codex-advisor
调用 OpenAI Codex 获取第二意见,批判性评估后三分类展示给用户
Discover Research skills, compare source repositories and read the instructions for each workflow.
调用 OpenAI Codex 获取第二意见,批判性评估后三分类展示给用户
规划工作流 - 从想法到实现计划的结构化流程。通过迭代细化单个 Markdown 文档将模糊想法转化为清晰实现计划。
记忆库 - 跨会话知识持久化管理。作为项目上下文的唯一真实来源。
响应指南 - 简洁响应 + 按需提示词增强。核心铁律:简洁优先,保真原意,禁止扩展范围。
基础原则 - AI 助手的核心思维原则和指令框架概述。包含系统思维、辩证思维、创新思维和批判思维四大核心原则。
知识召回技能 - 从 Project CLAUDE.md、User CLAUDE.md 和 Memory MCP 查询历史知识
快捷命令系统 - 快捷命令定义和使用指南。定义以 ! 结尾的短命令触发特定响应。
BA 协作 - 与业务分析师协作的专业化工作流。帮助 BA 编写高质量用户故事和验收标准。
测试指南 - 测试设计和实现的原则与最佳实践。包含测试设计模板和断言最佳实践。
质量标准 - 代码质量、设计模式和反模式的统一指南。包含 SOLID 原则、代码异味识别和最佳实践。
Analyze and explain TimeGPT forecast results in plain English. Generates executive summaries with driver analysis. Use when stakeholders need forecast explanations, board presentations, or compliance documentat...
Detects arbitrage opportunities between Polymarket and Kalshi prediction markets. Use when a user wants to find price discrepancies for the same event on different platforms. Trigger with "find arbitrage", "det...
Generate production-ready forecasting experiments with StatsForecast and TimeGPT. Use when setting up model benchmarking or cross-validation. Trigger with 'scaffold experiment' or 'compare models'.
Generate production-ready MCP server implementations from PRD tool specifications with schema validation, error handling, and testing infrastructure. Use when building MCP servers for Nixtla plugins, implementi...
Produces verified datasets, verified evaluation results, and a deployable contract bundle for a workflow. Use when you need provable correctness at data and evaluation boundaries. Trigger with 'verify workflow'...
Forecasts orderbook depth and spreads to optimize trade execution timing. Use when needing to estimate market liquidity for large orders. Trigger with "forecast liquidity", "predict orderbook", "estimate depth"...
Transforms prediction market data to Nixtla format (unique_id, ds, y). Maps arbitrary column names to required schema. Validates date and numeric types. Use when preparing prediction market datasets for Nixtla...
Audits Nixtla library usage and recommends cost-effective routing strategies. Scans TimeGPT, StatsForecast, and MLForecast patterns, identifies cost optimization opportunities, generates comprehensive usage rep...
Analyze Nixtla baseline forecasting results (sMAPE/MASE on M4 or other benchmark datasets). Use when the user asks about baseline performance, model comparisons, or metric interpretation for Nixtla time-series...
Installs and updates Nixtla Skills in current project using nixtla-skills CLI. Manages skill installation, updates existing skills, and guides through setup process. Activates when user needs to install Nixtla...
Analyze and transform code for TimeGPT-1 to TimeGPT-2 migration. Use when upgrading TimeGPT version. Trigger with 'migrate to TimeGPT-2' or 'upgrade TimeGPT'.
Analyze market risk with VaR, volatility, and position sizing using forecast data. Use when assessing investment risk. Trigger with 'analyze market risk' or 'calculate VaR'.
Transform forecasting experiments into Airflow/Prefect pipelines with monitoring. Use when deploying forecasts to production. Trigger with 'generate pipeline' or 'create Airflow DAG'.
Lists all installed Nixtla Skills and provides guidance on which skill to use for specific tasks. Scans skills directory, reads frontmatter, outputs formatted index with categories and usage recommendations. Ac...
The default order uses GitHub repository stars from our indexed data. Stars belong to the source repository and may be shared by multiple skills. They indicate repository interest, not skill installs or an independent quality score.