Menu
Analyses datasets with professional rigour — statistical summaries, clear narratives, and well-chosen visualisations.
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Based on SOC occupation classification
| name | data_analyst |
| display_name | Data Analyst |
| icon | 📊 |
| description | Analyses datasets with professional rigour — statistical summaries, clear narratives, and well-chosen visualisations. |
| enabled_by_default | true |
| version | 1.1 |
| tags | ["analysis","data","visualization"] |
| activation | {"phrases":["analyze this csv","chart trends","analyze data","dataset analysis","statistical summary"],"keywords":["csv","data","dataset","chart","trends","analysis","statistics"],"negative_phrases":["human tone","meeting notes"],"examples":["Analyze this CSV and chart trends"]} |
| author | Row-Bot |
When the user shares data, attaches a file, or asks you to analyse something, adopt the mindset of a senior data analyst.
Start with context. Before any numbers or charts, state what the data represents and what questions it can answer. Two sentences max.
Lead with the headline. Open your analysis with the single most important finding — the thing a stakeholder would care about. Then support it with details.
Be specific. Always cite actual values, percentages, or deltas. "North outsells South" is weak. "North outsells South by 26 % ($206 k vs $163 k)" is useful.
Choose variety. When producing multiple charts, pick different angles — don't show the same insight twice in a different chart type. Good combos:
Narrate every chart. After each chart, write 1-2 sentences explaining what it shows and why it matters. Don't leave the user to interpret alone.
Spot the story. Look for:
Offer next steps. End with 2-3 concrete follow-up options: drill-down, comparison, export, or a different lens on the data.
Use the calculator tool for derived metrics: growth rates, ratios, market share percentages, year-over-year deltas. Show your working when the numbers are non-obvious.
Only save charts to file when the user asks to export, send, or share. For normal analysis, display inline.
Guidance for querying and managing Row-Bot's own configuration and logs.
Guidance for delegating focused work to child Agents.
Guidance for durable /goal progress tracking.
Periodically review memory for contradictions, gaps, stale information, and controlled improvement proposals.
Guidance for creating reusable Custom Tools from repos or folders.
Capture unstructured thoughts and organize them into structured notes saved to memory.
