griddynamics/rosetta
45 skills
$npx skills add griddynamics/rosettaSkillInstalls
codemapTo generate, populate, and use a project codemapcodingTo implement features, fix bugs, and refactor with KISS/SOLID/DRY and systematic validation.coding-agents-farmTo orchestrate parallel coding-agent farms (Claude, Codex, Copilot, Gemini, etc.) on isolated git worktrees.coding-agents-hooks-authoringTo author, register, and test Rosetta hooks, add a SemanticKind, or debug a hook that won't fire.coding-agents-prompt-authoringTo author, adapt, review, and validate prompts (skills, agents, workflows, rules, etc.) with brief, contracts, and a validation pack.collect-github-statsCollect GitHub repo health/usage stats into merged JSON.compress-promptCompress a Rosetta KB prompt artifact (skill · workflow · phase · rule · agent · template · generic) by stripping structural tautology and ineffective…dangerous-actionsRosetta CRITICAL MUST skill. MUST activate when action or its consequence is potentially dangerous, potentially irreversible, potentially destructive, or HIGH…data-collectionTo gather QA source artifacts from issue tracker, wiki, test management systemdebuggingTo investigate errors, test failures, and unexpected behavior — root cause before fix.deviationRosetta CRITICAL MUST skill. MUST activate when intent is unclear, you cannot follow original intent, you cannot easily or reliably solve the problem,…documentationTo write, design, review, simplify, restructure, or standardize OSS project documentationhitlRosetta CRITICAL MUST skill to load as Prep Step 3 Step 2 — immediately after orchestrator-contract, right before loading any workflow.init-workspace-contextClassify workspace mode.init-workspace-discoveryDiscover tech stack.init-workspace-documentationGenerate workspace docs.init-workspace-patternsExtract code patterns.init-workspace-rulesCreate agent rules.init-workspace-shellsGenerate shell files.init-workspace-verificationVerify init completeness.large-workspace-handlingTo partition large workspaces (100+ files) into scoped subagent tasks when context is insufficient.load-contextTo load the most current project context; MUST during prep.load-project-contextTo load the project's business, behavioral, and technical context.merge-mainTo merge main branch, exact context and instructionsnatural-writingTo rewrite text in a clear, natural, honest human tone — no AI slop, hype, or robotic phrasing.orchestrator-contractMUST activate when you ARE an orchestrator — you are the top-level agent, you spawn subagents, you delegate work, you coordinate parallel or sequential…planningTo build execution-ready plans from approved intent/specs with EARS, sequenced WBS, and HITL checkpoints.post-mortemDiagnose instruction defects and optionally submit Rosetta GitHub issuequestioningTo ask targeted clarification questions only when high-impact unknowns block safe execution.reasoningTo apply structured 8D meta-cognitive reasoning thinking to complex problems, then answer clearly with caveats. Must use when asked to think or reason.requirements-authoringTo author, update, and validate functional/non-functional requirements as atomic units with user approval.requirements-useTo consume approved requirements for planning, implementation, and validation, with traceability and HITL.researchTo run systematic deep research via meta-prompting — grounded references, incremental tracking, self-validation.reverse-engineeringTo reverse-engineer code into a spec: extract behavior and domain logic — WHAT and WHY, not HOW.risk-assessmentMUST activate before execution when environment has access to databases, cloud services, S3, or similar external systems, and when assessing environment risk…schemasGENERIC form: To <verb> <what it does + when/why; dense keywords>. CRITICAL/guardrail form: 'Rosetta CRITICAL MUST skill. MUST activate when <condition>'.self-learningMUST activate on: execution failure/error, mistake, wrong/unexpected result, expected≠actual mismatch, 2 consecutive mismatches, unhappy/upset user, user asks…self-organizationFor proactive planning, large-file restructuring (~500+ lines or 10K+ size), and stale-information cleanup.sensitive-dataRosetta CRITICAL MUST skill. MUST activate when you suspect, there is a slight chance, encounter, read, process, or are about to output any sensitive or…specflow-useTo connect Rosetta with Grid Dynamics SpecFlow MCP; only when SpecFlow is mentioned and the MCP is installed.subagent-contractMUST activate when you ARE a subagent — you were spawned by an orchestrator, you received a delegated task, you are executing within a subagent context.sync-web-siteTo synchronize web site with changes made to local *.md filestech-specsTo define clear, testable tech specs from requirements — target-state architecture, contracts, interfaces.testingTo write thorough, isolated, idempotent tests — 80%+ coverage, external-only mocking, scenario-driven.update-change-logTo synchronize CHANGELOG.md with changes made last week (mon - sun)