All authors
Claude Skills by griddynamics
github.com/griddynamics171 skills14 installs352 views
- DocumentationTo write, design, review, simplify, restructure, or standardize OSS project documentationVotes: 0GitHub stars: 352
- Schemas["Rosetta" + Brief description of WHEN and WHY to use this skill.]Votes: 0GitHub stars: 352
- Coding Agents FarmOrchestrate 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.Votes: 0GitHub stars: 352
- Coding Agents Prompt AuthoringAuthor, 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.Votes: 0GitHub stars: 352
- CodingRosetta 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.Votes: 0GitHub stars: 352
- Dangerous ActionsRosetta 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.Votes: 0GitHub stars: 352
- DebuggingRosetta debugging skill for errors, test failures, and unexpected behavior. Use proactively when encountering any issue. Ensures root cause investigation before attempting fixes.Votes: 0GitHub stars: 352
- DeviationRosetta 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.Votes: 0GitHub stars: 352
- HitlRosetta 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 `...Votes: 0GitHub stars: 352
- Init Workspace ContextRosetta skill to classify workspace initialization mode and build existing file inventory.Votes: 0GitHub stars: 352
- Init Workspace DiscoveryRosetta skill to produce TECHSTACK, CODEMAP, DEPENDENCIES from workspace analysis.Votes: 0GitHub stars: 352
- Init Workspace DocumentationRosetta skill to create CONTEXT.md, ARCHITECTURE.md, IMPLEMENTATION.md, ASSUMPTIONS.md, and AGENT MEMORY.md from workspace analysis.Votes: 0GitHub stars: 352
- Init Workspace PatternsRosetta skill to extract recurring coding and architectural patterns from workspace code into reusable templates.Votes: 0GitHub stars: 352
- Init Workspace RulesRosetta skill to create local cached agent rules configured for IDE/OS/project context.Votes: 0GitHub stars: 352
- Init Workspace ShellsRosetta skill to generate IDE/CodingAgent shell files from KB schemas.Votes: 0GitHub stars: 352
- Init Workspace VerificationRosetta skill to verify workspace initialization completeness and run catch-up for missed artifacts.Votes: 0GitHub stars: 352
- Large Workspace HandlingRosetta skill to partition large workspaces or folders (100+ files recursively) into scoped subagent tasks when single-agent context is insufficient.Votes: 0GitHub stars: 352
- Load ContextRosetta 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 pathVotes: 0GitHub stars: 352
- Natural WritingUse this skill to rewrite or generate text in a clear, natural, and honest human tone. Eliminates AI-sounding language, marketing hype, and robotic phrasing.Votes: 0GitHub stars: 352
- Orchestrator ContractRosetta 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.Votes: 0GitHub stars: 352
- PlanningBuild execution-ready implementation plans from approved intent/specs using EARS requirements, sequenced WBS, and explicit HITL checkpoints.Votes: 0GitHub stars: 352
- QuestioningAsk targeted clarification questions only when high-impact unknowns block safe execution.Votes: 0GitHub stars: 352
- ReasoningApply structured meta-cognitive reasoning to complex problems using canonical 7D, then deliver a clear answer with caveats.Votes: 0GitHub stars: 352
- Requirements AuthoringAuthor, update, and validate functional and non-functional requirements as a source of truth using atomic requirement units with explicit user approval.Votes: 0GitHub stars: 352
- Requirements UseConsume approved requirements to drive planning, implementation, and validation with explicit traceability and mandatory HITL for ambiguity or tradeoffs.Votes: 0GitHub stars: 352
- ResearchRosetta skill for systematic deep research using meta-prompting. Use when conducting project-related research that requires grounded references, incremental tracking, and self-validation.Votes: 0GitHub stars: 352
- Reverse EngineeringRosetta 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.Votes: 0GitHub stars: 352
- Risk AssessmentRosetta MUST skill. MUST activate before execution when environment has access to databases, cloud services, S3, or similar external systems. MUST activate when assessing environment risk level. SHOULD be invoked manually before any new environment interaction.Votes: 0GitHub stars: 352
- Self LearningRosetta 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.Votes: 0GitHub stars: 352
- Self OrganizationRosetta 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.Votes: 0GitHub stars: 352
- 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 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.Votes: 0GitHub stars: 352
- Specflow UseConnect Rosetta locally with Grid Dynamics SpecFlow MCP. Trigger only when the user mentions SpecFlow or SpecFlow workspaces and if SpecFlow MCP is already installed.Votes: 0GitHub stars: 352
- Subagent ContractRosetta 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.Votes: 0GitHub stars: 352
- Tech SpecsRosetta skill for defining clear, testable tech specifications from requirements. Use when creating implementation-ready documentation that defines the target state architecture, contracts, and interfaces.Votes: 0GitHub stars: 352
- TestingRosetta testing skill for thorough, isolated, idempotent tests with 80% minimum coverage, external-only mocking, and scenario-driven testing. Use when writing or updating tests.Votes: 0GitHub stars: 352
- ChecklistSession self-verification checklistVotes: 0GitHub stars: 352
- Collect Github StatsCollect GitHub repo health/usage stats into merged JSON.Votes: 0GitHub stars: 352
- Compress PromptCompress 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.Votes: 0GitHub stars: 352
- Daily OssBatch processing issues, PRs, discussions, implementations, etc.Votes: 0GitHub stars: 352
- Merge MainTo merge main branch, exact context and instructionsVotes: 0GitHub stars: 352
- Sync Web SiteTo synchronize web site with changes made to local *.md filesVotes: 0GitHub stars: 352
- Update Change LogTo synchronize CHANGELOG.md with changes made last week (mon - sun)Votes: 0GitHub stars: 352
- StoriesDiff scope: `feat/orchestration-skill` vs `main`, excluding `orchestration_v1` (a previous attempt at this skill, kept in the branch for reference only, not part of this review).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
- Post MortemDiagnose instruction defects and optionally submit Rosetta GitHub issueVotes: 0GitHub stars: 352
- BacklogTo validate story readiness for a sprint or to break work into a human WBS.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