griddynamics/rosetta - 第 4 页

testing

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

原文语言：英语

coding

To implement features, fix bugs, and refactor with KISS/SOLID/DRY and systematic validation.

原文语言：英语

dangerous-actions

MUST activate when action OR its consequence is potentially dangerous/irreversible/destructive, or HIGH RISK, or environment is stage, pre-prod, prod, or blast radius.

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

hitl

MUST activate for ALL tasks — planning, execution, validation, review: session-wide work with human together, human-in-the-loop questioning, approvals, stop-and-wait vs proceed. NEVER assume approval. MANDATORY unless user requested EXACTLY `fully autonomous`…

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

natural-writing

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

原文语言：英语

planning

To build execution-ready AI sessions graph with intent/ACs/checklists.

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

reasoning

To apply structured meta-cognitive thinking to complex problems. Invoke on explicit only.

原文语言：英语

requirements-authoring

To author, update, and validate functional/non-functional requirements as atomic units with user approval.

原文语言：英语

requirements-use

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

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-learning

MUST STOP and activate on: any failure/error, mistakes, wrong/unexpected result, expected≠actual mismatch, 2 consecutive mismatches, unhappy/upset user, user WRITING IN CAPS, something didn't work. No edits, no reverses, no actions, except this skill.

原文语言：英语

sensitive-data

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, tokens,…

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

tech-specs

To define clear, testable tech specs from requirements — target-state architecture, contracts, interfaces.

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

coding

To implement features, fix bugs, and refactor with KISS/SOLID/DRY and systematic validation.

原文语言：英语

dangerous-actions

MUST activate when action OR its consequence is potentially dangerous/irreversible/destructive, or HIGH RISK, or environment is stage, pre-prod, prod, or blast radius.

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

hitl

MUST activate for ALL tasks — planning, execution, validation, review: session-wide work with human together, human-in-the-loop questioning, approvals, stop-and-wait vs proceed. NEVER assume approval. MANDATORY unless user requested EXACTLY `fully autonomous`…

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

natural-writing

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

原文语言：英语

planning

To build execution-ready AI sessions graph with intent/ACs/checklists.

原文语言：英语

post-mortem

Diagnose instruction defects and optionally submit Rosetta GitHub issue

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

reasoning

To apply structured meta-cognitive thinking to complex problems. Invoke on explicit only.

原文语言：英语

requirements-authoring

To author, update, and validate functional/non-functional requirements as atomic units with user approval.

原文语言：英语

requirements-use

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

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

rosetta

Rosetta identifies and routes user request to the most matching workflow

原文语言：英语

self-learning

MUST STOP and activate on: any failure/error, mistakes, wrong/unexpected result, expected≠actual mismatch, 2 consecutive mismatches, unhappy/upset user, user WRITING IN CAPS, something didn't work. No edits, no reverses, no actions, except this skill.

原文语言：英语

sensitive-data

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, tokens,…

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

tech-specs

To define clear, testable tech specs from requirements — target-state architecture, contracts, interfaces.

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

coding

To implement features, fix bugs, and refactor with KISS/SOLID/DRY and systematic validation.

原文语言：英语

dangerous-actions

MUST activate when action OR its consequence is potentially dangerous/irreversible/destructive, or HIGH RISK, or environment is stage, pre-prod, prod, or blast radius.

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