// Data analysis and interpretation — tabular data, trend identification, statistical summaries, comparisons, chart recommendations, anomaly detection.
Create beautiful visual art in .png and .pdf documents using design philosophy. You should use this skill when the user asks to create a poster, piece of art, design, or other static piece. Create original visual designs, never copying existing artists' work to avoid copyright violations.
Parse a PRD, requirements document, or feature description into a structured task list with dependencies and priorities. Trigger when the user wants to plan a project, break down requirements, create a task list from a document, or says things like "plan this project", "break this down into tasks", "create tasks from this PRD".
Generate personalized project instructions through an adaptive onboarding conversation. Trigger when the user wants to set up, initialize, or personalize their AI assistant — e.g., "bootstrap my agent", "set up my assistant", "personalize this AI", "let's do onboarding", "create my instructions", or when project instructions are missing. Also trigger for updates like "update my instructions", "change my AI's personality".
Conduct multi-round deep research on any GitHub repository. Use when users request comprehensive analysis, timeline reconstruction, competitive analysis, or in-depth investigation of a GitHub project. Produces structured markdown reports with executive summaries, chronological timelines, metrics analysis, and Mermaid diagrams. Triggers on GitHub repository URLs or open source project names.
Create Mermaid diagrams: flowcharts, sequence diagrams, class diagrams, ER diagrams, Gantt charts, pie charts, architecture diagrams, and 20+ more types.
Document summarization and interpretation — long document distillation, multi-level summaries (one-line/paragraph/detailed), key information extraction.
| name | data-analysis |
| description | Data analysis and interpretation — tabular data, trend identification, statistical summaries, comparisons, chart recommendations, anomaly detection. |
When the user provides data (tables, CSV, numbers) and asks for analysis, follow this workflow:
For large datasets or precise calculations, use code_execute — no temp files needed:
code_execute call runs in a fresh, isolated process. No variables or data persist between calls. Include ALL imports, data loading, and analysis in a single call. Never split related analysis across multiple calls.read to view thembash to run pip install <package> if a specialized library is neededOnly use write + bash when the script itself needs to be saved for reuse.
Use code for: CSV/Excel processing, statistical calculations, chart generation, data cleaning, batch operations. For small datasets (a few rows/columns), analyze directly in text — no need to write code.
| Analysis goal | Recommended chart |
|---|---|
| Trends over time | Line chart |
| Category comparison | Bar chart |
| Composition/share | Pie / donut chart |
| Distribution | Histogram |
| Correlation | Scatter plot |
| Multi-dimension comparison | Radar chart |
| Ranking | Horizontal bar chart |