모든 Claude 스킬 탐색

OpenShift Regression Monitor

Analyzes and tracks software regressions across OpenShift releases to monitor component health and triage efficiency.

OVS Network Analyzer

Analyzes Open vSwitch data from sosreports to troubleshoot networking issues, packet drops, and flow performance.

Resource Analysis for sosreport

Analyzes system resource usage data from sosreport archives to diagnose performance bottlenecks and resource exhaustion.

LVMS Storage Analyzer

Analyzes LVMS must-gather data to diagnose and remediate storage issues in OpenShift and Kubernetes environments.

Sosreport Logs Analysis

Analyzes system and application log data from sosreport archives to identify root causes of system failures, crashes, and performance issues.

Prow Job Test Failure Analyzer

Streamlines CI/CD debugging by automatically analyzing Prow test failures through log inspection, artifact scanning, and cluster event correlation.

System Design Interrogation

Guides architectural planning through structured questioning to ensure scalability, security, and coherence before implementation.

AI Defense-in-Depth

Implements a robust 8-layer security architecture to harden AI pipelines and protect LLM integrations from end-to-end.

Superpowers Workflow Orchestrator

Enforces mandatory protocols for skill discovery, brainstorming-first workflows, and task tracking to ensure consistent AI output quality.

Type Safety & Validation

Implements rigorous end-to-end type safety and runtime validation using Zod, tRPC, and Prisma for robust TypeScript and Python applications.

Context Engineering

Optimizes LLM context windows through strategic positioning, token budgeting, and attention-aware design to maximize signal and reduce costs.

Context Compression

Optimizes Claude's memory by compressing conversation history while preserving critical task data and session intent.

Golden Dataset Curation

Automates the curation and quality validation of high-fidelity evaluation datasets using multi-agent analysis pipelines.

RFC 9457 API Error Handling

Standardizes HTTP API error responses using the machine-readable RFC 9457 Problem Details format for FastAPI and backend services.

HyDE Semantic Retrieval

Enhances RAG retrieval accuracy by generating hypothetical answer documents to bridge vocabulary gaps in semantic search.

Security Scanning

Automates vulnerability detection for dependencies, source code, and containers using industry-standard security tools.

DevOps & Deployment Patterns

Automates the creation of production-grade CI/CD pipelines, containerized environments, and Kubernetes-ready infrastructure.

LangGraph Supervisor Pattern

Coordinates complex multi-agent workflows using a central supervisor to route tasks among specialized LangGraph workers.

Golden Dataset Management

Protects and maintains high-quality test datasets for AI/ML systems through automated backup, restoration, and integrity validation.

Subagent-Driven Development

Automates the execution of multi-step implementation plans by dispatching fresh subagents for each task followed by iterative code reviews.

Unit Testing Patterns

Implements robust unit testing patterns and best practices for TypeScript and Python using the AAA pattern and optimized fixtures.

Structured Plan Execution

Executes multi-step implementation plans in controlled batches with built-in review checkpoints and mandatory verification.

GitHub Issue Architect

Generates comprehensive GitHub issues with embedded TDD plans and autonomous agent instructions for full pull request lifecycle management.

Handling PR Comments

Automates the systematic discovery, resolution, and response to pull request feedback from AI bots and human reviewers.

System Resilience Patterns

Implements production-grade fault tolerance patterns like circuit breakers, bulkheads, and retries for robust distributed systems and LLM integrations.

Brainstorming Extension: Design Review Gate

Automates a multi-agent design review process immediately following the creation of design documents to ensure technical and product readiness.

Condition-Based Waiting

Eliminates flaky tests and race conditions by replacing arbitrary timeouts with smart, deterministic condition polling.

Provider Scorecard

Evaluates and tracks data enrichment provider performance, costs, and quality metrics to optimize vendor selection and routing.

LLM Cache Cost Tracking

Monitors LLM expenditures and analyzes cache efficiency using Langfuse observability for complex multi-agent systems.

OpenShift CNTRLPLANE Jira Assistant

Automates Jira issue creation for the OpenShift Control Planes project with standardized field mapping and version normalization.