griddynamics

coding-agents-prompt-authoring

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

hitl

CRITICAL. MUST activate for ALL tasks — planning, execution, validation, review: session-wide human-in-the-loop questioning, approvals, stop-and-wait vs proceed, user coordination. NEVER assume approval. MANDATORY unless user requested EXACTLY `fully autonomous` or `No HITL`.

large-workspace-handling

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

natural-writing

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

orchestrator-contract

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.

planning

To build execution-ready plans from approved intent/specs with EARS, sequenced WBS, and HITL checkpoints.

post-mortem

Diagnose instruction defects and optionally submit Rosetta GitHub issue

reasoning

To apply structured 8D meta-cognitive reasoning thinking to complex problems, then answer clearly with caveats. Must use when asked to think or reason.

research

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

reverse-engineering

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

specflow-use

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

tech-specs

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

Testing & QA Featured

testing

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

coding-agents-farm

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

data-collection

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

backlog

To validate story readiness for a sprint or to break work into a human WBS.

init-workspace-context

Classify workspace mode.

init-workspace-discovery

Discover tech stack.

init-workspace-documentation

Generate workspace docs.

init-workspace-patterns

Extract code patterns.

init-workspace-rules

Create agent rules.

init-workspace-shells

Generate shell files.

init-workspace-verification

Verify init completeness.

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.

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 critically affect the solution, you detect deviation NOT complying with original intent, you panic, or user asked to UNDO.

load-context

To load the most current project context; MUST during prep.

questioning

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

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.

self-organization

For proactive planning, large-file restructuring (~500+ lines or 10K+ size), and stale-information cleanup. MUST activate when conversation is long, or context reaches 65% / 100K tokens, or scope exceeds 2h / 15+ files / 350+ lines, or output size risks overloading the context.

sensitive-data

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, credentials, tokens, certificates, or any data that could potentially be sensitive. Applicable for coding too

subagent-contract

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.

Code & Development Featured

coding

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

debugging

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

coding-agents-hooks-authoring

To author, register, and test Rosetta hooks, add a SemanticKind, or debug a hook that won't fire.

compress-prompt

Compress a Rosetta KB prompt artifact (skill · workflow · phase · rule · agent · template · generic) by stripping structural tautology and ineffective scaffolding while preserving every importance-bearing token. Use when the user asks to compress, shorten, tighten, densify, or reduce a prompt / skill / workflow / phase / rule file.