모든 Claude 스킬 탐색

GitHub Actions Templates

Generates production-ready GitHub Actions workflows for automated testing, building, and multi-environment deployment.

Async Python Patterns

Implements high-performance asynchronous Python patterns using asyncio and concurrent programming techniques.

ShellCheck Configuration

Configures and optimizes ShellCheck static analysis to ensure shell script quality, portability, and security.

Error Handling Patterns

Implements robust error handling strategies and resilience patterns across multiple programming languages to build fault-tolerant applications.

Evidence-Based Task Verification

Enforces a rigorous protocol requiring empirical evidence and command output before any task is marked as complete or successful.

Brainstorming & Design Architect

Refines rough ideas into fully-formed technical designs through iterative questioning and alternative exploration.

Prometheus Configuration

Configures Prometheus for comprehensive metric collection, infrastructure monitoring, and proactive alerting.

TypeScript Advanced Types Mastery

Master TypeScript's complex type system using generics, conditional types, and mapped types to build robust, type-safe applications.

Python Performance Optimization

Profiles and optimizes Python code to eliminate bottlenecks, reduce memory overhead, and accelerate execution using advanced profiling tools and best practices.

Condition-Based Waiting

Eliminates flaky tests by replacing arbitrary delays with intelligent condition polling for asynchronous state changes.

Python Packaging & Distribution

Streamlines the creation of distributable Python packages using modern standards like pyproject.toml and automated PyPI publishing workflows.

Advanced Debugging Strategies

Implements systematic diagnostic methodologies and profiling tools to identify, isolate, and resolve complex software bugs across any technology stack.

Async Python Patterns

Implements high-performance Python applications using asyncio, concurrent programming patterns, and non-blocking I/O strategies.

Python Testing Patterns

Implements comprehensive Python testing strategies using pytest, fixtures, mocking, and test-driven development best practices.

Verification Before Completion

Enforces a strict evidence-based workflow that requires fresh command output before any task can be claimed as complete.

Verification Before Completion

Enforces rigorous verification protocols to ensure all coding tasks are validated with empirical evidence before marking them as complete.

LLM Evaluation Suite

Implements comprehensive evaluation strategies for LLM applications using automated metrics, human feedback, and rigorous benchmarking.

Cross-Review Multi-Model Workflow

Implements an iterative, multi-model code review process that separates coding and auditing tasks between Claude and Codex to ensure production-grade quality.

Survey Report Builder

Automates the generation of professional Quarto PDF reports and PowerPoint presentations from CSV survey data.

Langdock API Integration

Integrates Langdock's AI assistants, knowledge retrieval, and RAG pipelines into custom applications using Python or Node.js.

Compound Improvement Cycle

Establishes a proactive improvement framework to capture learnings and encode patterns during development, ensuring every task compounds into future efficiency.

Compound Reflection Craft

Transforms development sessions into structured, actionable learnings and testable rules to continuously improve AI-driven workflows.

Behavioral Design Toolkit

Applies behavioral psychology and decision science principles to optimize user flows and improve product adoption.

Langfuse Annotation Manager

Manages human annotations and manual scoring workflows for Langfuse LLM traces directly from Claude.

Langfuse Experiment Runner

Facilitates LLM experiment execution and prompt evaluation using Langfuse datasets and automated LLM-as-judge scoring.

Behavior Mapping & Tracking

Maps high-level goals to the specific daily behaviors that produce them to create actionable, data-driven tracking systems.

Langfuse Dataset Setup

Automates the creation and configuration of Langfuse datasets for LLM evaluation and observability workflows.

Langfuse Session Analysis

Provides deep insights into multi-turn LLM conversations by analyzing and debugging Langfuse trace sessions.

Langdock API Operations

Manage Langdock assistants, knowledge folders, and usage analytics through specialized API integrations and CLI tools.

Assistant Prompt Craft

Generates expertly structured German system prompts and tool integration instructions for Langdock assistants.