AIエージェントの能力を拡張するClaudeスキルの完全なコレクションをご覧ください。
Downloads YouTube transcripts and generates structured Markdown summaries with time-stamped key points.
Automates Claude Code task progression using intelligent confidence scoring to minimize manual interruptions during extended development workflows.
Provides a standardized framework and boilerplate for developing custom Claude Code skills with consistent structure.
Simplifies codebases by removing unnecessary abstractions, inlining single-use functions, and flattening deep logic nesting.
Analyzes existing SCSS and CSS codebases to identify variables, mixins, and utility classes for consistent styling.
Enables seamless interaction with Google Chat spaces to send notifications, list conversations, and manage messages directly through Claude.
Optimizes financial data pipelines by automatically filtering non-standard ticker symbols that cause API errors during sector lookups.
Implements a structured checkpointing system for connecting multiple Jupyter notebooks into robust, memory-efficient data pipelines.
Audits and optimizes marketing and operational copy for quality, clarity, and legal compliance.
Analyzes and optimizes cryptocurrency trading strategies to minimize fees on the Alpaca platform through direct pair rotations.
Manages separate development and production environments for private repository trading models and Colab training.
Implements a multi-stage validation system for algorithmic trading that filters signals through pattern-matching and risk-management gates.
Optimizes historical market data retrieval by eliminating redundant downloads through persistent caching and incremental gap-filling.
Accelerates financial correlation matrix computations using GPU-vectorized PyTorch operations and persistent SQLite caching.
Validates and assesses reinforcement learning trading models through systematic gating, backtesting, and walk-forward validation.
Optimizes Jupyter notebook workflows by preventing unnecessary kernel restarts when using the IPython autoreload extension.
Provides real-time visibility into silent universe selection phases by implementing standardized progress callbacks and notebook-friendly output.
Refactors Jupyter notebook code into reusable Python modules while preserving critical variable definitions and configuration.
Implements a 7-action space with integrated position sizing and small account simulation for reinforcement learning trading models.
Ensures quantitative accuracy in microscopy deconvolution by preserving original intensity relationships across image channels.
Automates the archival and quality classification of algorithmic trading models based on performance metrics and risk thresholds.
Corrects file path errors and API key configurations in Google Colab environments after repository extraction.
Optimizes PPO neural network dimensions to balance trading model capacity, inference speed, and hardware memory usage.
Integrates multi-agent Claude systems into algorithmic trading pipelines to optimize model training and manage live risk with automated oversight.
Optimizes financial data retrieval by caching market symbol data to reduce API latency and avoid rate limits during trading bot development.
Optimizes the visualization of sparse single-cell gene expression data by implementing alternative plotting patterns that prevent boxplot collapse.
Reorganizes Python projects into self-contained packages with internal configuration for maximum portability.
Automatically organizes messy invoices and receipts by extracting metadata, renaming files, and sorting them into tax-ready folder structures.
Implements high-performance FastAPI backends for OpenAI ChatKit with real-time SSE streaming and agent integration.
Systematically analyzes stack traces and application logs to identify root causes and implement reliable bug fixes.
Scroll for more results...