All authors
Claude Skills by griddynamics
github.com/griddynamics171 skills24 installs461 views
- Dangerous ActionsMUST activate when action OR its consequence is potentially dangerous/irreversible/destructive, or HIGH RISK, or environment is stage, pre-prod, prod, or blast radius.Votes: 0GitHub stars: 352
- Data CollectionTo gather QA source artifacts from issue tracker, wiki, test management systemVotes: 0GitHub stars: 352
- DebuggingTo investigate errors, test failures, and unexpected behavior — root cause before fix.Votes: 0GitHub stars: 352
- DesignTo decide architecture — alternatives, tradeoffs, committed decision with rationale, boundaries, domain-specific concerns.Votes: 0GitHub stars: 352
- DeviationMUST 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.Votes: 0GitHub stars: 352
- DiscoveryTo establish what exists — affected areas, behavior, prior attempts, dependencies, data.Votes: 0GitHub stars: 352
- HarnessTo build an AI harness: run, observe, validate, automate repeated work faster — CLI/MCP actions, devcontainers, skills, subagents, hooks, pipelines, automations.Votes: 0GitHub stars: 352
- HitlMUST 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`.Votes: 0GitHub stars: 352
- Large Workspace HandlingTo partition large workspaces (100+ files) into scoped subagent tasks when context is insufficient.Votes: 0GitHub stars: 352
- Load Project ContextTo load the project's business, behavioral, and technical context.Votes: 0GitHub stars: 352
- OrchestrationTo delegate, prompt and manage subagents. MUST activate to spawn subagent with a quality prompt, unless trivial.Votes: 0GitHub stars: 352
- PlanningTo build execution-ready AI sessions graph with intent/ACs/checklists.Votes: 0GitHub stars: 352
- Post MortemDiagnose instruction defects and optionally submit Rosetta GitHub issueVotes: 0GitHub stars: 352
- Qa KnowledgeTo run QA engineering — requirements/gap analysis, scenario & spec design, test implementation, failure triage — over the QA knowledge base.Votes: 0GitHub stars: 352
- Qa StructureTo resolve QA session paths, identifiers/slugs, and state-file shapeVotes: 0GitHub stars: 352
- QuestioningTo ask targeted clarification questions only when high-impact unknowns block safe execution.Votes: 0GitHub stars: 352
- Requirements AuthoringTo author, update, and validate functional/non-functional requirements as atomic units with user approval.Votes: 0GitHub stars: 352
- Requirements UseTo consume approved requirements for planning, implementation, and validation, with traceability and HITL.Votes: 0GitHub stars: 352
- ResearchTo run systematic deep research via meta-prompting — grounded references, incremental tracking, self-validation.Votes: 0GitHub stars: 352
- Risk AssessmentMUST 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.Votes: 0GitHub stars: 352
- RosettaRosetta identifies and routes user request to the most matching workflowVotes: 0GitHub stars: 352
- SecurityRun authorized, evidence-preserving security reviews and prepare remediation inputs.Votes: 0GitHub stars: 352
- Self LearningMUST 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.Votes: 0GitHub stars: 352
- Self OrganizationMUST activate at 65%+ context usage or on large-file restructuring. Proactive planning, reorganization, stale-content cleanup.Votes: 0GitHub stars: 352
- Sensitive DataMUST 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.Votes: 0GitHub stars: 352
- Solr ExtendingTo build Solr plugins: SearchComponent, QParser, URP, DocTransformer.Votes: 0GitHub stars: 352
- Solr QueryTo build and debug Solr queries: eDisMax, block join, JSON facets, kNN, explain.Votes: 0GitHub stars: 352
- Solr SchemaTo design and audit Solr schemas: field types, analyzers, docValues, solrconfig.Votes: 0GitHub stars: 352
- Solr Semantic SearchTo build Solr phrase-tagging semantic search: concept tagging, taxonomy, graph paths.Votes: 0GitHub stars: 352
- Specflow UseTo connect Rosetta with Grid Dynamics SpecFlow MCP; only when SpecFlow is mentioned and the MCP is installed.Votes: 0GitHub stars: 352
- Subagent DirectivesMUST duties for a spawned subagentVotes: 0GitHub stars: 352
- Tech SpecsTo define clear, testable tech specs from requirements — target-state architecture, contracts, interfaces.Votes: 0GitHub stars: 352
- TestingTo write thorough, isolated, idempotent tests — 80%+ coverage, external-only mocking, scenario-driven.Votes: 0GitHub stars: 352
- Adhoc FlowWorkflow for the rest of tasks: lightweight documentation, build, track, synchronize, etc.Votes: 0GitHub stars: 352
- Api Aqa FlowWorkflow for backend API test automation: TMS / Issue Tracker test cases → automated API tests, HITL-gated.Votes: 0GitHub stars: 352
- Aqa FlowRouter workflow for test automation: routes to ui-aqa-flow, api-aqa-flow, or testgen-flow. Kept for backward compatibility.Votes: 0GitHub stars: 352
- Arrange Workspace FlowWorkflow for arranging a workspace: layout, reference source code, business/technical context, ecosystem setup.Votes: 0GitHub stars: 352
- BacklogTo validate story readiness for a sprint or to break work into a human WBS.Votes: 0GitHub stars: 352
- Code Analysis FlowWorkflow for reverse-engineering a codebase into grounded architecture docs, requirements capture, etc.Votes: 0GitHub stars: 352
- CodemapTo generate, populate, and use a project codemapVotes: 0GitHub stars: 352
- Coding Agents FarmTo orchestrate parallel coding-agent farms (Claude, Codex, Copilot, Gemini, etc.) on isolated git worktrees.Votes: 0GitHub stars: 352
- Coding Agents Hooks AuthoringTo author, register, and test Rosetta hooks, add a SemanticKind, or debug a hook that won't fire.Votes: 0GitHub stars: 352
- Coding Agents Prompt AuthoringTo author, adapt, review, and validate prompts (skills, agents, workflows, rules, etc.) with brief, contracts, and a validation pack.Votes: 0GitHub stars: 352
- Coding Agents Prompting FlowWorkflow for authoring and adapting AI-agent prompts: skills, agents, workflows, rules, etc.Votes: 0GitHub stars: 352
- Coding FlowLight coding workflow: features, fixes, refactors, unit tests, etc.; scales small to large.Votes: 0GitHub stars: 352
- CodingTo implement features, fix bugs, and refactor with KISS/SOLID/DRY and systematic validation.Votes: 0GitHub stars: 352
- Dangerous ActionsMUST activate when action OR its consequence is potentially dangerous/irreversible/destructive, or HIGH RISK, or environment is stage, pre-prod, prod, or blast radius.Votes: 0GitHub stars: 352
- Data CollectionTo gather QA source artifacts from issue tracker, wiki, test management systemVotes: 0GitHub stars: 352
- DebuggingTo investigate errors, test failures, and unexpected behavior — root cause before fix.Votes: 0GitHub stars: 352
- DesignTo decide architecture — alternatives, tradeoffs, committed decision with rationale, boundaries, domain-specific concerns.Votes: 0GitHub stars: 352