浏览所有 Claude 技能

Auto-Claude Build System

Orchestrates an autonomous multi-agent pipeline to plan, implement, and validate software features from specifications.

AC Spec Parser

Parses and validates project specifications to bridge the gap between human requirements and autonomous coding execution.

Agent-Native Architecture

Build autonomous agents by defining features as outcomes in prompts rather than hard-coding workflow logic.

History Pruner

Optimizes local storage by pruning bloated Claude Code conversation history and truncating large tool outputs.

AC Test Generator

Automates the creation of comprehensive test suites following Test-Driven Development principles to ensure high code quality and feature coverage.

Claude Cost Optimization

Monitors and reduces Anthropic API expenses through advanced token tracking and implementation of optimization patterns like prompt caching and effort selection.

Documentation Reviewer

Reviews technical documentation for factual accuracy, validates code examples, and identifies broken links.

DrugBank Database Integration

Accesses and analyzes comprehensive pharmaceutical data, including drug properties, interactions, molecular targets, and chemical structures from DrugBank.

Gemini 3 Pro Advanced Features

Implements advanced Gemini 3 Pro capabilities including function calling, structured outputs, and context caching for production-grade AI applications.

AC Task Executor

Orchestrates autonomous coding tasks by managing feature queues and coordinating implementation, testing, and validation phases.

DOCX Document Processor

Automates the creation, editing, and analysis of Microsoft Word documents with support for tracked changes and scientific visualizations.

Karpenter EKS Autoscaling

Automates intelligent Kubernetes node provisioning and cost optimization for Amazon EKS using Karpenter.

Multi-AI Debugging Council

Orchestrates a multi-agent debugging workflow using Claude, Gemini, and Codex to perform advanced root cause analysis and automated fix generation.

Stable Baselines3 RL Suite

Implements production-ready reinforcement learning algorithms using a unified, scikit-learn-style API for efficient agent training and evaluation.

Agent Organizer

Orchestrates complex multi-agent workflows by decomposing tasks, delegating to specialized skills, and managing execution through to delivery.

Multi-AI Research & Analysis

Conducts deep, multi-perspective technical audits and research by orchestrating Claude, Gemini, and Codex AI systems.

Testing Validator

Validates Claude Code skill functionality through automated example execution, integration checks, and systematic regression testing.

Test Writing Expert

Generates comprehensive unit, integration, and E2E tests using industry-standard patterns and robust edge case detection.

Analyze-Verify 150 Protocol

Verifies critical claims and factual assertions through source-backed evidence and recursive confidence-building loops.

Anthropic Docs Updater

Automates the synchronization and maintenance of the anthropic-expert skill by tracking the latest Anthropic API and SDK documentation.

Checkpoint Manager

Manages state snapshots and automated rollbacks to enable safe experimentation during autonomous coding sessions.

Agentic Workflow Pattern

Implements a standardized multi-agent pipeline to orchestrate complex software development tasks through autonomous sub-agents.

Maestro Spec-Driven Development

Orchestrates spec-driven development workflows and multi-phase task management within the Gemini CLI environment.

EKS Troubleshooting & Debugging

Provides expert diagnostics and remediation steps for Amazon EKS cluster issues, pod failures, and networking problems.

TDD Test Generator

Generates comprehensive test suites following Test-Driven Development principles to ensure robust feature coverage and automated validation.

Skill Creator

Standardizes the creation and optimization of specialized AI skills to extend Codex's capabilities with domain-specific knowledge.

Hypogenic Scientific Hypothesis Discovery

Automates scientific hypothesis generation and testing from tabular datasets using LLMs and literature integration.

Codex Autonomous Execution

Enables autonomous, hands-off task execution using the Codex CLI to implement features, fix bugs, and refactor code without constant approval prompts.

Feature Dependency & Path Analyzer

Maps complex feature dependencies and calculates critical paths to determine the most efficient implementation order for software projects.

Security Sandbox

Safeguards autonomous coding operations using command validation, allowlists, and real-time execution hooks.