Production ADK agents need trace, log, and analytics signals without exposing prompt data. This skill guides Cloud Trace, prompt logging, BigQuery analytics, and provider choices.

Agent teams need repeatable evidence before changing prompts, tools, or deployment settings. This skill guides dataset design, metric selection, grading, comparison, and failure analysis for Google ADK agents.

Deploying ADK agents across Google Cloud targets requires many infrastructure choices. This skill guides target selection, deployment commands, secrets, CI/CD, testing, and recovery.

Developers need reliable ADK patterns when building Python agents. This skill provides concise references for tools, callbacks, state, multi-agent orchestration, and workflow code.

Contract and schema changes can break downstream services, clients, and data flows. This skill maps affected references and produces a business impact report before commit.

Release decisions often rely on incomplete evidence and inconsistent standards. This skill applies structured controls, deterministic scoring, and mandatory gates to assess readiness.

Long technical tasks lose decisions, evidence, and next actions across sessions. This skill maintains a concise Markdown state file with reviewed local evidence references.

Python teams need repeatable checks for common application security controls. This skill provides configurable pytest coverage with clear evidence, boundaries, and release decisions.

Automated drafts can sound repetitive or overly polished and may lose the writer's original voice. This skill applies minimal editorial fixes while preserving meaning.

Windows POSIX shells can garble Chinese output from Python, PowerShell, and cmd.exe. This skill gives targeted UTF-8 and GBK fixes for Claude, Codex, and related agents.

Weak tests can hide production bugs while inflating coverage metrics. This skill reviews test quality and identifies misleading, redundant, or excessively mocked tests.

Ambiguous specifications create implementation gaps, security risks, and costly rework. This skill reviews plans through architecture, security, quality, user, and governance perspectives before engineers begin implementation.

Complex features fail when requirements, architecture effects, and verification criteria remain unclear. This skill guides agents through research and produces an implementation-ready Gjalla specification.

Code changes can hide correctness, security, and maintainability issues before merge. This skill reviews diffs from relevant perspectives and returns prioritized, location-specific fixes.

Large feature specifications can be difficult to sequence and track. This skill creates dependency-ordered waves of small tasks with files and acceptance checks.

Complex code slows maintenance and makes changes risky. This skill guides small, tested refactoring steps that improve structure while preserving behavior.

Vague product ideas cause unclear scope, weak acceptance criteria, and delivery risk. This skill turns stakeholder input into a structured, measurable Product Requirements Document.

Spring Boot projects can become inconsistent across architecture, configuration, data access, and testing. This skill provides focused practices for maintainable Java applications.

GitHub teams need fast command guidance for repositories, issues, pull requests, Actions, and releases. This skill supplies focused gh CLI examples and workflows for Claude, Codex, and Claude Code.

Manual diagram creation is slow and inconsistent. This skill converts natural language into editable Excalidraw files using templates, layout guidance, and optional icon tools.