Menu
Skills neste repositório
O SkillsMP coletou 249 skills de griddynamics/rosetta. Abra uma skill para revisar a origem e os detalhes.
griddynamics/rosettaMostrando 40 de 249 skills coletadas.
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,…
Idioma do texto original: inglês
To connect Rosetta with Grid Dynamics SpecFlow MCP; only when SpecFlow is mentioned and the MCP is installed.
Idioma do texto original: inglês
To write thorough, isolated, idempotent tests — 80%+ coverage, external-only mocking, scenario-driven.
Idioma do texto original: inglês
To orchestrate parallel coding-agent farms (Claude, Codex, Copilot, Gemini, etc.) on isolated git worktrees.
Idioma do texto original: inglês
To investigate errors, test failures, and unexpected behavior — root cause before fix.
Idioma do texto original: inglês
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…
Idioma do texto original: inglês
To ask targeted clarification questions only when high-impact unknowns block safe execution.
Idioma do texto original: inglês
To run systematic deep research via meta-prompting — grounded references, incremental tracking, self-validation.
Idioma do texto original: inglês
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.
Idioma do texto original: inglês
CRITICAL. MUST activate at 65%+ context usage, 2h / 15+ file / 350+ line scope, or large-file restructuring. Proactive planning, reorganization, stale-content cleanup.
Idioma do texto original: inglês
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,…
Idioma do texto original: inglês
To connect Rosetta with Grid Dynamics SpecFlow MCP; only when SpecFlow is mentioned and the MCP is installed.
Idioma do texto original: inglês
To write thorough, isolated, idempotent tests — 80%+ coverage, external-only mocking, scenario-driven.
Idioma do texto original: inglês
Collect GitHub repo health/usage stats into merged JSON.
Idioma do texto original: inglês
To orchestrate parallel coding-agent farms (Claude, Codex, Copilot, Gemini, etc.) on isolated git worktrees.
Idioma do texto original: inglês
To implement features, fix bugs, and refactor with KISS/SOLID/DRY and systematic validation.
Idioma do texto original: inglês
Rosetta CRITICAL MUST skill. 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…
Idioma do texto original: inglês
Rosetta CRITICAL MUST skill to load as Prep Step 3 Step 2 — immediately after orchestrator-contract, right before loading any workflow. Loads the session-wide approval-gate protocol governing when to stop and wait vs proceed. WITHOUT IT decisions proceed…
Idioma do texto original: inglês
MUST activate when you ARE an orchestrator — you are the top-level agent, you spawn subagents, you delegate work, you coordinate parallel or sequential execution. Defines delegation quality, subagent dispatch, routing, review, and ownership protocol.
Idioma do texto original: inglês
MUST activate when you ARE a subagent — you were spawned by an orchestrator, you received a delegated task, you are executing within a subagent context. Defines your input contract, output contract, behavior boundaries, and escalation protocol.
Idioma do texto original: inglês
Rosetta CRITICAL MUST skill. MUST activate when action or its consequence is potentially dangerous, potentially irreversible, potentially destructive, or HIGH RISK. MUST activate when consequence MAYBE dangerous even if action itself seems safe. This is…
Idioma do texto original: inglês
To apply structured 8D meta-cognitive reasoning thinking to complex problems, then answer clearly with caveats. Must use when asked to think or reason.
Idioma do texto original: inglês
Diagnose instruction defects and optionally submit Rosetta GitHub issue
Idioma do texto original: inglês
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.
Idioma do texto original: inglês
To author, adapt, review, and validate prompts (skills, agents, workflows, rules, etc.) with brief, contracts, and a validation pack.
Idioma do texto original: inglês
Extract code patterns.
Idioma do texto original: inglês
Create agent rules.
Idioma do texto original: inglês
Generate shell files.
Idioma do texto original: inglês
Verify init completeness.
Idioma do texto original: inglês
To author, update, and validate functional/non-functional requirements as atomic units with user approval.
Idioma do texto original: inglês
To build execution-ready plans from approved intent/specs with EARS, sequenced WBS, and HITL checkpoints.
Idioma do texto original: inglês
To define clear, testable tech specs from requirements — target-state architecture, contracts, interfaces.
Idioma do texto original: inglês
Rosetta CRITICAL MUST skill. 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,…
Idioma do texto original: inglês
To write, design, review, simplify, restructure, or standardize OSS project documentation
Idioma do texto original: inglês
To investigate errors, test failures, and unexpected behavior — root cause before fix.
Idioma do texto original: inglês
Classify workspace mode.
Idioma do texto original: inglês
Discover tech stack.
Idioma do texto original: inglês
Generate workspace docs.
Idioma do texto original: inglês
To partition large workspaces (100+ files) into scoped subagent tasks when context is insufficient.
Idioma do texto original: inglês
To load the most current project context; MUST during prep.
Idioma do texto original: inglês