Build orchestration pipelines with idempotency.

Monitor and troubleshoot dual-pipeline data collection systems on GCP. This skill should be used when checking pipeline health, viewing logs, diagnosing failures, or monitoring long-running operations for data collection workflows. Supports Cloud Run Jobs (batch pipelines) and VM systemd services (real-time streams).

Follow these patterns when implementing data pipelines, ETL, data ingestion, or data validation in OptAIC. Use for point-in-time (PIT) correctness, Arrow schemas, quality checks, and Prefect orchestration.

Process JSON with jq and YAML/TOML with yq. Filter, transform, query structured data efficiently. Triggers on: parse JSON, extract from YAML, query config, Docker Compose, K8s manifests, GitHub Actions workflows, package.json, filter data.

Set up database replication for high availability and disaster recovery. Use when configuring master-slave replication, multi-master setups, or replication monitoring.

Documentation of available data science libraries (scipy, numpy, pandas, sklearn) and best practices for statistical analysis, regression modeling, and organizing analysis scripts. **CRITICAL:** All analysis scripts MUST be placed in reports/{topic}/scripts/, NOT in root scripts/ directory.

Data science and analytics expertise for statistical analysis, machine learning pipelines, data governance, business intelligence, predictive modeling, and analytics strategy. Use when building ML models, analyzing data, creating dashboards, or designing data architectures.

Connect your own data source to replace the demo unicorns data. Use when the user wants to use their own database URL or CSV file instead of the sample data. Triggers on requests to connect database, import CSV, change data source, use own data, or switch from demo data.

This skill should be used when reading any tabular data file (Excel, CSV, Parquet, ODS). It automatically detects and fixes common data issues including multi-level headers, encoding problems, empty rows/columns, and data type mismatches. Returns a clean DataFrame ready for analysis with zero user intervention.

For data

Implementing comprehensive validation rules across database, application, and pipeline layers to ensure data integrity.

Creating effective data visualizations using charts, graphs, and visual representations to communicate insights clearly and accurately following Tufte and Few principles.

Provides expert design guidance for creating truthful, clear, beautiful data visualizations. Focuses on **DESIGN DECISIONS ONLY**—chart selection, color strategy, visual encoding, and validation. Assumes data is accurate and prepared. Auto-activates when user mentions: data viz, dashboard, chart type, visualization, infographic

专业数据可视化专家，精通现代图表库、仪表板设计和交互式数据展示。能够将复杂数据转化为直观、美观且富有洞察力的可视化作品。

Build mathematically correct, visually prominent data visualizations for time-series charts. Use this skill when creating charts with mathematical overlays (trendlines, patterns, indicators), fixing visual artifacts (wavy lines, domain mismatches), or validating chart correctness. Focuses on technical correctness and progressive validation, not aesthetic design.

Create visualizations that Seaborn users, Tufte readers, and everyone else will love. Marry NYT Graphics rigor with MoMA aesthetics, Nike energy, and On Kawara precision.

Create publication-quality plots and visualizations using matplotlib and seaborn. Works with ANY LLM provider (GPT, Gemini, Claude, etc.).

>

Role assignment for Claude Agent #1 - Database schema architect for Lead Hunter Prime. Build ONLY database schema (11 tables, RLS policies, seed data). Do NOT build APIs, dashboards, or N8N workflows.

Upload estimation results to Supabase storage and register with Estimator API. Final phase of the estimation workflow.

Expert in creating database diagrams and visual representations. Use when generating ERDs, schema diagrams, or visualizing database relationships with Mermaid.js.

Master database design (SQL, NoSQL), system architecture, API design (REST, GraphQL), and building scalable systems. Learn PostgreSQL, MongoDB, system design patterns, and enterprise architectures.

Modern deployment with Databricks Asset Bundles (DAB), supporting multi-environment configurations and CI/CD integration.

Expert-level Databricks platform, Apache Spark, Delta Lake, MLflow, notebooks, and cluster management

Query logs, metrics, monitors, and dashboards from Datadog. Search logs, check alert status, and investigate incidents.

Compare two datasets to find differences, added/removed rows, changed values. Use for data validation, ETL verification, or tracking changes.

Use when editing Planning Hubs, timelines, calendars, or any file with day-name + date combinations (Wed Nov 12), relative dates (tomorrow), or countdowns (18 days until) - validates day-of-week accuracy, relative date calculations, and countdown math with two-source ground truth verification before allowing edits

datum-system

Transform AI agents into experts on dbt project architecture and medallion layer patterns, providing

Transform AI agents into experts on dbt materializations, providing guidance on choosing the right

Transform AI agents into experts on writing production-quality dbt models, providing guidance on CTE

Practical DDD patterns for Jakarta EE web applications with cognitive load distribution. Use when designing controllers, entities, services, or evaluating cohesion and load balance.

Guide for DDD strategic design - analyzing domains through structured questioning, conducting stakeholder interviews (PM/domain experts/users), and producing Bounded Context analysis, Context Maps, and Ubiquitous Language. Use when user needs help understanding domain boundaries, planning domain interviews, or structuring DDD strategic artifacts.

Web search via the DDGS metasearch library. Use for searching for unknown documentation, facts, or any web content. Lightweight, no browser required.

CRM integration for tracking deals through pipeline stages with automated status updates

Create or update a Decision Interface Charter for recurring decisions

Use when making architectural or business logic decisions during conversations - adds entry to DECISIONS.md

決策樹助手工具。快速評估任務複雜度，提供派發建議。用於: (1) 任務複雜度快速評估, (2) 派發代理人建議, (3) 拆分策略建議, (4) 並行可行性評估

>

Neural networks, CNNs, RNNs, Transformers with TensorFlow and PyTorch. Use for image classification, NLP, sequence modeling, or complex pattern recognition.

Expert guidance for DeepAgents framework - simplified agent creation with tool integration for LangChain/LangGraph workflows.

deepagents framework integration patterns for agent creation, planning, filesystem operations, and subagent orchestration. Current version 0.2.5 with LangGraph 1.0.2+

Use this skill in the scenario of deep learning project development.

Expert in lease defaults and landlord remedies. Use when analyzing default scenarios, calculating cure periods, assessing damages, or drafting default notices. Key terms include monetary default, non-monetary default, cure period, notice to cure, lease termination, re-entry, damages, acceleration of rent, unamortized TI clawback

'Create a DESIGN_GUIDELINES.md that defines how to design UI/UX for your customer. Requires CUSTOMER.md to exist first. Covers aesthetic direction, design tokens, typography, color, motion, components, and layout patterns. Bakes in frontend-design skill principles to avoid generic AI aesthetics.'

Create spike definitions with canonical names and numbered approaches for parallel exploratory implementation. Use when partner has an underdefined feature idea and wants to explore multiple implementation approaches in parallel, when uncertain which technical approach is best, or when comparing alternatives before committing to implementation

Split work across subagents with explicit contracts, interfaces, and merge strategies. Use when parallelizing tasks, distributing workload, or orchestrating multi-agent workflows.

Use when designing cloud infrastructure, CI/CD pipelines, or deployment strategies

Run Digital Elevation Model (DEM) analysis pipeline to identify unmapped fault structures through edge detection, drainage pattern analysis, and topographic lineament extraction. Validated in Italy wh