ALWAYS ACTIVE — read at the start of any ADK agent development session. ADK development lifecycle and mandatory coding guidelines — spec-driven workflow, code preservation rules, model selection, and troubleshooting.

MUST READ before creating or enhancing any ADK agent project. Use when the user wants to build a new agent (e.g. "build me a search agent") or enhance an existing project (e.g. "add CI/CD to my project", "add RAG").

MUST READ before deploying any ADK agent. ADK deployment guide — Agent Engine, Cloud Run, GKE, CI/CD pipelines, secrets, observability, and production workflows. Use when deploying agents to Google Cloud or troubleshooting deployments. Do NOT use for API code patterns (use adk-cheatsheet), evaluation (use adk-eval-guide), or project scaffolding (use adk-scaffold).

MUST READ before writing or modifying ADK agent code. ADK API quick reference for Python — agent types, tool definitions, orchestration patterns, callbacks, and state management. Includes an index of all ADK documentation pages. Do NOT use for creating new projects (use adk-scaffold).

MUST READ before running any ADK evaluation. ADK evaluation methodology — eval metrics, evalset schema, LLM-as-judge, tool trajectory scoring, and common failure causes. Use when evaluating agent quality, running adk eval, or debugging eval results. Do NOT use for API code patterns (use adk-cheatsheet), deployment (use adk-deploy-guide), or project scaffolding (use adk-scaffold).

Use when running controlled perf experiments to validate hypotheses.

Use when synthesizing perf findings into evidence-backed recommendations and decisions.

Use when managing perf baselines, consolidating results, or comparing versions. Ensures one baseline JSON per version.

Use when profiling CPU/memory hot paths, generating flame graphs, or capturing JFR/perf evidence.

Use when appending structured perf investigation notes and evidence.

Use when running performance benchmarks, establishing baselines, or validating regressions with sequential runs. Enforces 60s minimum runs (30s only for binary search) and no parallel benchmarks.

Use when mapping code paths, entrypoints, and likely hot files before profiling.

Use when generating performance hypotheses backed by git history and code evidence.

Ensure all communication matches brand voice and tone guidelines. Use when creating marketing copy, customer communications, public-facing content, or when users mention brand voice, tone, or writing style.

DART build system knowledge - CMake, pixi, dependencies, troubleshooting

DART model loading - URDF, SDF, MJCF, SKEL parsers and dart::io unified API

DART testing patterns - unit tests, integration tests, CI validation

DART contribution workflow - branching, PRs, code review, dual-PR for bugfixes

Helps generate release notes to be published on GitHub as well as in a Slack community channel

AWS Bedrock foundation models for generative AI. Use when invoking foundation models, building AI applications, creating embeddings, configuring model access, or implementing RAG patterns.