anthropics avatar

Data Context Extractor

This is a bootstrapping tool for data teams who are tired of explaining their warehouse schema to Claude every single conversation. It walks you through schema discovery, asks targeted questions about your metrics and terminology (like "when you say 'user' what do you actually mean?"), then generates a company-specific data analyst skill with reference files. You can run it once to create the initial skill or use iteration mode to add new domains. The real value is capturing tribal knowledge about gotchas, standard filters, and metric calculations so future Claude sessions already know that ARR excludes test accounts and the users table has three different ID columns. Saves you from writing this documentation yourself.

skills.sh installs
3.2K
GitHub stars
35.3K
last updated
Aug 21, 2026

Install

$ npx -y skills add anthropics/knowledge-work-plugins --skill data-context-extractor --agent claude-code

Installs into .claude/skills of the current project.

Files

Data Context Extractor

A meta-skill that extracts company-specific data knowledge from analysts and generates tailored data analysis skills.

How It Works

This skill has two modes:

  1. Bootstrap Mode: Create a new data analysis skill from scratch
  2. Iteration Mode: Improve an existing skill by adding domain-specific reference files

Bootstrap Mode

Use when: User wants to create a new data context skill for their warehouse.

Phase 1: Database Connection & Discovery

Step 1: Identify the database type

Ask: "What data warehouse are you using?"

Common options:

  • BigQuery
  • Snowflake
  • PostgreSQL/Redshift
  • Databricks

Use ~~data warehouse tools (query and schema) to connect. If unclear, check available MCP tools in the current session.

Step 2: Explore the schema

Use ~~data warehouse schema tools to:

  1. List available datasets/schemas
  2. Identify the most important tables (ask user: "Which 3-5 tables do analysts query most often?")
  3. Pull schema details for those key tables

Sample exploration queries by dialect:

-- BigQuery: List datasets
SELECT schema_name FROM INFORMATION_SCHEMA.SCHEMATA

Sponsors

Details

Repository
github.com/anthropics/knowledge-work-plugins
Categories
Backend & APIs, Databases
First seen
Apr 16, 2026

More from anthropics/knowledge-work-plugins

All 198
1pytorch avatarat-dispatch-v2pytorch/pytorchConvert PyTorch AT_DISPATCH macros to AT_DISPATCH_V2 format in ATen C++ code. Use when porting AT_DISPATCH_ALL_TYPES_AND*, AT_DISPATCH_FLOATING_TYPES*, or other3.2Kskills.sh installs
2arize-ai avatararize-annotationarize-ai/arize-skillsCreates and manages annotation configs (categorical, continuous, freeform label schemas) and annotation queues (human review workflows) on Arize. Applies human 3.1Kskills.sh installs
3anthropics avatarprocess-docanthropics/knowledge-work-pluginsDocument a business process — flowcharts, RACI, and SOPs. Use when formalizing a process that lives in someone's head, building a RACI to clarify who owns what,3.1Kskills.sh installs
4openai avatarfigma-create-design-system-rulesopenai/skillsGenerates custom design system rules for the user's codebase. Use when user says "create design system rules", "generate rules for my project", "set up design r3.1Kskills.sh installs
5hoodini avatarowasp-securityhoodini/ai-agents-skillsImplement secure coding practices following OWASP Top 10. Use when preventing security vulnerabilities, implementing authentication, securing APIs, or conductin3.1Kskills.sh installs
6actionbook avatardomain-cloud-nativeactionbook/rust-skillsUse when building cloud-native apps. Keywords: kubernetes, k8s, docker, container, grpc, tonic, microservice, service mesh, observability, tracing, metrics, hea3Kskills.sh installs