griddynamics/rosetta - 第 4 页

aqa-flow

Router workflow for test automation: routes to ui-aqa-flow, api-aqa-flow, or testgen-flow. Kept for backward compatibility.

原文语言：英语

code-analysis-flow

Workflow for reverse-engineering a codebase into grounded architecture docs, requirements capture, etc.

原文语言：英语

debugging

To investigate errors, test failures, and unexpected behavior — root cause before fix.

原文语言：英语

large-workspace-handling

To partition large workspaces (100+ files) into scoped subagent tasks when context is insufficient.

原文语言：英语

modernization-flow

Workflow for converting, modernizing, upgrading, or re-architecting code (e.g. C++→Java, monolith→microservices), etc.

原文语言：英语

questioning

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

原文语言：英语

research

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

原文语言：英语

self-help-flow

Rosetta self-help: explains capabilities and usage. DEPRECATED.

原文语言：英语

self-learning

MUST activate on: execution failure/error, mistake, wrong/unexpected result, expected≠actual mismatch, 2 consecutive mismatches, unhappy/upset user, user asks why something failed/didn't work.

原文语言：英语

sensitive-data

CRITICAL. MUST activate when you suspect, there is a slight chance, encounter, read, process, or are about to output any sensitive or possibly sensitive data including PII, PCI, HIPAA, PHI, GDPR, SOC2, FedRAMP, secrets, API keys, passwords, credentials,…

原文语言：英语

specflow-use

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

原文语言：英语

testgen-flow

Workflow for generating test cases from requirements (Issue Tracker / Wiki sources), exporting to a Test Management System, etc.

原文语言：英语

testing

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

原文语言：英语

security

Run authorized, evidence-preserving security reviews and prepare remediation inputs.

原文语言：英语

security

Run authorized, evidence-preserving security reviews and prepare remediation inputs.

原文语言：英语

large-workspace-handling

To partition large workspaces (100+ files) into scoped subagent tasks when context is insufficient.

原文语言：英语

aqa-flow

Router workflow for test automation: routes to ui-aqa-flow, api-aqa-flow, or testgen-flow. Kept for backward compatibility.

原文语言：英语

code-analysis-flow

Workflow for reverse-engineering a codebase into grounded architecture docs, requirements capture, etc.

原文语言：英语

coding-agents-farm

To orchestrate parallel coding-agent farms (Claude, Codex, Copilot, Gemini, etc.) on isolated git worktrees.

原文语言：英语

data-collection

To gather QA source artifacts from issue tracker, wiki, test management system

原文语言：英语

debugging

To investigate errors, test failures, and unexpected behavior — root cause before fix.

原文语言：英语

deviation

CRITICAL. MUST activate when intent is unclear, you cannot follow original intent, you cannot easily or reliably solve the problem, something came as SURPRISE or UNEXPECTED, you cannot bet $100 on your solution, you detect unknowns or assumptions that…

原文语言：英语

large-workspace-handling

To partition large workspaces (100+ files) into scoped subagent tasks when context is insufficient.

原文语言：英语

qa-knowledge

To run QA engineering — requirements/gap analysis, scenario & spec design, test implementation, failure triage — over the QA knowledge base.

原文语言：英语

questioning

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

原文语言：英语

research

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

原文语言：英语

reverse-engineering

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

原文语言：英语

self-help-flow

Rosetta self-help: explains capabilities and usage. DEPRECATED.

原文语言：英语

self-learning

MUST activate on: execution failure/error, mistake, wrong/unexpected result, expected≠actual mismatch, 2 consecutive mismatches, unhappy/upset user, user asks why something failed/didn't work.

原文语言：英语

self-organization

CRITICAL. MUST activate at 65%+ context usage, 2h / 15+ file / 350+ line scope, or large-file restructuring. Proactive planning, reorganization, stale-content cleanup.

原文语言：英语

sensitive-data

CRITICAL. MUST activate when you suspect, there is a slight chance, encounter, read, process, or are about to output any sensitive or possibly sensitive data including PII, PCI, HIPAA, PHI, GDPR, SOC2, FedRAMP, secrets, API keys, passwords, credentials,…

原文语言：英语

solr-extending

To build Solr plugins: SearchComponent, QParser, URP, DocTransformer.

原文语言：英语

solr-query

To build and debug Solr queries: eDisMax, block join, JSON facets, kNN, explain.

原文语言：英语

solr-schema

To design and audit Solr schemas: field types, analyzers, docValues, solrconfig.

原文语言：英语

solr-semantic-search

To build Solr phrase-tagging semantic search: concept tagging, taxonomy, graph paths.

原文语言：英语

specflow-use

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

原文语言：英语

testing

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

原文语言：英语

large-workspace-handling

To partition large workspaces (100+ files) into scoped subagent tasks when context is insufficient.

原文语言：英语

large-workspace-handling

To partition large workspaces (100+ files) into scoped subagent tasks when context is insufficient.

原文语言：英语

coding-agents-farm

To orchestrate parallel coding-agent farms (Claude, Codex, Copilot, Gemini, etc.) on isolated git worktrees.

原文语言：英语