Agent skills for DeepSeek Harness

This skill should be used when the user wants to "develop an agent", "build an agent using ADK", "run the agent locally", "debug agent…

This skill should be used when the user wants to "run an evaluation", "evaluate my ADK agent", "write an eval dataset", "analyze eval…

Use when executing implementation plans with independent tasks in the current session

Use when implementing any feature or bugfix, before writing implementation code

Use when creating new skills, editing existing skills, or verifying skills work before deployment

Maps and documents codebases of any size by orchestrating parallel subagents.

Game building mechanics case studies and decision frameworks.

Reads AR/AP, historical cash timing, and known fixed costs from the ledger (MYOB, NetSuite, QuickBooks, Xero, or Zoho Books) or from…

LinkedIn post generation from meeting transcripts, Slack dumps, and other source material, written in the user's personal writing style.

Integrate CAST AI policy validation and cost checks into CI/CD pipelines.

Diagnose and fix CAST AI agent, API, and autoscaler errors.

Configure CAST AI autoscaler policies and node templates for cost optimization.

Configure CAST AI Workload Autoscaler for pod-level right-sizing and

Maximize Kubernetes cost savings with CAST AI spot strategies and right-sizing.

Install and configure CAST AI agent on a Kubernetes cluster with API

Set up a local Kubernetes development loop with CAST AI cost monitoring.

Production readiness checklist for CAST AI cluster onboarding.

CAST AI reference architecture for multi-cluster Kubernetes cost optimization.

Production-ready CAST AI REST API wrapper patterns in TypeScript and

Secure CAST AI API keys, RBAC configuration, and Kvisor security agent.

This skill covers causal inference methods in observational and quasi-experimental settings.