Creative Skills

This skill should be used when the user asks to "create a mermaid diagram", "draw a flowchart", "make a sequence diagram", "update diagram theme", "customize diagram colors", "add icons to architecture diagram", or mentions working with architecture diagrams, state diagrams, gantt charts, timelines, mindmaps, entity relationships, sankey diagrams, or user journeys. Always use when creating, editing, or customizing mermaid diagrams in markdown files.

Expert-level guidance on data platform architecture, pipeline design patterns, and engineering rigor. Use when designing data platforms, reviewing Airflow DAGs, working with Polars/DuckDB/dbt, establishing data quality contracts, implementing composable data stacks, or architecting lakehouse solutions with Iceberg.

>

Aggregate-only summarizer for K18 QC artifacts; produces summary outputs and appends manifest rows when format is confirmed.

Extracts structured, chart-ready JSON data from medical analysis for visualization, including diagnoses, timeline, prognosis, and supplement schedules.

Interactive dashboard design workflow. Analyzes data, asks clarifying questions, generates visualizations, and saves reusable configs. Use when user has raw data and wants a dashboard created collaboratively.

Provides expert backend analysis, API/service architecture review, and integration guidance. Use for API design evaluation, service layer review, data access patterns, or when asked to assess server-side code. Produces consultant-style reports with prioritized recommendations — does NOT write implementation code.

Provides expert database analysis, schema design review, and query optimization assessment. Use this skill when the user needs database architecture evaluation, query performance analysis, or data integrity review. Triggers include requests for database audit, schema review, query optimization, or when asked to evaluate database patterns. Produces detailed consultant-style reports with findings and prioritized recommendations — does NOT write implementation code.

Use when "data visualization", "plotting", "charts", "matplotlib", "plotly", "seaborn", "graphs", "figures", "heatmap", "scatter plot", "bar chart", "interactive plots

Generate HTML reports, charts, and dashboards with neo-brutal design. Use for creating GitHub activity reports, Fieldy summaries, Skillz analytics, and other data visualizations.

Expert business intelligence covering dashboard design, data visualization, reporting automation, and executive insights delivery.

Create, edit, and analyze Excel spreadsheets with formulas, charts, pivot tables, and data analysis (Official Anthropic skill)

Edit or create interactive Plotly.js graph components in Svelte 5. Use when asked to create a graph, add a visualization, build a chart, make a plot, visualize data, add slider controls to a graph, or create a new graph page. Handles 60fps slider updates, throttling, data precomputation, and proper Svelte 5 reactivity patterns.

Data scientist specializing in startup analytics, user behavior tracking, and metrics analysis for Lean Startup and Customer Development methodologies. Use when analyzing user data, setting up analytics, measuring validation metrics, cohort analysis, or when user asks about tracking, metrics, data analysis, or measuring startup hypotheses.

Design, standardize, and implement ECharts-based visualizations and themes for InsightPulseAI dashboards, Superset plugins, and OpEx UI (AntD + M3 + ECharts).

Crear diagramas Mermaid compatibles con Obsidian (flowchart, sequence, gantt). Evita errores comunes y produce diagramas simples y mantenibles.

Automatically convert uploaded data (CSV, Excel, JSON) into complete interactive dashboards with zero user input required. Detects patterns in PPC reports, sales data, analytics exports, and business metrics - then generates insights, recommendations, and visualizations instantly. Works seamlessly with CURV design system for on-brand outputs with tabs, funnels, filters, and multi-view layouts.

Connect Supabase databases to Claude Desktop artifacts with read-only queries and live data visualization.

This skill should be used when the user asks "Chart.js gradients", "Chart.js linear gradient", "Chart.js radial gradient", "custom Chart.js chart type", "extend Chart.js", "derived chart type", "custom Chart.js scale", "Chart.js programmatic events", "Chart.js setActiveElements", "Chart.js custom controller", or needs help with advanced Chart.js v4.5.1 techniques.

This skill should be used when the user asks "Chart.js plugin", "custom Chart.js plugin", "Chart.js plugin hooks", "Chart.js beforeDraw", "Chart.js afterDraw", "custom chart type", "extend Chart.js", "Chart.js API", "Chart.js update", "Chart.js destroy", "Chart.js methods", "Chart.js events", "Chart.js canvas", "Chart.js TypeScript", "custom scale", "Chart.js DatasetController", "Chart.js Scale", or needs help creating custom Chart.js v4.5.1 plugins, extensions, custom chart types, custom scales

This skill should be used when the user asks "Chart.js axes", "Chart.js scales", "Chart.js x-axis", "Chart.js y-axis", "Chart.js time axis", "Chart.js logarithmic scale", "Chart.js axis labels", "Chart.js ticks", "Chart.js grid lines", "Chart.js multiple axes", "Chart.js dual axis", "Chart.js axis title", "Chart.js axis range", "Chart.js min max", "stacked axes", "Chart.js radial axis", or needs help configuring Chart.js v4.5.1 axes and scales.

Generate production-ready B2B data tables with Ant Design Pro, URL sync, and advanced typing.

Expert guidance for creating syntactically correct and well-structured Mermaid diagrams following best practices. Use when creating flowcharts, sequence diagrams, class diagrams, state diagrams, Gantt charts, ER diagrams, data lineage visualizations, or any other Mermaid visualization.

Extracts, transforms, and analyzes NBA statistics using the nba_api Python library. Use when working with NBA player stats, team data, game logs, shot charts, league statistics, or any NBA-related data engineering tasks. Supports both stats.nba.com endpoints and static player/team lookups.

Map non-linear connections across files, thoughts, and projects. Reveal hidden patterns in seemingly unrelated work. Use when feeling scattered, when working across multiple domains, or when sensing connections but unable to articulate them.

Professional rules for AI-driven data modeling and creation. Use this skill when users need to create and manage MySQL databases, design data models using Mermaid ER diagrams, and implement database schemas.

Create tiered reports (micro/standard/comprehensive) based on task complexity. Tier 1 (200-500 words) for Level 1 tasks, Tier 2 (500-1500 words) for Level 2, Tier 3 (1500-5000 words) for Level 3 epics. Synthesizes agent outputs into concise, scannable reports without duplication. Uses density over volume, actionable over descriptive. Triggers ONLY after multi-agent completion (2+ agents) or complex investigations. NOT for single-agent trivial tasks.

Interactive data exploration and visualization skill. Use when users ask to visualize data, analyze datasets, create charts, or explore data files (CSV, Excel, Parquet, JSON). This skill guides through data exploration, proposes visualization strategies based on data characteristics, creates interactive Plotly charts in marimo notebooks, and generates analytical conclusions.

Knowledge about pyecharts chart creation, HTML report generation, and visualization best practices

Master SQL query optimization, indexing strategies, and EXPLAIN analysis to dramatically improve database performance and eliminate slow queries. Use when debugging slow queries, designing database schemas, or optimizing application performance.

Use Superset-style APIs to manage workspaces, users, datasets, charts, and dashboards as code for the InsightPulseAI Data Lab platform.

Design, organize, and operate Deepnote projects as the InsightPulseAI Data Lab workspace for exploration, jobs, and Superset-ready summary tables.

Analyzes Snowflake query performance, identifies optimization opportunities, and provides cost reduction recommendations. Use when user needs to optimize slow queries, reduce Snowflake costs, analyze query profiles, design clustering keys, or troubleshoot performance issues.

Expert guidance on statistical analysis methodologies and Monte Carlo simulation for fantasy football. Use this skill when selecting regression approaches, designing simulations, performing variance analysis, or conducting hypothesis tests. Covers regression types (OLS, Ridge, Lasso, GAMs), Monte Carlo frameworks, regression-to-mean analysis, and statistical best practices for player performance modeling.

Design system or visualization guidelines.

This skill should be used when creating or modifying frontend dashboard components in the ClaudeCode Sentiment Monitor project. Specifically trigger this skill for tasks involving React 19 components, Next.js 15 App Router pages, shadcn/ui components, Recharts visualizations, SWR data fetching, or Tailwind CSS styling.

Stock analysis UI frontend. React + TypeScript with Tailwind CSS, shadcn/ui, Recharts. Use for React components, API integration, routing, state management, styling, charts visualization.

Generate professional HTML presentation slides from Markdown files or raw content. Use when creating presentations, slide decks, or when asked to make slides. Fully automated workflow - Markdown analysis → Layout selection → HTML generation → Thumbnail generation → Surge deployment. Supports 16 layouts, Chart.js graphs, and interactive features.

Executes structured, factual research runs across any domain (e.g., algorithms, competitors, AI models, audience behavior). Creates timestamped, reproducible artifacts with inline citations, confidence scoring, and adaptive freshness control.

Thrivve Partners Monte Carlo simulation to forecast story/task completion based on historical throughput. Use when the user asks "how many stories/tasks will be completed by [date]" with historical daily throughput data. Requires at least 10 days of throughput history and a future target date. Provides probabilistic forecasts at specified confidence levels (default 85%).