why - Investigate the rationale behind code decisions
Investigates why code was designed a certain way by querying historical evidence and returning cited findings with calibrated confidence.
Tags
Updated: 2026-10-08Capabilities
Typical Inputs
Typical Outputs
What this skill does
- Discover available MCPs
- Anchor investigations in code
- Query evidence categories in parallel
- Analyze source control history
- Investigate tickets and issues
- Search documents and team chat
- Inspect operational and product data
- Cite supporting evidence
- Surface contradictions and gaps
- Calibrate investigative confidence
Inputs
- User question
- Target code
- Repository history
- Available MCPs
- Linked tickets and documents
- Operational records
Outputs
- Cited rationale findings
- Confidence-calibrated conclusions
- Coverage map
- Contradictions and evidence gaps
Requirements
- Cursor environment
- Git repository
- GitHub CLI
- Available MCP servers
- Parallel subagent support
- Investigator model support