griddynamics/rosetta - Página 4

orchestration

To delegate, prompt and manage subagents. MUST activate to spawn subagent with a quality prompt, unless trivial.

Idioma del texto original: inglés

planning

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

Idioma del texto original: inglés

post-mortem

Diagnose instruction defects and optionally submit Rosetta GitHub issue

Idioma del texto original: inglés

questioning

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

Idioma del texto original: inglés

reasoning

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

Idioma del texto original: inglés

requirements-authoring

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

Idioma del texto original: inglés

requirements-use

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

Idioma del texto original: inglés

research

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

Idioma del texto original: inglés

rosetta

Rosetta identifies and routes user request to the most matching workflow

Idioma del texto original: inglés

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.

Idioma del texto original: inglés

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,…

Idioma del texto original: inglés

specflow-use

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

Idioma del texto original: inglés

tech-specs

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

Idioma del texto original: inglés

testing

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

Idioma del texto original: inglés

coding-agents-farm

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

Idioma del texto original: inglés

coding-agents-prompt-authoring

To author, adapt, review, and validate prompts (skills, agents, workflows, rules, etc.) with brief, contracts, and a validation pack.

Idioma del texto original: inglés

coding

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

Idioma del texto original: inglés

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.

Idioma del texto original: inglés

debugging

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

Idioma del texto original: inglés

deviation

MUST activate when intent is unclear, or cannot follow or deviate from original intent, or easily or reliably solve the problem, something came as SURPRISE or UNEXPECTED, you cannot bet $100 on solution, unknowns or assumptions critically affect solution, you…

Idioma del texto original: inglés

harness

To build an AI harness: run, observe, validate, automate repeated work faster — CLI/MCP actions, devcontainers, skills, subagents, hooks, pipelines, automations.

Idioma del texto original: inglés

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`…

Idioma del texto original: inglés

large-workspace-handling

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

Idioma del texto original: inglés

natural-writing

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

Idioma del texto original: inglés

orchestration

To delegate, prompt and manage subagents. MUST activate to spawn subagent with a quality prompt, unless trivial.

Idioma del texto original: inglés

planning

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

Idioma del texto original: inglés

post-mortem

Diagnose instruction defects and optionally submit Rosetta GitHub issue

Idioma del texto original: inglés

questioning

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

Idioma del texto original: inglés

reasoning

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

Idioma del texto original: inglés

requirements-authoring

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

Idioma del texto original: inglés

requirements-use

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

Idioma del texto original: inglés

research

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

Idioma del texto original: inglés

risk-assessment

MUST activate before execution when environment has access to databases, cloud services, S3, or similar external systems, any access to servers of higher environments, and when assessing environment risk level.

Idioma del texto original: inglés

rosetta

Rosetta identifies and routes user request to the most matching workflow

Idioma del texto original: inglés

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.

Idioma del texto original: inglés

self-organization

MUST activate at 65%+ context usage or on large-file restructuring. Proactive planning, reorganization, stale-content cleanup.

Idioma del texto original: inglés

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,…

Idioma del texto original: inglés

specflow-use

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

Idioma del texto original: inglés

subagent-directives

MUST duties for a spawned subagent

Idioma del texto original: inglés

tech-specs

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

Idioma del texto original: inglés