griddynamics/rosetta - Seite 5

data-collection

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

Quellsprache: Englisch

debugging

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

Quellsprache: Englisch

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…

Quellsprache: Englisch

post-mortem

Diagnose instruction defects and optionally submit Rosetta GitHub issue

Quellsprache: Englisch

qa-knowledge

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

Quellsprache: Englisch

questioning

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

Quellsprache: Englisch

research

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

Quellsprache: Englisch

reverse-engineering

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

Quellsprache: Englisch

rosetta

Rosetta identifies and routes user request to the most matching workflow

Quellsprache: Englisch

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.

Quellsprache: Englisch

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.

Quellsprache: Englisch

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,…

Quellsprache: Englisch

solr-extending

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

Quellsprache: Englisch

solr-query

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

Quellsprache: Englisch

solr-schema

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

Quellsprache: Englisch

solr-semantic-search

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

Quellsprache: Englisch

specflow-use

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

Quellsprache: Englisch

testing

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

Quellsprache: Englisch

coding-agents-farm

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

Quellsprache: Englisch

research

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

Quellsprache: Englisch

coding-agents-farm

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

Quellsprache: Englisch

coding-agents-farm

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

Quellsprache: Englisch

debugging

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

Quellsprache: Englisch

post-mortem

Diagnose instruction defects and optionally submit Rosetta GitHub issue

Quellsprache: Englisch

questioning

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

Quellsprache: Englisch

research

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

Quellsprache: Englisch

rosetta

Rosetta identifies and routes user request to the most matching workflow

Quellsprache: Englisch

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.

Quellsprache: Englisch

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,…

Quellsprache: Englisch

specflow-use

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

Quellsprache: Englisch

testing

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

Quellsprache: Englisch

coding-agents-farm

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

Quellsprache: Englisch

debugging

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

Quellsprache: Englisch

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…

Quellsprache: Englisch

post-mortem

Diagnose instruction defects and optionally submit Rosetta GitHub issue

Quellsprache: Englisch

questioning

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

Quellsprache: Englisch

research

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

Quellsprache: Englisch

rosetta

Rosetta identifies and routes user request to the most matching workflow

Quellsprache: Englisch

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.

Quellsprache: Englisch

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.

Quellsprache: Englisch