Use when a graph already exists and the user needs retrieval, tracing, explanation, or gap detection from graph memory before reopening the full corpus.
Use when the user provides a MarkItDown-supported file or URL and converting it to Markdown first will make inspection easier, cheaper, or more reliable.
Use when connecting to a managed codebase-context MCP/session service, checking stale maps, or safely using MCP-provided repository context.
Relay questions and tasks to a local Claude CLI using one-shot subprocesses per ask.
Audit the methodology used to split data into train, validation, and test sets.
Process-first advisor routing with artifact capture
Multi-model orchestration — route to two external advisors, then synthesize
Verify that API endpoints match their OpenAPI/Swagger specifications.
Use to diagnose tests that pass and fail intermittently without code changes.
Use when code needs restructuring without changing observable behavior.
Ensure that new complex models actually outperform simple, naive baselines.
Identify and prevent target leakage in ML preprocessing pipelines.
Extract a learned skill from the current conversation manually
Turn vague implementation requests into testable requirements before coding.