Przeszukuje docs/solutions/ pod kątem aplikowalnych wniosków z przeszłości przez metadane frontmatter (bugi, wzorce architektoniczne, wzorce projektowe, konwencje, wnioski workflow). Używaj przed implementacją feature'a, podejmowaniem decyzji lub rozpoczęciem pracy w udokumentowanym obszarze, żeby wiedza…
A DevOps specialist agent for building CI/CD pipelines and managing infrastructure. DevOps covers the tools and practices used to build, test, release, and run software.
The DevOps Engineer maintains build pipelines, CI/CD configuration, version control workflow, and deployment infrastructure. Use this agent for build script maintenance, CI configuration, branching strategy, or automated testing pipeline setup.
Ports an existing script, Makefile target, CI job or prompt chain to a checkable .nika.yaml workflow. Use when converting ad-hoc automation to nika, when a shell script wraps LLM/HTTP/file plumbing, or when a prompt chain in a doc should become a runnable, auditable file. Inventories side effects first, maps steps to…
Optimizes prompts for LLMs and AI systems. Use when building AI features, improving agent performance, or crafting system prompts. Expert in prompt patterns and techniques.
DevOps teammate — infrastructure, CI/CD, containers, configuration, and documentation. Claims tasks from the shared task list, communicates with other teammates, self-verifies before marking complete.
Scaffold a complete CI/CD setup for a repo — multiple GitHub Actions workflows (test, build, release, deploy) in one isolated pass. Use when delegating a full from-scratch pipeline buildout; edit single workflows inline instead.
SCOPE audit orchestrator — single entry point for the full audit pipeline. Runs Python SCOPE runtime enumeration, chains attack-path reasoning, verification, defensive controls, post-processing, and dashboard generation. Invoke with /scope:audit .
Gemini Live native audio model configuration and prompting expert. Use PROACTIVELY when writing or modifying system prompts for Gemini Live, configuring voice/audio settings, optimizing for native audio dialog, or reviewing prompt quality before deployment. Supersedes prompt-engineering-expert for native audio…
Voice AI prompting and system prompt design expert. Use PROACTIVELY when writing or modifying system prompts, designing conversation stages, optimizing prompts for specific models, or reviewing prompt quality before deployment. Provides analysis based on production voice AI best practices.
Launch a single TPU training workload on a GKE cluster via XPK, poll until completion or hang, capture xprof + HLO dumps to GCS, and report structured verdict signals back to the master agent. Stateless one-shot worker — does NOT write wiki pages, decide experiment verdicts, or update the model page. Use for every…