Cursor skills grow fast. The hard part is not writing the first SKILL.md - it is knowing the skill still does what you need after the next edit, the next model, or the next teammate’s prompt.
This series is about Harbor evals for agentic skills: repeatable checks for agent behaviour, the Harbor (opens in a new tab) CLI that runs those checks in containers, and Eval-Driven Development (EDD) so you can improve a skill against an eval instead of only against manual eyeballing.
If you followed Building Scalable Skills for Agentic Workflows (opens in a new tab) to build a Team Brain, that skill’s Intent identified: line is the contract many of the sample evals assert.
Who Harbor evals for agentic skills are for
- People authoring Cursor skills (or similar agent workflows) who want regression checks
- Engineers who know Test-Driven Development (TDD) and want the same rhythm for agents
- Anyone willing to pay their own model API costs for containerized trials - Harbor orchestrates; you bring the keys
What you will build toward
Companion samples live in CodeSloth Cursor Samples (opens in a new tab):
harbor-evals/simple/(opens in a new tab) - small Team Brain intent evalsharbor-evals/advanced/(opens in a new tab) - shared images, mounts, generatorsteam-brain-edd/(opens in a new tab) - an EDD skill that interviews, writes an eval, and loops skill fixes (Parts 3-6 territory)
Posts in this series
Only published parts are linked. Draft parts stay named until they ship.
| Part | Topic |
|---|---|
| Part 1 - What Are Evals? (opens in a new tab) | Why the manual skill loop hurts, EDD vs TDD, what Harbor is |
| Part 2 - Install and Scaffold (opens in a new tab) | Install Harbor with uv, harbor tasks init, default task layout |
| Part 3 - Writing Tasks (opens in a new tab) | Pass/fail fixtures, deterministic checks vs LLM-as-judge, expected output files |
| Part 4 - Task Shapes and DRY (opens in a new tab) | Granularity, base images, mounts, generators, orchestration tradeoffs |
| Part 5 - Running and Results | Run scripts, API keys, model matrices, harbor view |
| Part 6 - Eval-Driven Development | Interview → write eval → improve Team Brain in a capped loop |
How to read Harbor evals for agentic skills
Start with Part 1 (opens in a new tab) if you want the mindset. Skip to Part 2 (opens in a new tab) if you already buy the idea and want the CLI on your machine. Jump to Part 3 (opens in a new tab) when you are ready to write pass/fail fixtures and verifiers.
Official Harbor docs: harborframework.com/docs (opens in a new tab). Harbor source: github.com/laude-institute/harbor (opens in a new tab).
Sloth Summary
- Harbor evals for agentic skills turns skill quality from “looks fine in chat” into Harbor tasks with verifiers and rewards.
- Parts 1-4 are published; Parts 5-6 follow.
- Samples grow under
harbor-evals/andteam-brain-edd/in CodeSloth Cursor Samples.
May your regressions show up in a reward file, not in a teammate’s chat. 🦥