Analyze

anthropics/knowledge-work-pluginsOfficial

Handles data questions across three complexity levels: quick metric lookups, multi-dimensional analyses, and formal stakeholder reports. Works with connected data warehouse MCP servers to explore schemas, write SQL, and validate results before presenting, or guides you through manual data gathering if nothing's connected. The validation step is smart, it runs sanity checks on row counts, nulls, and aggregation logic before showing you anything. Responds with just the answer for simple questions, structured findings with caveats for investigations, or full methodology and recommendations for reports. Can kick to the data visualization skill when charts would land better than tables.

skills.sh installs: 5.8K
GitHub stars: 35.3K
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add anthropics/knowledge-work-plugins --skill analyze --agent claude-code

Installs into .claude/skills of the current project.

Files

/analyze - Answer Data Questions

If you see unfamiliar placeholders or need to check which tools are connected, see CONNECTORS.md.

Answer a data question, from a quick lookup to a full analysis to a formal report.

Usage

/analyze <natural language question>

Workflow

1. Understand the Question

Parse the user's question and determine:

Complexity level:
- Quick answer: Single metric, simple filter, factual lookup (e.g., "How many users signed up last week?")
- Full analysis: Multi-dimensional exploration, trend analysis, comparison (e.g., "What's driving the drop in conversion rate?")
- Formal report: Comprehensive investigation with methodology, caveats, and recommendations (e.g., "Prepare a quarterly business review of our subscription metrics")
Data requirements: Which tables, metrics, dimensions, and time ranges are needed
Output format: Number, table, chart, narrative, or combination