Claude Skills by griddynamics

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

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.

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

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

To decide architecture — alternatives, tradeoffs, committed decision with rationale, boundaries, domain-specific concerns.

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 panic, or user asked to UNDO.

To establish what exists — affected areas, behavior, prior attempts, dependencies, data.

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

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` or `No HITL`.

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

To load the project's business, behavioral, and technical context.

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

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

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

Diagnose instruction defects and optionally submit Rosetta GitHub issue

To run QA engineering — requirements/gap analysis, scenario & spec design, test implementation, failure triage — over the QA knowledge base.

To resolve QA session paths, identifiers/slugs, and state-file shape

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

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

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

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

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

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

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.

Rosetta identifies and routes user request to the most matching workflow

Run authorized, evidence-preserving security reviews and prepare remediation inputs.

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.

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

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 sensitive data. Follow compliance/regulations.

To build Solr plugins: SearchComponent, QParser, URP, DocTransformer.

To build and debug Solr queries: eDisMax, block join, JSON facets, kNN, explain.

To design and audit Solr schemas: field types, analyzers, docValues, solrconfig.

To build Solr phrase-tagging semantic search: concept tagging, taxonomy, graph paths.

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

MUST duties for a spawned subagent

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

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

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

To generate, populate, and use a project codemap

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

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

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

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

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.

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

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

To decide architecture — alternatives, tradeoffs, committed decision with rationale, boundaries, domain-specific concerns.

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 panic, or user asked to UNDO.

To establish what exists — affected areas, behavior, prior attempts, dependencies, data.

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