Harbor Task Shapes and DRY (Harbor Evals Part 4)
Harbor task shapes and DRY patterns: simple skill evals vs complex flows, shallow-clone base images, sibling tasks, skill volume mounts, and generate/copy scripts.
10 min
Category
AI
Cursor, Claude, and agentic engineering workflows.
8 articles
[Series] Harbor Evals for Agentic Skills
Harbor evals for agentic skills: series overview covering why evals matter, Harbor task setup, and eval-driven development for Cursor skills.
3 min
Harbor Evals Part 3: Writing Tasks with Pass and Fail Fixtures
Writing Harbor tasks with reference pass and fail outputs, deterministic pytest checks versus LLM-as-judge, neutral instructions, and output files the verifier can find.
12 min
Harbor Evals Part 2: Install Harbor and Scaffold Tasks
Install Harbor with uv, explore harbor --help, and scaffold tasks with harbor tasks init - plus the default folder layout agents can also create for you.
6 min
Harbor Evals for Agentic Skills Part 1: What Are Evals?
What are evals for agentic skills? Why the manual skill loop hurts, how eval-driven development mirrors test-driven development, and what Harbor brings - containers, model matrices, and cheap deterministic checks.
7 min
Building Scalable Skills for Agentic Workflows
Building scalable skills for agentic workflows: classify intent, route thin workflows, and load references on demand - with Team Brain as the reference pattern.
12 min
How to Automate Engineering Workflows with Cursor AI
This blog post will demonstrate how to automate engineering workflows with Cursor and Claude. Sit back and watch AI program your most boring work!
13 min
Getting Started With Cursor AI
Getting started with Cursor AI can be a daunting thought. However, once you understand the basics, it is actually quite simple. Let's get started today!
6 min