探索我们完整的 Claude 技能集合,扩展 AI 代理的能力。
Orchestrates structured multi-perspective technical debates using adversarial AI subagents to evaluate architectural trade-offs and technology choices.
Performs comprehensive, multi-perspective technical specification reviews using parallel AI subagents to ensure project feasibility.
Transforms specification documents into structured GitHub issue hierarchies using automated draft generation and the GitHub CLI.
Guides users through a structured requirement clarification process to eliminate ambiguity before technical documentation begins.
Validates and debugs Claude Code hooks through unit testing, direct payload invocation, and headless CLI integration.
Verifies real-time API statuses, library versions, and documentation to ensure code implementations are current and secure.
Standardizes the creation of new Claude Code skills by enforcing project patterns, naming conventions, and structural best practices.
Enforces a strict Red-Green-Refactor cycle to ensure all production code is verified by failing tests first.
Generates domain-specific reference documents, architecture specifications, and strategic guides for software projects.
Enforces a rigorous, evidence-based methodology to identify root causes and implement reliable fixes for complex software bugs.
Audits Algorand smart contracts for 11 critical security vulnerabilities, including rekeying attacks and unchecked transaction fields.
Automates the creation and verification of isolated Git worktrees for safe, parallel feature development.
Extracts and analyzes YouTube video transcripts to provide actionable insights, technical concepts, and project-specific recommendations.
Automates dotfile management and templating using Dotter to streamline environment configurations across multiple systems.
Automates web browser interactions, end-to-end testing, and UI verification using the Playwright framework.
Refines and humanizes AI-generated text by identifying and removing common linguistic markers, puffery, and technical artifacts.
Standardizes code implementation through language-specific patterns, best practices, and automated Git workflows.
Orchestrates a specialized three-phase TDD pipeline using AI subagents for testing, implementation, and mandatory code review.
Processes code review feedback through technical verification and objective evaluation to ensure high-quality, logic-driven implementations.
Enforces strict, evidence-based verification protocols before any task is marked as complete or fixed.
Verifies real-time API documentation, library versions, and architectural best practices to ensure code accuracy and security.
Standardizes the creation and optimization of specialized Claude Code Skills and reusable AI coding patterns.
Facilitates collaborative design sessions to transform rough ideas into structured implementation plans through iterative dialogue and alternative exploration.
Standardizes the creation and maintenance of specialized Claude Code skills and reusable coding patterns.
Synthesizes diverse technical perspectives into unified architectural decisions using the F-thread multi-agent fusion pattern.
Employs a rigorous, evidence-based approach to identify and resolve root causes of software bugs and test failures.
Automates web browsers for end-to-end testing, UI verification, and screen capture using the Playwright framework.
Resolves codebase ambiguities and defines automated testing strategies before moving from exploration to implementation.
Facilitates a rigorous, evidence-based debugging workflow using automated investigation loops and regression-first testing.
Orchestrates complex software implementations by managing specialized subagents with mandatory TDD enforcement and multi-stage review cycles.
Scroll for more results...