Use this skill when performing exploratory data analysis, statistical testing, data visualization, or building predictive models. Triggers on EDA, pandas, matplotlib, seaborn, hypothesis testing, A/B test analysis, correlation, regression, feature engineering, and any task requiring data analysis or statistical inference.
Market data preparation including OHLCV resampling, gap handling, anomaly detection, normalization, and multi-source merging
Solana token data, PnL, risk scores, 1-second OHLCV, wallet analytics, and self-hosted swap execution via Raptor
对问卷原始数据进行全流程自动化分析，包括基础统计（频率分布 + 人口学概览）、 交叉分析（不同人群差异对比）和文本分析（开放题主题归纳）。 支持两种数据来源：用户提供本地 CSV/Excel 文件，或通过问卷 ID/名称从问卷系统直接下载（支持清洗）后分析。 输出 Markdown 摘要报告 + Word 分析报告（默认），支持转换为 Excel/TXT 格式。 当用户要求分析问卷数据、生成问卷调研报告、对比不同人群差异、 分析开放题文本内容时触发。即使用户没有明确说"问卷"，只要涉及 调研数据分析、用户反馈分析、满意度分析、NPS 分析等场景也应触发此 skill。 当用户说"下载并分析问卷"、"清洗问卷然后出报告"、"帮我下载问卷90450"、 "下载国内问卷数据"、"从问卷系统拉数据"等涉及下载+分析的场景时，也应触发。 确保在用户说"帮我分析这份问卷"、"分析一下不同性别的差异"、 "请结合文本题分析"、"下载问卷90450然后分析"、"清洗并导出问卷"等类似表达时使用。
Deploy agent to Databricks Apps using DAB (Databricks Asset Bundles). Use when: (1) User says 'deploy', 'push to databricks', or 'bundle deploy', (2) 'App already exists' error occurs, (3) Need to bind/unbind existing apps, (4) Debugging deployed apps, (5) Querying deployed app endpoints.
Enterprise Test Architecture (TEA) framework for quality engineering. Includes workflows for testing education (TEA Academy), risk-based test design, framework scaffolding, ATDD (Red-phase), CI/CD pipeline configuration, NFR (Non-functional) assessment, and quality auditing (0-100 scoring). Use for establishing or executing comprehensive testing strategies.
Structured content platform — GROQ queries, schema definitions, @sanity/client, Portable Text, image handling, real-time listeners, mutations, TypeGen
Pinecone serverless vector database -- index management, vector operations, metadata filtering, namespaces, hybrid search, inference API
Qdrant vector database -- collection management, point operations, payload filtering, named vectors, quantization, recommendations, snapshots
Firebase Data Connect integration for GraphQL-based data access with PostgreSQL. Use when building GraphQL schemas, queries, mutations, or integrating Firebase Data Connect with Angular applications. Supports type-safe generated SDKs, real-time subscriptions, and server-side data validation.
Use the Repomix MCP server to package codebase into consolidated files for AI analysis, search file contents, and understand project structure; essential for comprehensive codebase analysis and context gathering.
Use when launching OCI compute instances, troubleshooting out-of-capacity or boot failures, optimizing compute costs, or handling instance lifecycle. Covers shape selection, capacity planning, service limits, and production incident resolution.
Use when creating Autonomous Databases, troubleshooting connection failures, managing PDBs, or optimizing database costs. Covers connection string confusion, password validation errors, stop/start cost traps, clone type selection, and backup retention gotchas.
Deploy agent to Databricks Apps using DAB (Databricks Asset Bundles). Use when: (1) User says 'deploy', 'push to databricks', or 'bundle deploy', (2) 'App already exists' error occurs, (3) Need to bind/unbind existing apps, (4) Debugging deployed apps, (5) Querying deployed app endpoints.
Use when managing Oracle Autonomous Database on OCI, troubleshooting performance issues, optimizing costs, or implementing HA/DR. Covers ADB-specific gotchas, cost traps, SQL_ID debugging workflows, auto-scaling behavior, and version differences (19c/21c/23ai/26ai).
DEX orderflow analysis, trade classification, buyer/seller pressure, and microstructure signals for Solana tokens
Pre-execution Solana transaction streaming via Jito ShredStream, Shyft RabbitStream, and Triton Deshred
Architecture of the Dolos processing pipeline — WorkUnit lifecycle, executor modes, CardanoWorkUnit variants, WorkBuffer state machine, and sequencing. Reference when debugging execution ordering, understanding phase boundaries, or adding new work unit types.
SDK for ingesting data into Deeplake managed tables. Use when users want to store, ingest, or query data in Deeplake.
Redux Toolkit patterns for complex client state. Use when managing enterprise-scale state, needing DevTools, entity normalization, or RTK Query for data fetching.
Use when managing Oracle Autonomous Database on OCI, troubleshooting performance, optimizing costs, or implementing HA/DR. ADB-specific gotchas, cost traps, SQL_ID debugging workflows, auto-scaling behavior, and version differences (19c/21c/23ai/26ai). Keywords: ADB, Autonomous Database, ECPU, auto-scaling, SQL_ID, wait events, ORA- errors, wallet, BYOL.
Apollo Client GraphQL patterns - useQuery, useMutation, cache management, optimistic updates, subscriptions
