Data Science

Comprehensive security and code quality audit. Use for thorough security, vulnerability, and code quality analysis. Related: project-health-checker for quick diagnostic checks.

Work with raster and imagery data including ImageryLayer, ImageryTileLayer, multidimensional data, pixel filtering, and raster analysis. Use for satellite imagery, elevation data, and scientific raster datasets.

Use when editing Observable notebooks (docs/index.html), creating charts with Plot, adding SQL cells, loading data with FileAttachment, or working with DuckDB. Triggers on notebook editing, visualization, data loading.

Generate structured reports from collected data.LOAD THIS SKILL WHEN: User says "寫報告", "產出報告", "撰寫報告", "generate report" | after research/analysis | need structured documentation.CAPABILITIES: Research/Technical/Project reports, Markdown format, auto date stamps, structured sections (abstract, methods, results, discussion).

This skill should be used when the user asks to "profile the data", "explore the dataset", "plan the analysis", or as Phase 2 of the /ds workflow after brainstorming. Profiles data and creates analysis task breakdown.

Discover refactoring opportunities by analyzing code for excessive responsibilities, tight coupling, low cohesion, and SOLID principle violations. Generate detailed reports with redesign proposals tailored to the project's architecture. Use when analyzing existing code modules for quality issues, before major refactoring, or to maintain code health. Performs module-by-module analysis on demand. (project, gitignored)

Message Batches API for Claude with 50% cost savings on bulk processing. Activate for batch jobs, JSONL processing, bulk analysis, and cost optimization.

Strategic consultant for hackathons, competitions, and new projects. Provides deep research-driven ideation with multiple differentiated options, feasibility analysis, and strategic recommendations. Use when the user needs creative ideas for challenges, asks "what should I build?", requests project brainstorming, or needs strategic decision-making for competitions with specific criteria.

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes - four-phase framework (root cause investigation, pattern analysis, hypothesis testing, implementation) that ensures understanding before attempting solutions

Analyzes vendor spend data from Ramp and exports to connected systems. Use when user asks to "analyze vendor spend", "build vendor database", "update managed vendors", "top vendors report", "show vendors over X spend", "vendor spend analysis", "vendor renewals", "contract end dates", or asks about vendor spending patterns, vendor owners, purchase orders, or department-level vendor data.

Configure treemap charts in drizzle-cube dashboards for hierarchical data visualization. Use when creating treemaps, hierarchical visualizations, or nested proportions.

Presentation creation, editing, and analysis. When Claude needs to work with presentations (.pptx files) for: (1) Creating new presentations, (2) Modifying or editing content, (3) Working with layouts, (4) Adding comments or speaker notes, or any other presentation tasks

Use when preparing daily standups or status reports - automates PR summary generation with categorization, metrics, and velocity analysis; eliminates manual report compilation and ensures consistent format

Helps an agent analyze application logs and identify security issues.

"Convert markdown files to Jupyter notebooks (.ipynb). Splits markdown by `---` delimiters into cells, extracts code blocks (```python```, ```sql```) as code cells, and handles YAML front matter removal. Use when converting documentation, tutorials, or structured markdown into interactive Jupyter notebooks."

Expert guidance for creating and working with marimo notebooks - reactive Python notebooks that can be executed as scripts and deployed as apps. Use when the user asks to create marimo notebooks, convert Jupyter notebooks to marimo, build interactive dashboards or data apps with marimo, work with marimo's reactive programming model, debug marimo notebooks, or needs help with marimo-specific features (cells, UI elements, reactivity, SQL integration, deploying apps, etc.).

Systematic methodology for debugging bugs, test failures, and unexpected behavior.Use when encountering any technical issue before proposing fixes. Covers root causeinvestigation, pattern analysis, hypothesis testing, and fix implementation.Use ESPECIALLY when under time pressure, "just one quick fix" seems obvious, oryou've already tried multiple fixes. NOT for exploratory code reading.

Generate detailed implementation plans for complex tasks. Creates comprehensive strategic plans in Markdown format with objectives, step-by-step implementation tasks using checkbox format, verification criteria, risk assessments, and alternative approaches. All plans MUST be validated using the included validation script. Use when users need thorough analysis and structured planning before implementation, when breaking down complex features into actionable steps, or when they explicitly ask for a plan, roadmap, or strategy. Strictly planning-focused with no code modifications.

Automated generation of promotional assets for podcast episodes from transcripts. Use when the user provides a podcast episode transcript (markdown file) and needs: (1) a one-paragraph episode summary, (2) AI-generated featured image, (3) compelling quotes for social media, (4) short promotional video. Orchestrates transcript analysis, AI image generation via Replicate MCP, and video creation for complete episode marketing asset package.

Create sophisticated economic data analyses and visualizations for higher education stakeholders using FRED (Federal Reserve Economic Data). Use this skill when users request: (1) Analysis of student loan debt, unemployment by education level, or earnings data, (2) Dashboard or visual presentations of higher ed economic indicators, (3) Narrative reports on higher education ROI or economic value, (4) Data-driven communications for institutional stakeholders (trustees, enrollment management, financial aid offices), or (5) Integration of FRED API data into interactive visualizations.