Explore our collection of Agent Skills to enhance your AI workflow.
Implements production-grade LLM-as-a-Judge techniques for evaluating AI outputs through rigorous scoring, pairwise comparisons, and bias mitigation.
Manages system design documentation and Architecture Decision Records (ADRs) within the Workbench CLI environment.
Standardizes the creation and organization of modular, domain-specific capabilities for Claude through structured guidelines and progressive disclosure patterns.
Orchestrates the creation of publication-quality AI and ML benchmark reports with high-resolution diagrams and professional PDF exports.
Generates structured, step-by-step implementation plans for repository code changes based on specified goals and codebase snapshots.
Integrates agent documentation and templates into existing repositories without overwriting or deleting current content.
Orchestrates complex, seven-act narrative arcs and validates structural coherence for high-quality documentary-style storytelling.
Generates cross-linked narrative rumors and lore artifacts to populate game worlds with immersive leads and connections.
Architects robust React applications using modern state patterns for Redux Toolkit, Zustand, Jotai, and TanStack Query.
Implements metric-based quality assurance and monitoring for Amazon Bedrock AI agents using built-in and custom evaluators.
Facilitates isolated UI component testing across major frontend frameworks using Playwright's experimental component features.
Detects legacy code patterns and provides strategic guidance for modernization and architectural consistency.
Design and implement multi-layered memory architectures for AI agents to ensure long-term state persistence and entity consistency.
Optimizes cloud infrastructure spending through rightsizing, FinOps principles, and automated resource management strategies.
Configures and manages Amazon EKS networking components including VPC CNI, load balancers, and network security policies.
Manages and compresses AI context usage to ensure seamless session continuity during long-running development tasks.
Manages Rust and Python interoperability using PyO3 and maturin to build, test, and validate high-performance cross-language bindings.
Extracts and formalizes recurring patterns and best practices from development experiences to enable continuous ecosystem improvement.
Manages automated documentation refreshes and session-based learning capture for terminal configuration plugins.
Optimizes software development workflows by analyzing task dependencies, identifying critical paths, and detecting bottlenecks using advanced MCP orchestration.
Performs precise code modifications using Abstract Syntax Tree (AST) manipulation to minimize syntax errors and maintain structural integrity.
Builds and manages fully managed RAG solutions using Amazon Bedrock for semantic search and document-based AI applications.
Organizes complex feature development by managing tracked GitHub epics, related issues, and project milestones.
Implements hook-based state machines to enforce sequential phases and quality gates in complex development workflows.
Provides a comprehensive command-line interface for managing autonomous coding tasks, spec creation, and QA validation within the Auto-Claude framework.
Manages the full lifecycle of autonomous coding sessions by automating initialization, state resumption, and iterative execution flows.
Improves code quality and team collaboration by applying structured review frameworks, checklists, and constructive feedback patterns.
Applies structural code changes using AST-aware edits to minimize syntax errors and maintain code integrity.
Triage incidents and debug applications by querying Datadog logs, metrics, and traces directly from your terminal.
Optimizes context window usage by prioritizing essential information and reducing token consumption during autonomous coding tasks.
Scroll for more results...