모든 Claude 스킬 탐색

Metrics Performance Review

Analyzes tracked behaviors and outcomes to generate actionable insights and data-driven feedback loops.

Friction Audit

Systematically identifies and reduces friction in behavioral systems and workflows to improve consistency and efficiency.

Conduct Ad Research

Conducts in-depth digital advertising research and generates data-driven campaign strategy reports using real-time web search.

Skill Creator

Guides the development of modular, high-performance skills to extend Claude's capabilities with specialized knowledge and workflows.

Langfuse Dataset Manager

Manages Langfuse datasets for AI regression testing and golden set curation directly through the Claude Code CLI.

MCP Deployment & Testing for OpenAI

Streamlines the deployment and validation of MCP servers for ChatGPT integration using ngrok, MCP Inspector, and production-ready patterns.

MCP Server Builder

Streamlines the development of Model Context Protocol (MCP) servers with standardized patterns for TypeScript and Python integrations.

E2E Testing Patterns

Implements robust end-to-end testing suites using Playwright and Cypress to ensure application reliability and prevent regressions.

MCP Evaluation Framework

Evaluates Model Context Protocol (MCP) applications for product fit, value delivery, and user experience using automated persona-based walkthroughs.

Linear Workflow Manager

Streamlines personal task management and daily planning by integrating Linear's GraphQL API directly into your development environment.

Codex Code Review

Automates comprehensive code reviews, security audits, and pull request analysis using the Codex CLI to identify and fix quality issues.

MCP Authentication for OpenAI Apps SDK

Implements secure authentication patterns including OAuth 2.1 and API keys for Model Context Protocol (MCP) servers.

Langfuse Session Analysis

Analyzes multi-turn conversation flows and session-level metrics within Langfuse to debug user journeys and track LLM performance.

MCP Tool Design for OpenAI Apps SDK

Guides the creation of robust, secure, and well-documented MCP tools for the OpenAI Apps SDK using standardized schemas and behavioral hints.

Compound Reflection Craft

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

Compound Discovery Craft

Analyzes coding sessions to extract repeatable patterns and transform them into modular Claude Code components like skills, commands, or agents.

Langdock Action Patterns

Streamlines the creation of production-ready Langdock integration actions using standardized patterns for API authentication, request handling, and metadata formatting.

Work Meeting Toolkit

Streamlines the preparation of meeting agendas, stakeholder updates, and project status reports using live data from project management tools.

Langfuse Annotation Manager

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

Langfuse Agent Evaluator

Orchestrates end-to-end evaluation cycles for AI agents using Langfuse to identify performance regressions and generate actionable optimization reports.

Code Review Assistant

Provides structured, expert feedback on code changes to identify bugs, security risks, and quality improvements before merging.

Requirement Clarifier

Identifies ambiguities in user requirements and generates structured clarification questions to ensure precise project scoping.

Compound Improvement Cycle

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

Failure Diagnosis

Diagnoses barriers to progress by systematically analyzing target selection, strategic algorithms, and execution friction.

Goal Methodology & Habit Tracking

Provides evidence-based frameworks for setting, tracking, and optimizing personal goals and habits using data-driven behavioral psychology.

Evaluation Design

Designs structured evaluation frameworks for AI agents including metrics, datasets, and automated grading strategies.

Langfuse Session Analysis

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

German Business Communication

Drafts professional German business emails and project updates tailored for technical teams and AI startups.

E2E Testing Patterns

Implements robust end-to-end testing suites using Playwright and Cypress to ensure application reliability and prevent regressions.

Shodan Reconnaissance & Pentesting

Conducts comprehensive security reconnaissance and vulnerability discovery using Shodan's search engine, CLI, and API.