すべてのClaudeスキルを閲覧

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.

Reflection Craft

Transforms work sessions into structured, actionable learnings and testable rules to improve development workflows.

Langdock API Operations

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

Langfuse Prompt Management

Manages the complete lifecycle of Langfuse LLM prompts, including version control, deployment labels, and side-by-side version comparisons.

Bead Issue Tracker Importer

Automates the importation of structured BEADS.md project plans into the bd issue tracker with full dependency mapping.

Consolidation Craft

Automates the implementation of captured insights and behavioral improvements into Claude Code plugins.

Agentic Optimization Loop

Automates the iterative refinement of AI agent performance through contract-driven evaluation and multi-lever optimization protocols.

Backend Readiness Framework

Conducts systematic production-readiness audits of backend systems across security, reliability, and performance layers.

Agentic Optimization Target

Defines precise optimization goals and regression guardrails for autonomous agent loops using normalized 0-1 scoring.

Langfuse Prompt Management

Streamlines the lifecycle of LLM prompts by enabling versioning, deployment, and management within the Langfuse observability platform.

Alpha Production Readiness Trace

Evaluates software readiness for alpha release by tracing end-to-end user flows from the UI to the backend to identify functional gaps.

Langfuse Agent Advisor

Provides strategic guidance for evaluating and optimizing AI agents using Langfuse traces and data-driven iteration loops.

YouTrack Project Management & Reporting

Automates YouTrack project management tasks, including epic health checks, weekly reporting, and Linear issue synchronization.

OpenAI Widget Development

Streamlines the creation of interactive UI components and widgets for the OpenAI Apps SDK using the MCP skybridge protocol.

Langfuse Score Analytics

Analyzes and visualizes LLM quality scores, trends, and regressions within the Langfuse observability platform.

Plan Polish

Converts rough project concepts into implementation-ready Technical Design Documents optimized for autonomous coding agents.

Langfuse Trace Analysis

Diagnoses and resolves LLM workflow issues by performing structured root-cause analysis on Langfuse traces.

Langfuse Instrumentation Setup

Instruments Python LLM pipelines with Langfuse tracing, observability patterns, and performance scoring.

Discovery Craft

Extracts repeatable work patterns and generates modular component specifications for Claude Code plugins.

OpenAI App Widget Patterns

Provides standardized UI patterns and implementation guidance for building interactive widgets within the OpenAI Apps SDK.

Langfuse Data Retrieval

Extracts and filters Langfuse observability traces to provide surgical debugging insights directly within the Claude Code environment.

SwiftUI UI Patterns

Streamlines SwiftUI development by providing best practices, reusable UI patterns, and optimized component architectures.

Linear Task & Planning Toolkit

Manages Linear issues and daily planning workflows directly within Claude Code to streamline task execution and reporting.

Bead Review Auditor

Performs adversarial QA audits on bead-based task decompositions to ensure reliable autonomous agent execution.

Requirement Clarifier

Ensures implementation accuracy by identifying ambiguous requests and asking targeted, low-friction clarifying questions before starting work.

UX Evaluator

Evaluates user experience, assesses production readiness, and identifies UI-to-backend gaps through structured auditing workflows.

MCP Server Architecture

Provides architectural guidance and implementation patterns for building Model Context Protocol (MCP) servers with the OpenAI Apps SDK.