griddynamics/rosetta - Page 7

natural-writing

To rewrite text in a clear, natural, honest human tone — no AI slop, hype, or robotic phrasing.

questioning

To ask targeted clarification questions only when high-impact unknowns block safe execution.

reverse-engineering

To reverse-engineer code into a spec: extract behavior and domain logic — WHAT and WHY, not HOW.

risk-assessment

MUST activate before execution when environment has access to databases, cloud services, S3, or similar external systems, and when assessing environment risk level. SHOULD be invoked manually before any new environment interaction.

self-organization

For proactive planning, large-file restructuring (~500+ lines or 10K+ size), and stale-information cleanup. MUST activate when conversation is long, or context reaches 65% / 100K tokens, or scope exceeds 2h / 15+ files / 350+ lines, or output size risks…

specflow-use

To connect Rosetta with Grid Dynamics SpecFlow MCP; only when SpecFlow is mentioned and the MCP is installed.

testing

To write thorough, isolated, idempotent tests — 80%+ coverage, external-only mocking, scenario-driven.

requirements-use

To consume approved requirements for planning, implementation, and validation, with traceability and HITL.

research

To run systematic deep research via meta-prompting — grounded references, incremental tracking, self-validation.