{"skill":{"slug":"data","displayName":"Data","summary":"Work with data across the full lifecycle from extraction and cleaning to analysis, visualization, and reporting.","description":"---\nname: Data\nslug: data\nversion: 1.0.1\nchangelog: Minor refinements for consistency\ndescription: Work with data across the full lifecycle from extraction and cleaning to analysis, visualization, and reporting.\nmetadata: {\"clawdbot\":{\"emoji\":\"📊\",\"requires\":{\"bins\":[]},\"os\":[\"linux\",\"darwin\",\"win32\"]}}\n---\n\n## When to Use\n\nUser needs to: extract data from sources (databases, APIs, files), clean and transform messy datasets, analyze and find patterns, visualize results, or automate recurring data tasks. Agent handles the full data workflow.\n\n## Quick Reference\n\n| Area | File | Focus |\n|------|------|-------|\n| Querying & Extraction | `querying.md` | SQL generation, API fetching, multi-source |\n| Cleaning & Transformation | `cleaning.md` | Nulls, duplicates, normalization, joins |\n| Analysis & Statistics | `analysis.md` | EDA, statistical tests, insights |\n| Visualization & Reporting | `visualization.md` | Charts, dashboards, exports |\n| Quality & Validation | `quality.md` | Data checks, anomaly detection, drift |\n| Workflow Patterns | `patterns.md` | Common data workflows, automation |\n\n## Core Operations\n\n**Query generation:** User describes what data they need → Agent writes SQL/query, handles joins, filters, aggregations → Returns results or explains execution plan.\n\n**Data cleaning:** Load messy dataset → Detect issues (nulls, duplicates, outliers, inconsistent formats) → Apply appropriate fixes → Document transformations.\n\n**Exploratory analysis:** New dataset arrives → Generate descriptive stats, distributions, correlations → Surface interesting patterns and anomalies → Produce summary with key findings.\n\n**Visualization:** Analysis complete → Generate appropriate chart type → Export in requested format (PNG, SVG, interactive HTML) → Ready for stakeholders.\n\n**Recurring reports:** Define report once → Agent runs on schedule → Updates charts and metrics → Delivers summary with highlights.\n\n## Critical Rules\n\n- Always preview transformations before applying — show sample of what will change\n- Document every data transformation with source, operation, and rationale\n- Validate data types and ranges before analysis — garbage in, garbage out\n- Use appropriate statistical tests — check assumptions first\n- Generate reproducible outputs — include seeds, versions, timestamps\n- Handle missing data explicitly — document chosen strategy (drop, impute, flag)\n- Match chart type to data type — categorical, continuous, time series\n\n## User Modes\n\n| Mode | Focus | Trigger |\n|------|-------|---------|\n| Analyst | SQL, exploration, insights | \"What does this data tell us?\" |\n| Engineer | Pipelines, transformations, quality | \"Clean this and load it there\" |\n| Business | KPIs, dashboards, plain language | \"How are we doing vs last quarter?\" |\n| Researcher | Statistical rigor, reproducibility | \"Is this difference significant?\" |\n| Developer | Schema design, API data, types | \"Generate types from this JSON\" |\n\nSee `patterns.md` for workflows per mode.\n\n## On First Use\n\n1. Identify data source (database, file, API)\n2. Establish connection or load file\n3. Initial EDA — shape, types, quality issues\n4. Clean and transform as needed\n5. Analyze or visualize per user goal\n","tags":{"latest":"1.0.1"},"stats":{"comments":0,"downloads":1114,"installsAllTime":3,"installsCurrent":3,"stars":2,"versions":2},"createdAt":1771086391173,"updatedAt":1778990541234},"latestVersion":{"version":"1.0.1","createdAt":1771413511367,"changelog":"Minor refinements for consistency","license":null},"metadata":{"setup":[],"os":["linux","darwin","win32"],"systems":null},"owner":{"handle":"ivangdavila","userId":"s178jdk12x4qj3gs2se3etxf3h83h7ft","displayName":"Iván","image":"https://avatars.githubusercontent.com/u/81719670?v=4"},"moderation":{"isSuspicious":false,"isMalwareBlocked":false,"verdict":"clean","reasonCodes":["review.llm_review"],"summary":"Review: review.llm_review","engineVersion":"v2.4.24","updatedAt":1779967064621}}