Technical Skills

Real-time monitoring of ClickHouse metrics, events, and asynchronous metrics. Use for load average, connections, queue monitoring, and resource saturation.

Diagnose ClickHouse SELECT query performance, analyze query patterns, identify slow queries, and find optimization opportunities. Use for query latency and timeout issues.

Diagnose ClickHouse RAM usage, OOM errors, memory pressure, and allocation patterns. Use for memory-related issues and out-of-memory errors.

Unified marketing metrics dashboard and CLI. Use when building or running a marketing status dashboard that pulls from PostHog, Google Search Console, Stripe, and ad platforms. Covers traffic, SEO, ads, revenue, and funnel conversion reporting in terminal output.

Rapid decision-making loop for dynamic situations. Use for incident response, competitive scenarios, time-sensitive decisions, and situations requiring quick adaptation.

Safe database exploration using Laravel Boost tools. Use for querying data, understanding schema, checking records, and debugging data issues. Auto-triggers on "query database", "check data", "find records", "database query", "show me the data".

Helps create and structure Jupyter notebooks for teaching labs. Use this skill when creating lab notebooks, adding explanations for students, structuring educational content, or writing code cells with proper documentation.

This skill should be used when the user asks to "get Census data", "query American Community Survey", "find ACS data", "get population by state", "query Decennial Census", "find Census variables", "get median income data", "download demographic data", "Census API query", "get housing data from Census", or mentions US Census Bureau data (demographics, income, poverty, education, housing, population estimates, etc.).

End-to-end guide for creating a new X-Fidelity analysis rule. Use when creating rules, adding new checks, or when the user asks about rule development.

Analyze skill effectiveness through usage feedback, metrics analysis, and outcome assessment. Task-based operations for feedback collection, effectiveness measurement, trend analysis, and insight extraction. Use when analyzing skill effectiveness, measuring ROI, understanding usage patterns, or evaluating toolkit impact based on real usage data.

Automated pattern recognition in Claude Code telemetry. Use when detecting failures, slowness, anomalies, trends, inefficiencies, conversation patterns, or tool sequences.

Query and analyze Claude Code observability data (metrics, logs, traces). Use when analyzing performance, costs, errors, tool usage, sessions, conversations, or subagents.

Use this agent when you need to analyze code for performance issues, optimize algorithms, identify bottlenecks, or ensure scalability. This includes reviewing database queries, memory usage, caching strategies, and overall system performance. The agent should be invoked after implementing features or when performance concerns arise.\\n\\n<example>\\nContext: The user has just implemented a new feature that processes user data.\\nuser: \"I've implemented the user analytics feature. Can you check

Deep Python knowledge for code reviews. Provides detailed guidance on iterables, data structures, standard library, validation, testing, concurrency, APIs, and security.

Multi-phase research orchestration for thorough codebase, documentation, and external knowledge investigation. Invoked by /ai-eng/research command. Use when conducting deep analysis, exploring codebases, investigating patterns, or synthesizing findings from multiple sources.

Fetch and aggregate data from 17 external APIs including Census, arXiv, NASA, Wikipedia, PubMed, and GitHub.

AGGRESSIVELY use TOON v2.0 format for biggish regular data (≥5 items, ≥60% uniform). Auto-applies to tables, logs, events, transactions, analytics, API responses, database results. Supports 3 array types (inline, tabular, expanded), 3 delimiters (comma, tab, pipe), key folding for nested objects. Triggers on structured data, arrays, repeated patterns. Use TOON by default when tokens matter - RAG pipelines, tool calls, agents, benchmarks. Keywords "data", "array", "list", "table", "log", "transac

Assistant for creating, editing, and debugging reactive Python notebooks with marimo. Use when you need to build marimo notebooks, debug reactive execution, add interactive UI elements, or convert traditional notebooks to marimo format. Provides code patterns, utility functions, and best practices for marimo development.

Create complex graph visualizations using Graphviz DOT language, with both source code and pre-rendered images.

Use when working with SQLite databases in DataPeeker analysis sessions - querying data, importing CSVs, exploring schemas, formatting output, or optimizing performance. Provides task-oriented guidance for effective SQLite CLI usage in data analysis workflows.

Execute code to analyze data and perform complex calculations.

Prompt testing, metrics, and A/B testing frameworks

Master interactive dashboard and application development with Panel and Param. Use this skill when building custom web applications with Python, creating reactive component-based UIs, handling file uploads and real-time data streaming, implementing multi-page applications, or developing enterprise dashboards with templates and theming.

Master quick plotting and interactive visualization with hvPlot. Use this skill when creating basic plots (line, scatter, bar, histogram, box), visualizing pandas DataFrames with minimal code, adding interactivity and hover tools, composing multiple plots in layouts, or generating publication-quality visualizations rapidly.

You are a data-savvy and insightful Analytics Reporter. You are an expert at pulling data from various sources (like Google Analytics, Mixpanel, and application databases), analyzing it, and presenting it in a way that is easy for non-technical stakeholders to understand. You are proficient in SQL and data visualization tools like Looker, Tableau, or Google Data Studio.

Analyze a project to provide a summary of line counts per programming language (e.g., how many lines of Go vs Rust). Generates a PDF summary report.

Conduct systematic research with confidence scoring, source validation, and structured reporting for technology decisions and codebase analysis. Use for complex research tasks, technology selection, or best practice discovery.

Guide for implementing analytics tracking in SuperTool. Use this when adding analytics events, tracking user actions, or ensuring privacy compliance.

Analytical thinking patterns for comprehensive evaluation, code audits, security analysis, and performance reviews. Provides structured templates for thorough investigation with extended thinking support.

This skill should be used when the user asks to "work with polars", "create a dataframe", "use lazy evaluation", "migrate from pandas", "optimize data pipelines", "read parquet files", "group by operations", or needs guidance on Polars DataFrame operations, expression API, performance optimization, or data transformation workflows.

Comprehensive statistical analysis toolkit for research. Conduct hypothesis tests (t-test, ANOVA, chi-square), regression, correlation, Bayesian stats, power analysis, assumption checks, and APA reporting. Use when the user asks about statistics, needs help analyzing data, or when writing methods sections that include statistical approaches.

Autogenerate formula implementations from formula specifications (F-*). Converts mathematical formulas, calculations, and algorithms into production code with tests. Use when F-* includes formula specifications.

Matrix data model verification using ASCII diagrams. Use when working with *Progressions.ts files, defineProgression(), or testing how 2D numeric grids evolve over time. Auto-apply when editing files matching *Progressions.ts or src/test-utils/ascii*.ts.

Analyze code performance, detect bottlenecks, suggest optimizations for algorithms, queries, and resource usage. Use when improving application performance or investigating slow code.

Python tools for analyzing Instruments traces and performance data

Use this skill when running performance benchmarks, measuring API endpoint response times, detecting performance regressions, running load tests, comparing performance before/after changes, analyzing performance trends, or validating optimization improvements. Handles baseline comparisons, historical tracking, and report generation.

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.

Guide for discovering and integrating with Rubin Science Platform (RSP) APIs using OpenAPI specifications. Use this skill when working with Gafaelfawr authentication APIs (/auth/*), Times Square notebook APIs (/times-square/api/*), or other RSP services. Covers finding OpenAPI specs, using WebFetch to download specifications, creating TypeScript types from schemas, implementing SWR-based hooks, handling authentication patterns (CSRF tokens, credentials), and creating mock APIs for development.

Fast Python framework for building interactive web apps, dashboards, and data visualizations without HTML/CSS/JavaScript. Use when user wants to create data apps, ML demos, dashboards, data exploration tools, or interactive visualizations. Transforms Python scripts into web apps in minutes with automatic UI updates.

Pattern detection and automatic skill recommendation system. Activates when analyzing Cortex memory files, detecting recurring work patterns, or determining if new skills are needed. Analyzes .cortex_log.md, PRD files, and task lists to identify patterns (API calls, testing, deployment, etc.) appearing 5+ times. Generates Synapse_RECOMMENDATIONS.md with prioritized skill suggestions. Use when optimizing workflows or identifying automation opportunities.