griddynamics/rosetta - 3ページ

rosetta

Rosetta identifies and routes user request to the most matching workflow

原文の言語: 英語

security

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

原文の言語: 英語

self-learning

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.

原文の言語: 英語

self-organization

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

原文の言語: 英語

sensitive-data

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,…

原文の言語: 英語

solr-extending

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

原文の言語: 英語

solr-query

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

原文の言語: 英語

solr-schema

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

原文の言語: 英語

solr-semantic-search

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

原文の言語: 英語

specflow-use

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

原文の言語: 英語

subagent-directives

MUST duties for a spawned subagent

原文の言語: 英語

tech-specs

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

原文の言語: 英語

testing

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

原文の言語: 英語

coding-agents-prompt-authoring

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

原文の言語: 英語

coding

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

原文の言語: 英語

dangerous-actions

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.

原文の言語: 英語

debugging

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

原文の言語: 英語

hitl

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`…

原文の言語: 英語

large-workspace-handling

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

原文の言語: 英語

natural-writing

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

原文の言語: 英語

orchestration

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

原文の言語: 英語

planning

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

原文の言語: 英語

questioning

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

原文の言語: 英語

reasoning

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

原文の言語: 英語

requirements-authoring

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

原文の言語: 英語

requirements-use

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

原文の言語: 英語

research

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

原文の言語: 英語

self-learning

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.

原文の言語: 英語

sensitive-data

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,…

原文の言語: 英語

specflow-use

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

原文の言語: 英語

tech-specs

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

原文の言語: 英語

testing

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

原文の言語: 英語

coding-agents-prompt-authoring

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

原文の言語: 英語

coding

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

原文の言語: 英語

dangerous-actions

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.

原文の言語: 英語

debugging

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

原文の言語: 英語

harness

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

原文の言語: 英語

hitl

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`…

原文の言語: 英語

large-workspace-handling

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

原文の言語: 英語

natural-writing

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

原文の言語: 英語