google

Security fixes can fail when verification uses stale code or broken test harnesses. This skill guides minimal patches with snapshot checks, baseline tests, and independent re-attacks.

Long security reviews require coordinated specialist stages and reliable campaign state across repeated passes. This skill supervises Mantis subagents, preserves findings, and manages optional synchronization and snapshot provenance.

Repeated security findings increase review effort and can obscure regressions. This skill guides consolidation while preserving provenance, active regression candidates, and transaction history.

Architecture notes often leave attacker access and trust boundaries unclear. This skill turns existing Mantis knowledge into a structured threat model with deployment intent and snapshot provenance.

Past security fixes are difficult to track across repository history. This skill guides an AI agent to extract, classify, and cache historical vulnerabilities for later analysis.

Large source trees make symbol navigation and caller discovery expensive. This skill guides structural indexing with reusable caches and coverage-aware queries while preserving lexical discovery.

Security findings need consistent priorities grounded in exploit evidence and architectural context. This skill applies a risk matrix and documented caps to existing Mantis findings.

Agent projects often lose consistency between design, testing, deployment, and operations. This skill guides coding agents through a structured agents-cli and Google ADK workflow.

Starting a Google ADK agent project requires several template, deployment, and workflow choices. This skill guides agents-cli scaffolding from prototype setup through enhancement and upgrade planning.

Publishing ADK agents to Gemini Enterprise requires the correct registration mode, resource IDs, and permissions. This skill guides Claude, Codex, or Claude Code through safe CLI registration and Agent Registry management.

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.