Claude skill
Data Context Extractor
Data Context Extractor is a Claude skill in the Data plugin, built by Anthropic. Generate or improve a company-specific data analysis skill by extracting tribal knowledge from analysts.
What it does
The description in the skill's SKILL.md, which Claude reads to decide when to use it:
Generate or improve a company-specific data analysis skill by extracting tribal knowledge from analysts. BOOTSTRAP MODE - Triggers: "Create a data context skill", "Set up data analysis for our warehouse", "Help me create a skill for our database", "Generate a data skill for [company]" → Discovers schemas, asks key questions, generates initial skill with reference files ITERATION MODE - Triggers: "Add context about [domain]", "The skill needs more info about [topic]", "Update the data skill with [metrics/tables/terminology]", "Improve the [domain] reference" → Loads existing skill, asks targeted questions, appends/updates reference files Use when data analysts want Claude to understand their company's specific data warehouse, terminology, metrics definitions, and common query patterns.
The skill's instructions (about 937 words) cover:
- How It Works
- Bootstrap Mode
- Phase 1: Database Connection & Discovery
- Phase 2: Core Questions (Ask These)
- Phase 3: Generate the Skill
- Phase 4: Package and Deliver
- Iteration Mode
- Step 1: Load Existing Skill
- Step 2: Identify the Gap
- Step 3: Targeted Discovery
- Step 4: Update and Repackage
- Reference File Standards
How to use it
- Data Context Extractor comes inside the Data plugin, so you get it by installing that plugin, along with its 9 other skills. A plugin installs as one unit, with all its skills. The plugin's page has the install steps, and plugins are saved to your Claude account.
- Ask Claude for the task. When your request matches the skill's description, Claude loads it.
- To pick it yourself in Claude chat, type
/or click + and choose data-context-extractor. In Claude Code and Cowork, type:/data:data-context-extractor
Source
- Plugin
- Data (Anthropic)
- SKILL.md
- View on GitHub
- Repo stars
- 36,253
- Repo last pushed
- Nov 13, 2026
- Checked
- Nov 16, 2026
More skills in Data
- Data VisualizationCreate effective data visualizations with Python (matplotlib, seaborn, plotly).
- Explore DataProfile and explore a dataset to understand its shape, quality, and patterns.
- SQL QueriesWrite correct, performant SQL across all major data warehouse dialects (Snowflake, BigQuery, Databricks, PostgreSQL, etc.).
- Statistical AnalysisApply statistical methods including descriptive stats, trend analysis, outlier detection, and hypothesis testing.
- Validate DataQA an analysis before sharing -- methodology, accuracy, and bias checks.
- Write QueryWrite optimized SQL for your dialect with best practices.
- AnalyzeAnswer data questions -- from quick lookups to full analyses.
- Build DashboardBuild an interactive HTML dashboard with charts, filters, and tables.
- Create VizCreate publication-quality visualizations with Python.