Data & AI

Platform inventory, strategy discovery, backtesting, and optimization workflows for this trading project. Use when asked about strategies, backtesting, or what's available.

Advanced persistent context management system for web development work that never loses context between Claude Desktop sessions. Automatically tracks, saves, and restores all work context, session history, decisions, and progress across multiple sessions and projects.

Use when spec is complete and you need detailed implementation tasks for LLM agents. Creates execution plans with exact file paths, complete code examples, and verification steps. Triggers: 'write plan', 'execution plan', 'implementation plan', 'break down into tasks', 'detailed steps'.

Masked arrays for robust handling of missing or invalid data, ensuring they are excluded from statistical and mathematical computations. Triggers: masked array, numpy.ma, missing data, invalid values, hard mask.

Guide to creating agent skills with proper structure and best practices

Build headless automation and agentic workflows with Google's Gemini CLI. Covers approval modes (default, auto_edit, yolo), file permission model, Edit vs WriteFile tool selection, smartEdit configuration, GEMINI.md context files, settings.json hierarchy, and MCP server integration. Use when building CI/CD pipelines with Gemini, debugging "0 occurrences found" edit failures, configuring --approval-mode for automation, creating long-running agents with --resume, or integrating external services via Model Context Protocol.

Perform SQL joins and multi-table analysis on DST data in DuckDB. Use whenresearch requires combining multiple tables on common dimensions (time, region).Provides patterns for common DST dimension joins and multi-table comparisons.

Use when starting a fine-tuning project to determine if fine-tuning is needed, or when evaluating whether a base model meets quality thresholds for a specific domain task

Examples and patterns for writing effective agent and skill descriptions. Use when crafting descriptions that serve as routing keys for Claude's invocation decisions.

Real-time collection and analysis of Claude Skills examples from multiple sources including GitHub repositories, blog posts, documentation, and community discussions. Use this skill when the user requests to gather examples, use cases, best practices, or implementation patterns for Claude Skills. Generates comprehensive markdown reports summarizing collected examples.

Naming conventions for planning documents in prompts/. Use when creating plans, PRDs, research reports, idea capture or other workflow documents. Triggers on (1) creating new planning documents, (2) naming PRDs or research reports, (3) questions about document organization in prompts/.

Search RAG database for relevant content. Use for semantic queries over processed documents, code, or papers.

Agent Lightning를 사용하여 AI 에이전트를 자동으로 최적화하는 방법을 제공합니다.

Comprehensive toolkit for creating, analyzing, and visualizing complex networks and graphs in Python. Use when working with network/graph data structures, analyzing relationships between entities, computing graph algorithms (shortest paths, centrality, clustering), detecting communities, generating synthetic networks, or visualizing network topologies. Applicable to social networks, biological networks, transportation systems, citation networks, and any domain involving pairwise relationships.

Guide Claude in writing efficient, idiomatic SWI-Prolog DCGs (Definite Clause Grammars) following best practices for single-pass parsing, character codes, pure declarative style, and accumulator patterns. Use when working with Prolog parsing tasks.

Generate and run tests for TypeScript/JavaScript code using Bun test runner. Use this skill when you need to write tests, check coverage, or debug test failures.

Systematic debugging framework ensuring root cause investigation before fixes. Includes four-phase debugging process, backward call stack tracing, multi-layer validation, and verification protocols. Use when encountering bugs, test failures, unexpected behavior, performance issues, or before claiming work complete. Prevents random fixes, masks over symptoms, and false completion claims.

Decode BSV transaction hex into human-readable format using WhatsOnChain API. Shows inputs, outputs, scripts, and transaction details.

Creates unique, production-grade frontend interfaces with exceptional design quality. Use when user asks to build web components, pages, materials, posters, or applications (e.g., websites, landing pages, dashboards, React components, HTML/CSS layouts, or styling/beautifying any web UI). Generates creative, polished code and UI designs that avoid mediocre AI aesthetics.

Research external APIs/services/libraries for feature implementation. Interviews user, researches options, confirms choice, gathers implementation notes. Creates .claude/plans file.