feature is failing, tests are failing, an AI/LLM workflow produces low-quality outputs, or a multi-step agent pipeline is hard to reason about.

Prompt writing best practices - use when creating or improving prompts for LLM agents. Use when creating or revising system prompts, tool instructions, or evaluator prompts, or when improving agent reliability, safety, or output consistency.

Terraform best practices for writing modular, secure, and maintainable infrastructure as code - use when creating or reviewing Terraform projects

Code review checklist - use for checking Python code quality, bugs, security issues, and best practices

Generate conventional commit messages - use when creating commits, writing commit messages, or asking for git commit help

Debugging patterns and strategies - use when debugging issues, errors, or unexpected behavior

Build RAG systems with LlamaIndex covering the full pipeline: data pre-processing, loading, chunking, indexing, storing, query transformation, retrieval, re-ranking, response synthesis, evaluation, and observability. Includes guidance on advanced techniques: hybrid search, re-ranking, ColBERT, ColPali, multimodal RAG, GraphRAG, and local models.

Prompt writing best practices - use when creating or improving prompts for LLM agents