rag-implementation
Build production-grade RAG systems using vector databases, semantic search, and LangGraph to ground LLMs in external knowledge.
Discover reusable agent skills, browse implementation details, and find the right skill for your workflow.
623 skills found
Build production-grade RAG systems using vector databases, semantic search, and LangGraph to ground LLMs in external knowledge.
Evaluate code generation models using BigCode Evaluation Harness. Benchmarks include HumanEval, MBPP, and MultiPL-E with pass@k metrics for multi-language coding models.
Generate production-ready Cloudscape Design System React + TypeScript UI code, components, and scaffolds with accessibility, responsive patterns, and robust state handling.
Run Semgrep static analysis scans on codebases using parallel subagents, multi-language detection, and Pro-enabled cross-file taint tracking.
Retrieve current, source-backed technical information using MCP tools to resolve queries about libraries, APIs, SDKs, and evolving tech ecosystems.
Build Claude Code extensions: skills, agents, hooks, plugins, and slash commands. Includes builder agents for autonomous component creation and structure management.
Creates and edits Excel spreadsheets with professional formatting, formulas, and financial modeling standards using openpyxl and pandas.
Efficiently manage git worktrees with automated file synchronization, background task execution, and CLI-based workspace orchestration.
Manage Supabase authentication, including user sign-up, sign-in, session management, and admin-level user lifecycle operations via the REST API.
Pre-execution security guardrails for AI agents. Validates shell commands and file reads against 400+ security patterns to block destructive operations, credential theft, and unauthorized system access.
AWS CloudFormation skill for infrastructure as code, automated stack management, template authoring, drift detection, and troubleshooting across AWS environments.
Optimize agent context windows through KV-caching, observation masking, summarization-based compaction, and context partitioning to reduce costs and latency.