griddynamics/rosetta

daily-oss

Batch processing issues, PRs, discussions, implementations, etc.

Idioma del texto original: inglés

checklist

Session self-verification checklist

Idioma del texto original: inglés

checklist

Session self-verification checklist

Idioma del texto original: inglés

collect-github-stats

Collect GitHub repo health/usage stats into merged JSON.

Idioma del texto original: inglés

compress-prompt

Compress 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,…

Idioma del texto original: inglés

documentation

To write, design, review, simplify, restructure, or standardize OSS project documentation

Idioma del texto original: inglés

merge-main

To merge main branch, exact context and instructions

Idioma del texto original: inglés

sync-web-site

To synchronize web site with changes made to local *.md files

Idioma del texto original: inglés

update-change-log

To synchronize CHANGELOG.md with changes made last week (mon - sun)

Idioma del texto original: inglés

backlog

To validate story readiness for a sprint or to break work into a human WBS.

Idioma del texto original: inglés

codemap

To generate, populate, and use a project codemap

Idioma del texto original: inglés

coding-agents-farm

To orchestrate parallel coding-agent farms (Claude, Codex, Copilot, Gemini, etc.) on isolated git worktrees.

Idioma del texto original: inglés

coding-agents-hooks-authoring

To author, register, and test Rosetta hooks, add a SemanticKind, or debug a hook that won't fire.

Idioma del texto original: inglés

coding-agents-prompt-authoring

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

Idioma del texto original: inglés

coding

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

Idioma del texto original: inglés

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 del texto original: inglés

data-collection

To gather QA source artifacts from issue tracker, wiki, test management system

Idioma del texto original: inglés

debugging

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

Idioma del texto original: inglés

design

To decide architecture — alternatives, tradeoffs, committed decision with rationale, boundaries, domain-specific concerns.

Idioma del texto original: inglés

deviation

MUST 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…

Idioma del texto original: inglés

discovery

To establish what exists — affected areas, behavior, prior attempts, dependencies, data.

Idioma del texto original: inglés

harness

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

Idioma del texto original: inglés

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 del texto original: inglés

large-workspace-handling

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

Idioma del texto original: inglés

load-project-context

To load the project's business, behavioral, and technical context.

Idioma del texto original: inglés

natural-writing

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

Idioma del texto original: inglés

orchestration

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

Idioma del texto original: inglés

planning

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

Idioma del texto original: inglés

post-mortem

Diagnose instruction defects and optionally submit Rosetta GitHub issue

Idioma del texto original: inglés

qa-knowledge

To run QA engineering — requirements/gap analysis, scenario & spec design, test implementation, failure triage — over the QA knowledge base.

Idioma del texto original: inglés

qa-structure

To resolve QA session paths, identifiers/slugs, and state-file shape

Idioma del texto original: inglés

questioning

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

Idioma del texto original: inglés

reasoning

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

Idioma del texto original: inglés

requirements-authoring

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

Idioma del texto original: inglés

requirements-use

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

Idioma del texto original: inglés

research

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

Idioma del texto original: inglés

reverse-engineering

To reverse-engineer code into a spec: extract behavior and domain logic — WHAT and WHY, not HOW.

Idioma del texto original: inglés

risk-assessment

MUST 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.

Idioma del texto original: inglés

rosetta

Rosetta identifies and routes user request to the most matching workflow

Idioma del texto original: inglés

security

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

Idioma del texto original: inglés