griddynamics/rosetta - Página 3

rosetta

Rosetta identifies and routes user request to the most matching workflow

Idioma do texto original: inglês

security

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

Idioma do texto original: inglês

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.

Idioma do texto original: inglês

self-organization

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

Idioma do texto original: inglês

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,…

Idioma do texto original: inglês

solr-extending

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

Idioma do texto original: inglês

solr-query

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

Idioma do texto original: inglês

solr-schema

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

Idioma do texto original: inglês

solr-semantic-search

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

Idioma do texto original: inglês

specflow-use

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

Idioma do texto original: inglês

subagent-directives

MUST duties for a spawned subagent

Idioma do texto original: inglês

tech-specs

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

Idioma do texto original: inglês

testing

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

Idioma do texto original: inglês

coding-agents-prompt-authoring

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

Idioma do texto original: inglês

coding

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

Idioma do texto original: inglês

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.

Idioma do texto original: inglês

debugging

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

Idioma do texto original: inglês

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`…

Idioma do texto original: inglês

large-workspace-handling

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

Idioma do texto original: inglês

natural-writing

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

Idioma do texto original: inglês

orchestration

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

Idioma do texto original: inglês

planning

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

Idioma do texto original: inglês

questioning

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

Idioma do texto original: inglês

reasoning

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

Idioma do texto original: inglês

requirements-authoring

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

Idioma do texto original: inglês

requirements-use

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

Idioma do texto original: inglês

research

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

Idioma do texto original: inglês

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.

Idioma do texto original: inglês

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,…

Idioma do texto original: inglês

specflow-use

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

Idioma do texto original: inglês

tech-specs

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

Idioma do texto original: inglês

testing

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

Idioma do texto original: inglês

coding-agents-prompt-authoring

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

Idioma do texto original: inglês

coding

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

Idioma do texto original: inglês

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.

Idioma do texto original: inglês

debugging

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

Idioma do texto original: inglês

harness

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

Idioma do texto original: inglês

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`…

Idioma do texto original: inglês

large-workspace-handling

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

Idioma do texto original: inglês

natural-writing

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

Idioma do texto original: inglês