griddynamics

coding-agents-farm

Orchestrate multiple coding agent farms via CLI (Claude, Codex, Copilot, Gemini, OpenCode, Goose) running in parallel on isolated git worktrees. Farm Leader plans, dispatches, monitors, intervenes, and merges results.

coding-agents-prompt-authoring

Author, update, and validate prompts (skills, agents, subagents, workflows, commands, rules, templates, or just any generic prompt). Produces a final prompt with analytics artifacts (brief, contracts, and a validation pack). Use when creating, editing, refactoring, reviewing, validating, or migrating prompts for AI coding agents.

init-workspace-discovery

Rosetta skill to produce TECHSTACK, CODEMAP, DEPENDENCIES from workspace analysis.

init-workspace-documentation

Rosetta skill to create CONTEXT.md, ARCHITECTURE.md, IMPLEMENTATION.md, ASSUMPTIONS.md, and AGENT MEMORY.md from workspace analysis.

init-workspace-patterns

Rosetta skill to extract recurring coding and architectural patterns from workspace code into reusable templates.

init-workspace-rules

Rosetta skill to create local cached agent rules configured for IDE/OS/project context.

init-workspace-shells

Rosetta skill to generate IDE/CodingAgent shell files from KB schemas.

init-workspace-verification

Rosetta skill to verify workspace initialization completeness and run catch-up for missed artifacts.

large-workspace-handling

Rosetta skill to partition large workspaces or folders (100+ files recursively) into scoped subagent tasks when single-agent context is insufficient.

natural-writing

Use this skill to rewrite or generate text in a clear, natural, and honest human tone. Eliminates AI-sounding language, marketing hype, and robotic phrasing.

plan-manager

Rosetta skill for reliable execution: plan creation, tracking, and execution coordination via local JSON files.

planning

Build execution-ready implementation plans from approved intent/specs using EARS requirements, sequenced WBS, and explicit HITL checkpoints.

reasoning

Apply structured meta-cognitive reasoning to complex problems using canonical 7D, then deliver a clear answer with caveats.

research

Rosetta skill for systematic deep research using meta-prompting. Use when conducting project-related research that requires grounded references, incremental tracking, and self-validation.

init-workspace-context

Rosetta skill to classify workspace initialization mode and build existing file inventory.

questioning

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

Code & Development Solid

coding-iac

Rosetta planning, coding, and reviewing skill for IaC implementation (Terraform, Polumi, CloudFormation, ARM, Bicep, Crossplane, CDK, Helm, Kustomize, etc). MUST use when implementing features, fixing bugs, or making code changes to any IaC.

coding

Rosetta coding skill for implementation with KISS/SOLID/DRY principles, zero-tolerance quality, multi-environment awareness, and systematic validation. Use when implementing features, fixing bugs, or making code changes.

dangerous-actions

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 enterprise environment — the cost of dangerous activities is EXTREMELY HIGH, recovery may be impossible, and blast radius may affect production, shared environments, or other teams. If there is even a remote chance - load the skill.

debugging

Rosetta debugging skill for errors, test failures, and unexpected behavior. Use proactively when encountering any issue. Ensures root cause investigation before attempting fixes.

hitl

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 silently, violating enterprise policy. Activate it for ALL tasks always — planning, execution, validation, review — regardless of auto-mode, no approval policy, full access. THE ONLY exception: user DIRECTLY EXPLICITLY requests with EXACTLY `fully autonomous` or `No HITL`. Without explicit opt-out this skill is MANDATORY. Do not assume approval from a question or partial response. Contains human-in-the-loop collaboration, questioning, approvals, and user coordination requirements.

hooks-authoring

Rules for authoring, registering, and testing hooks in Rosetta. Use when creating a new hook, adding a SemanticKind, troubleshooting a hook that doesn't fire, or reviewing a hooks PR.

orchestrator-contract

Rosetta MUST skill. 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.

reverse-engineering

Rosetta skill to reverse-engineer existing code to a specification, to extract a behavior, distill domain logic from implementation, or produce a clean system-level description from source files, captures WHAT a system does and WHY, stripped of HOW.

specflow-use

Connect Rosetta locally with Grid Dynamics SpecFlow MCP. Trigger only when the user mentions SpecFlow or SpecFlow workspaces and if SpecFlow MCP is already installed.

tech-specs

Rosetta skill for defining clear, testable tech specifications from requirements. Use when creating implementation-ready documentation that defines the target state architecture, contracts, and interfaces.

Testing & QA Solid

testing

Rosetta testing skill for thorough, isolated, idempotent tests with 80% minimum coverage, external-only mocking, and scenario-driven testing. Use when writing or updating tests.

gitnexus-cli

GitNexus CLI reference for npx commands — analyze, status, clean, wiki, list — with flags, effects, and when to run each.

gitnexus-tools

Use when you need to select or call a GitNexus MCP tool and want the right tool with the right parameters. Consult before any GitNexus tool call.

load-context

Rosetta MUST skill to load the most current context, extremely useful, fast, fully automated, especially for planning, helps understand what actually user wants, skipping leads to wrong execution path

self-learning

Rosetta MUST skill. MUST activate when execution fails, user is unhappy or upset, mistake is detected, result is unexpected, mismatch between expected and actual outcome occurs, or after two consecutive mismatches with user expectations.

self-organization

Rosetta MUST skill for proactive planning, large-file restructuring (~500+ lines or 10K+ size), cleanup of stale information. 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.

Data & Documents Solid

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.

subagent-contract

Rosetta MUST skill. 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.

documentation

Design, review, simplify, restructure, or standardize project documentation, especially for open-source or developer-facing repos where the goal is better information architecture, less duplication, faster onboarding, and ultra-compact contributor docs. It is especially appropriate when the request is about best practices, document responsibilities, ToC design, doc boundaries, contributor experience, or AI-assisted documentation workflows rather than writing detailed technical content itself.

gitnexus-setup

Use when directly requested to install GitNexus.

deviation

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