探索我们完整的 Claude 技能集合,扩展 AI 代理的能力。
Generates detailed Product Requirement Plans (PRPs) that enable high-success, one-pass feature implementation through deep codebase analysis and research.
Integrates and manages diverse LLM providers in PydanticAI with support for fallback models, streaming, and usage tracking.
Reviews iOS and macOS networking code to ensure robust URLSession implementations, proper error handling, and secure data transmission.
Reduces false positives in code reviews by enforcing a mandatory multi-step verification process before reporting findings.
Reviews Swift Testing code for modern framework patterns, macro usage, and asynchronous verification best practices.
Reviews WidgetKit code to ensure optimal timeline management, view composition, and performance across Apple platforms.
Validates Prometheus metrics implementation in Go applications to ensure optimal observability and performance.
Implements complex node-based UI patterns and interactive diagrams using React Flow and XYFlow.
Extracts architectural decisions and trade-offs from conversation transcripts to automate technical documentation workflows.
Identifies and fixes common implementation errors and architectural pitfalls when building PydanticAI agents.
Simplifies the creation of deterministic, recorded, and snapshot-based tests for PydanticAI agents and workflows.
Generates structured Architectural Decision Records using the MADR template to document technical choices and their impact.
Implements high-performance vector similarity search and embedding storage directly within SQLite databases.
Reviews Apple CloudKit implementations to ensure proper container setup, error handling, and data synchronization patterns.
Reviews Go source code to ensure idiomatic patterns, robust error handling, and concurrency safety.
Reviews Swift code for concurrency safety, memory management, and modern SwiftUI patterns to ensure high-quality iOS and macOS development.
Refines prose into professional, punchy communication by applying classical composition principles and eliminating linguistic clutter.
Processes external code review feedback using a verification-first methodology to ensure technical accuracy before implementation.
Orchestrates environment preparation, information gathering, and Git branch creation to begin development on a Jira ticket.
Automates hierarchical and tree-based node positioning for React Flow diagrams using the Dagre layout engine.
Automates comprehensive accessibility audits for web pages, source code, and design mockups based on WCAG 2.2 and WAI-ARIA standards.
Manages GitHub Projects (v2) workflows and items using the GitHub CLI integration.
Validates charmbracelet/wish SSH server implementations for security, middleware correctness, and session management.
Conducts specialized code reviews for Apple Watch applications to ensure optimal performance, battery efficiency, and platform-specific best practices.
Compares and scores multiple code implementations using a multi-phase LLM-as-judge framework to evaluate functionality, security, and quality.
Simplifies GTM implementations by providing expert guidance on tags, triggers, variables, and data layer configurations.
Parses and converts complex documents like PDFs, Word, and PowerPoint into structured, layout-aware data for AI and RAG pipelines.
Audits and evaluates AI agent codebases for compliance with the 12-Factor Agents methodology to ensure production-grade reliability.
Analyzes codebases for 12-Factor App methodology compliance to ensure cloud-native readiness and architectural scalability.
Streamlines the editing, querying, and management of scientific ontologies in the Open Biomedical Ontologies (OBO) format.
Scroll for more results...