Browse skills

Assess serverless functions, primarily AWS Lambda, for unsafe execution of external input and unauthorized changes to code or added libraries. Combine source inspection, activity logs, and permission reviews to identify injection risks and recommend detection and prevention measures.

• Reviewing Lambda event handlers for injection vulnerabilities
• Investigating unauthorized function or layer changes
• Checking privilege escalation through Lambda execution roles

Investigate compromised credentials across AWS, Azure, and GCP by correlating security alerts and audit logs. Examines unusual API activity and suspicious sign-ins, helps assess the affected scope, and guides containment actions such as disabling keys and revoking sessions.

• Investigate cloud API activity from unfamiliar locations
• Assess exposure after a credential leak notification
• Correlate suspicious sign-ins across cloud providers

Set up decoy credentials, storage, and secrets across AWS, Azure, and GCP to detect suspicious access. Connect audit logs to security alerts, verify detection, and document permissions, resource inventories, and maintenance plans.

• Detecting use of leaked cloud credentials
• Monitoring suspicious access to decoy storage and secrets
• Extending on-premises deception coverage to cloud environments

Configure Google Cloud IAP to check identity before granting access to internal applications and virtual machines. Set permissions by user group, device, and network, configure reauthentication, enable service-account access, and record access decisions for monitoring.

• Replacing VPN access to internal Google Cloud applications
• Restricting sensitive tools to managed devices
• Configuring SSH and RDP access through IAP tunnels

Set up Microsoft Sentinel to collect security logs from AWS, Azure, and GCP. Build detection queries, investigate historical activity, and create automated response workflows for a centralized security operations team.

• Centralizing security monitoring across multiple clouds
• Migrating from an existing SIEM platform
• Automating responses to suspicious cloud activity

Map an organization's internet-facing assets using public information, including domains, indexed services, employee details, and leaked data. Compile findings into a reconnaissance report to support authorized security assessments and identify potential exposure.

• Gathering public information before a penetration test
• Finding unknown internet-facing assets
• Checking public sources for leaked credentials and documents

Plan and conduct authorized security tests of AWS, Azure, and GCP environments. Check access permissions, credential exposure, cross-account access, and monitoring, then organize findings into a report with severity, business impact, and remediation guidance.

• Assessing cloud security before production deployment
• Checking access controls after a cloud migration
• Testing monitoring and incident response readiness

Respond to security incidents across AWS, Azure, and GCP by investigating audit logs, containing compromised identities, isolating resources, and preserving evidence. Organize recovery and follow-up security measures for credential leaks, unauthorized permission changes, and attacks spanning cloud services.

• Responding to leaked cloud credentials
• Investigating unauthorized permission or resource changes
• Preserving audit logs and disk snapshots

Audit Google Cloud access permissions to find overly broad roles, unnecessary service account keys, public access, and impersonation risks. Use gcloud CLI, Policy Analyzer, and IAM Recommender to document findings and plan more limited permissions.

• Reviewing access permissions across a GCP organization
• Replacing broad Owner and Editor roles with narrower roles
• Auditing unused service accounts and user-managed keys

Audit AWS, Azure, and GCP configurations against CIS Benchmarks, security configuration guidelines. Use automated scan results to identify failed checks, prioritize fixes, report compliance by area, and establish ongoing monitoring for configuration changes.

• Running an initial cloud security configuration audit
• Preparing CIS-related evidence for SOC 2 or ISO 27001 audits
• Prioritizing fixes for failed security checks

Work with BigQuery to create datasets and tables, run SQL queries, ingest data, and manage processing jobs. The skill also covers connections to BigQuery ML and Gemini for machine learning and AI analysis.

• Creating datasets and tables
• Analyzing data with SQL queries
• Ingesting data and managing processing jobs

Design a database layer from business requirements, access patterns, and expected growth. Compare database technologies, define tables and relationships, and plan indexes, caching, scaling, migrations, backups, and recovery with clear reasons and trade-offs.

• Choosing a database for a new service
• Designing tables, relationships, and indexes
• Planning database migrations and rollback procedures

Write complex SQL, improve slow queries, and design database schemas for transaction processing and analytics. Uses schema details and query execution plans to guide indexing, validate results, and assess performance with realistic data volumes.

• Investigate and improve slow analytical queries
• Design a database schema for a SaaS application
• Write customer retention and cohort analysis queries

Investigate database slowdowns and plan measurable improvements to queries, indexes, caching, and scaling. The skill covers SQL and NoSQL systems, with guidance on monitoring, load testing, migrations, and balancing performance against cost.

• Analyze slow SQL queries and execution plans
• Resolve repeated database calls in APIs
• Plan indexes and caching for high traffic

Create and manage MySQL, PostgreSQL, and SQL Server databases on Google Cloud. Covers instance setup, users, backups, availability, and secure connections, with a PostgreSQL walkthrough and references for application connectors and Terraform configuration.

• Create a PostgreSQL database on Google Cloud
• Manage database users and passwords
• Connect through Cloud SQL Auth Proxy

Set up automated Android builds and Google Play publishing with GitHub Actions. Supports TWA, React Native, Flutter, and native Android, with signing setup, separate testing and production tracks, and automatic build-number increments on main.

• Setting up Google Play publishing from GitHub
• Separating internal, alpha, beta, and production releases
• Automating versionCode increments on main

Configure machine learning training and batch jobs across multiple clouds with SkyPilot. The skill guides GPU selection, lower-cost cloud and region choices, and automatic recovery when discounted spot instances are interrupted.

• Choose a lower-cost cloud for GPU training
• Run long training jobs with recovery after interruptions
• Configure distributed training across multiple machines

Integrate the Gemini API on Agent Platform using the Google Gen AI SDK. Guidance covers authentication, text and multimedia tasks, structured JSON responses, live voice interactions, context caching, and batch prediction across five programming languages.

• Adding document and multimedia understanding to an application
• Generating JSON that matches a defined schema
• Building live voice and video interactions

Design and implement machine learning systems for production use. Cover data preparation, training, prediction services, model comparisons, monitoring, and retraining, with attention to reliability, response time, resource costs, and both technical and business evaluation metrics.

• Designing a real-time recommendation service
• Comparing model versions with A/B testing
• Detecting changes in data and model performance

Adapt machine learning training to run across multiple GPUs or machines with Ray Train. Covers changes to existing code, comparing training settings with Ray Tune, and saving checkpoints so training can resume after failures.

• Adapting existing PyTorch code for multiple GPUs
• Training HuggingFace models across multiple machines
• Comparing learning rates and batch sizes with Ray Tune

Analyze business data, test hypotheses, and build predictive models with statistical and machine learning methods. Get support across data exploration, experiment design, visualization, result validation, and planning model deployment and monitoring.

• Analyzing customer churn and predicting customers at risk
• Designing an A/B test and evaluating its results
• Forecasting demand for inventory planning

Design and implement systems that collect, transform, validate, and store data for analysis. Covers scheduled and real-time processing, data warehouses, quality checks, monitoring, and cost tuning using tools such as Apache Spark, dbt, and Airflow.

• Building scheduled data collection and transformation workflows
• Designing a data warehouse for analysis
• Synchronizing database changes in real time

Create a Google Model Armor template for checking AI prompts and responses. Specify a Google Cloud project, location, and template ID, then use a preset or provide custom settings in JSON.

• Creating a template with the jailbreak preset
• Defining template settings in JSON
• Preparing a template for prompt and response checks

Connect NanoClaw to Google Chat so people can talk with agents in team spaces or direct messages. The skill installs the adapter, checks its registration, and guides service account and message delivery setup.

• Talk with agents in Google Chat team spaces
• Use direct messages with a personal assistant
• Keep conversations organized in threads