griddynamics/rosetta - الصفحة ٣

rosetta

Rosetta identifies and routes user request to the most matching workflow

لغة النص الأصلي: الإنجليزية

security

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

لغة النص الأصلي: الإنجليزية

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.

لغة النص الأصلي: الإنجليزية

self-organization

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

لغة النص الأصلي: الإنجليزية

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,…

لغة النص الأصلي: الإنجليزية

solr-extending

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

لغة النص الأصلي: الإنجليزية

solr-query

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

لغة النص الأصلي: الإنجليزية

solr-schema

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

لغة النص الأصلي: الإنجليزية

solr-semantic-search

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

لغة النص الأصلي: الإنجليزية

specflow-use

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

لغة النص الأصلي: الإنجليزية

subagent-directives

MUST duties for a spawned subagent

لغة النص الأصلي: الإنجليزية

tech-specs

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

لغة النص الأصلي: الإنجليزية

testing

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

لغة النص الأصلي: الإنجليزية

coding-agents-prompt-authoring

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

لغة النص الأصلي: الإنجليزية

coding

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

لغة النص الأصلي: الإنجليزية

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.

لغة النص الأصلي: الإنجليزية

debugging

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

لغة النص الأصلي: الإنجليزية

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`…

لغة النص الأصلي: الإنجليزية

large-workspace-handling

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

لغة النص الأصلي: الإنجليزية

natural-writing

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

لغة النص الأصلي: الإنجليزية

orchestration

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

لغة النص الأصلي: الإنجليزية

planning

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

لغة النص الأصلي: الإنجليزية

questioning

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

لغة النص الأصلي: الإنجليزية

reasoning

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

لغة النص الأصلي: الإنجليزية

requirements-authoring

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

لغة النص الأصلي: الإنجليزية

requirements-use

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

لغة النص الأصلي: الإنجليزية

research

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

لغة النص الأصلي: الإنجليزية

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.

لغة النص الأصلي: الإنجليزية

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,…

لغة النص الأصلي: الإنجليزية

specflow-use

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

لغة النص الأصلي: الإنجليزية

tech-specs

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

لغة النص الأصلي: الإنجليزية

testing

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

لغة النص الأصلي: الإنجليزية

coding-agents-prompt-authoring

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

لغة النص الأصلي: الإنجليزية

coding

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

لغة النص الأصلي: الإنجليزية

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.

لغة النص الأصلي: الإنجليزية

debugging

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

لغة النص الأصلي: الإنجليزية

harness

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

لغة النص الأصلي: الإنجليزية

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`…

لغة النص الأصلي: الإنجليزية

large-workspace-handling

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

لغة النص الأصلي: الإنجليزية

natural-writing

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

لغة النص الأصلي: الإنجليزية