griddynamics
- 289 skills
- 0 followers
- 375 repo stars
- yesterday last updated
- ▌
- ▌ Documentation · griddynamicsTo write, design, review, simplify, restructure, or standardize OSS project documentation
- ▌
- ▌ Compress Prompt · griddynamicsCompress 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.
- ▌ Update Change Log · griddynamicsTo synchronize CHANGELOG.md with changes made last week (mon - sun)
- ▌
- ▌ Coding Agents Hooks Authoring 2 · griddynamicsTo author, register, and test Rosetta hooks, add a SemanticKind, or debug a hook that won't fire.
- ▌ Hitl 3 · griddynamics bundleMUST 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`.
- ▌ Planning 3 · griddynamics bundleTo build execution-ready AI sessions graph with intent/ACs/checklists.
- ▌ Research 3 · griddynamics bundleTo run systematic deep research via meta-prompting — grounded references, incremental tracking, self-validation.
- ▌ Discovery 2 · griddynamics bundleTo establish what exists — affected areas, behavior, prior attempts, dependencies, data.
- ▌ Questioning 3 · griddynamics bundleTo ask targeted clarification questions only when high-impact unknowns block safe execution.
- ▌ Orchestration 2 · griddynamics bundleTo delegate, prompt and manage subagents. MUST activate to spawn subagent with a quality prompt, unless small task.
- ▌ Coding Agents Farm 3 · griddynamics bundleTo orchestrate parallel coding-agent farms (Claude, Codex, Copilot, Gemini, etc.) on isolated git worktrees.
- ▌ Requirements Authoring 3 · griddynamics bundleTo author, update, and validate functional/non-functional requirements as atomic units with user approval.
- ▌ Coding Agents Hooks Authoring 3 · griddynamics bundleTo author, register, and test Rosetta hooks, add a SemanticKind, or debug a hook that won't fire.
- ▌
- ▌ Coding Agents Farm 5 · griddynamics bundleTo orchestrate parallel coding-agent farms (Claude, Codex, Copilot, Gemini, etc.) on isolated git worktrees.
- ▌ Modernization Flow 4 · griddynamics bundleWorkflow for converting, modernizing, upgrading, or re-architecting code (e.g. C++→Java, monolith→microservices), etc.
- ▌ Init Workspace Flow 5 · griddynamics bundleWorkflow for initializing or upgrading a workspace: context, discovery, documentation, etc.
- ▌ Coding Flow 10 · griddynamicsLight coding workflow: features, fixes, refactors, unit tests, etc.; scales small to large.
- ▌ Coding Light Flow 2 · griddynamicsLight coding workflow: features, fixes, refactors, unit tests, etc.; scales small to large.
- ▌ Code Analysis Flow 5 · griddynamicsWorkflow for reverse-engineering a codebase into grounded architecture docs, requirements capture, etc.
- ▌ Init Workspace Flow 6 · griddynamics bundleWorkflow for initializing or upgrading a workspace: context, discovery, documentation, etc.
- ▌ Requirements Authoring 5 · griddynamics bundleTo author, update, and validate functional/non-functional requirements as atomic units with user approval.
- ▌ Requirements Authoring Flow 5 · griddynamicsWorkflow for authoring requirements and specifications: drafting, review, validation, etc.
- ▌ Coding Agents Prompting Flow 5 · griddynamicsWorkflow for authoring and adapting AI-agent prompts: skills, agents, workflows, rules, etc.
- ▌ Coding Agents Hooks Authoring 5 · griddynamics bundleTo author, register, and test Rosetta hooks, add a SemanticKind, or debug a hook that won't fire.
- ▌ Requirements Authoring Flow 6 · griddynamicsWorkflow for authoring requirements and specifications: drafting, review, validation, etc.
- ▌ Coding Agents Prompting Flow 6 · griddynamicsWorkflow for authoring and adapting AI-agent prompts: skills, agents, workflows, rules, etc.
- ▌ Discovery 4 · griddynamics bundleTo establish what exists — affected areas, behavior, prior attempts, dependencies, data.
- ▌ Adhoc Flow 5 · griddynamicsWorkflow for the rest of tasks: lightweight documentation, build, track, synchronize, etc.
- ▌ Coding Flow 7 · griddynamicsWorkflow for all coding: features, fixes, refactors, unit tests, etc.; scales small to large.
- ▌ Questioning 5 · griddynamics bundleTo ask targeted clarification questions only when high-impact unknowns block safe execution.
- ▌ Adhoc Flow 6 · griddynamicsWorkflow for the rest of tasks: lightweight documentation, build, track, synchronize, etc.
- ▌ Orchestration 4 · griddynamics bundleTo delegate, prompt and manage subagents. MUST activate to spawn subagent with a quality prompt, unless small task.
- ▌ Coding Flow 8 · griddynamicsWorkflow for all coding: features, fixes, refactors, unit tests, etc.; scales small to large.
- ▌ UI Aqa Flow 5 · griddynamics bundleWorkflow for automated QA: integration and end-to-end UI test automation, page objects, etc.
- ▌ API Aqa Flow 5 · griddynamics bundleWorkflow for backend API test automation: TMS / Issue Tracker test cases → automated API tests, HITL-gated.
- ▌ Testgen Flow 5 · griddynamics bundleWorkflow for generating test cases from requirements (Issue Tracker / Wiki sources), exporting to a Test Management System, etc.
- ▌ Research Flow 5 · griddynamicsWorkflow for deep project research with grounded references, parallel exploration, etc.
- ▌ Security Flow 5 · griddynamics bundleWorkflow for authorized, evidence-preserving security review and remediation-task preparation.
- ▌ Coding Flow 9 · griddynamicsLight coding workflow: features, fixes, refactors, unit tests, etc.; scales small to large.
- ▌ Coding Light Flow · griddynamicsLight coding workflow: features, fixes, refactors, unit tests, etc.; scales small to large.
- ▌
- ▌ Hitl 5 · griddynamics bundleMUST 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`.
- ▌ Planning 5 · griddynamics bundleTo build execution-ready AI sessions graph with intent/ACs/checklists.
- ▌ Research 5 · griddynamics bundleTo run systematic deep research via meta-prompting — grounded references, incremental tracking, self-validation.
- ▌ Security 5 · griddynamics bundleRun authorized, evidence-preserving security reviews and prepare remediation inputs.
- ▌ Hitl 4 · griddynamics bundleMUST 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`.
- ▌ Coding 4 · griddynamics bundleTo implement features, fix bugs, and refactor with KISS/SOLID/DRY and systematic validation.
- ▌ Design 3 · griddynamics bundleTo decide architecture — alternatives, tradeoffs, committed decision with rationale, boundaries, domain-specific concerns.
- ▌ Backlog 3 · griddynamics bundleTo validate story readiness for a sprint or to break work into a human WBS.
- ▌
- ▌ Harness 3 · griddynamics bundleTo build an AI harness: run, observe, validate, automate repeated work faster — CLI/MCP actions, devcontainers, skills, subagents, hooks, pipelines, automations.
- ▌ Rosetta 3 · griddynamics bundleRosetta identifies and routes user request to the most matching workflow
- ▌ Testing 4 · griddynamics bundleTo write thorough, isolated, idempotent tests — 80%+ coverage, external-only mocking, scenario-driven.
- ▌ Planning 4 · griddynamics bundleTo build execution-ready AI sessions graph with intent/ACs/checklists.
- ▌ Research 4 · griddynamics bundleTo run systematic deep research via meta-prompting — grounded references, incremental tracking, self-validation.
- ▌ Debugging 4 · griddynamics bundleTo investigate errors, test failures, and unexpected behavior — root cause before fix.
- ▌ Deviation 4 · griddynamics bundleMUST 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.
- ▌ Discovery 3 · griddynamics bundleTo establish what exists — affected areas, behavior, prior attempts, dependencies, data.
- ▌ Reasoning 4 · griddynamics bundleTo apply structured meta-cognitive thinking to complex problems. Invoke on explicit only.
- ▌ Solr Query 3 · griddynamics bundleTo build and debug Solr queries: eDisMax, block join, JSON facets, kNN, explain.
- ▌ Tech Specs 4 · griddynamics bundleTo define clear, testable tech specs from requirements — target-state architecture, contracts, interfaces.
- ▌ Aqa Flow 3 · griddynamicsRouter workflow for test automation: routes to ui-aqa-flow, api-aqa-flow, or testgen-flow. Kept for backward compatibility.
- ▌ Post Mortem 8 · griddynamics bundleDiagnose instruction defects and optionally submit Rosetta GitHub issue
- ▌ Questioning 4 · griddynamics bundleTo ask targeted clarification questions only when high-impact unknowns block safe execution.
- ▌ Solr Schema 3 · griddynamics bundleTo design and audit Solr schemas: field types, analyzers, docValues, solrconfig.
- ▌
- ▌ QA Knowledge 3 · griddynamics bundleTo run QA engineering — requirements/gap analysis, scenario & spec design, test implementation, failure triage — over the QA knowledge base.
- ▌ QA Structure 3 · griddynamics bundleTo resolve QA session paths, identifiers/slugs, and state-file shape
- ▌ Orchestration 3 · griddynamics bundleTo delegate, prompt and manage subagents. MUST activate to spawn subagent with a quality prompt, unless trivial.
- ▌ Self Learning 4 · griddynamics bundleMUST 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.
- ▌ Sensitive Data 4 · griddynamics bundleMUST 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.
- ▌ Solr Extending 3 · griddynamics bundleTo build Solr plugins: SearchComponent, QParser, URP, DocTransformer.
- ▌ Specflow Use 10 · griddynamics bundleTo connect Rosetta with Grid Dynamics SpecFlow MCP; only when SpecFlow is mentioned and the MCP is installed.
- ▌ Data Collection 3 · griddynamics bundleTo gather QA source artifacts from issue tracker, wiki, test management system
- ▌ Natural Writing 4 · griddynamics bundleTo rewrite text in a clear, natural, honest human tone — no AI slop, hype, or robotic phrasing.
- ▌ Risk Assessment 4 · griddynamics bundleMUST 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.
- ▌ Requirements Use 4 · griddynamics bundleTo consume approved requirements for planning, implementation, and validation, with traceability and HITL.
- ▌
- ▌ Dangerous Actions 4 · griddynamics bundleMUST activate when action OR its consequence is potentially dangerous/irreversible/destructive, or HIGH RISK, or environment is stage, pre-prod, prod, or blast radius.
- ▌ Self Organization 4 · griddynamics bundleMUST activate at 65%+ context usage or on large-file restructuring. Proactive planning, reorganization, stale-content cleanup.
- ▌ Coding Agents Farm 4 · griddynamics bundleTo orchestrate parallel coding-agent farms (Claude, Codex, Copilot, Gemini, etc.) on isolated git worktrees.
- ▌ Reverse Engineering 4 · griddynamics bundleTo reverse-engineer code into a spec: extract behavior and domain logic — WHAT and WHY, not HOW.
- ▌
- ▌ External Lib Flow 3 · griddynamicsWorkflow for onboarding an external private library so AI can use it without source access.
- ▌ Load Project Context 3 · griddynamics bundleTo load the project's business, behavioral, and technical context.
- ▌ Solr Semantic Search 3 · griddynamics bundleTo build Solr phrase-tagging semantic search: concept tagging, taxonomy, graph paths.
- ▌ Modernization Flow 3 · griddynamics bundleWorkflow for converting, modernizing, upgrading, or re-architecting code (e.g. C++→Java, monolith→microservices), etc.
- ▌ Requirements Authoring 4 · griddynamics bundleTo author, update, and validate functional/non-functional requirements as atomic units with user approval.
- ▌ Large Workspace Handling 4 · griddynamics bundleTo partition large workspaces (100+ files) into scoped subagent tasks when context is insufficient.
- ▌ Arrange Workspace Flow 3 · griddynamics bundleWorkflow for arranging a workspace: layout, reference source code, business/technical context, ecosystem setup.
- ▌ Coding Agents Hooks Authoring 4 · griddynamics bundleTo author, register, and test Rosetta hooks, add a SemanticKind, or debug a hook that won't fire.
- ▌ Coding Agents Prompt Authoring 4 · griddynamics bundleTo author, adapt, review, and validate prompts (skills, agents, workflows, rules, etc.) with brief, contracts, and a validation pack.
- ▌ Testgen Flow 3 · griddynamics bundleWorkflow for generating test cases from requirements (Issue Tracker / Wiki sources), exporting to a Test Management System, etc.
- ▌ Adhoc Flow 4 · griddynamicsWorkflow for the rest of tasks: lightweight documentation, build, track, synchronize, etc.
- ▌ Research Flow 3 · griddynamicsWorkflow for deep project research with grounded references, parallel exploration, etc.
- ▌ Security Flow 3 · griddynamics bundleWorkflow for authorized, evidence-preserving security review and remediation-task preparation.