Harness Eval

---
name: harness-eval
description: This skill should be used when the user asks to "/harness-eval", "evaluate the build", "run QA on the app", "grade the application", "test against the spec", or wants to run the evaluator agent standalone without a full harness loop. Dispatches the harness-evaluator agent to test a running application against a specification.
argument-hint: [optional path to spec file]
allowed-tools: [Read, Write, Bash, Glob, Grep, Agent, AskUserQuestion]
---

# Harness Eval — Standalone Evaluation

## Overview

Run the evaluator agent independently to assess an application against a specification. Useful for:
- Checking existing applications against requirements
- Re-evaluating after manual fixes
- Final quality gate before shipping
- Comparing quality across different builds

## Execution

### Step 1: Locate the Spec

Check for spec in this order:
1. Argument path (if provided)
2. `.harness/spec.md` in current project
3. Ask the user to provide or point to a spec

### Step 2: Verify Application is Running

Check if a development server is already running. If not, look for common start commands:
- `package.json` scripts (`dev`, `start`)
- `Makefile` targets
- Docker compose files
- Ask the user if unclear

### Step 3: Dispatch Evaluator

Dispatch the `harness-evaluator` agent with:
- The spec file
- Instructions to test the running application
- Any previous eval reports (for comparison)

### Step 4: Present Results

Show the user:
- Overall verdict (PASS / ITERATE / PIVOT)
- Quality dimension scores
- Critical issues found
- Comparison with previous eval (if available)

Determine the eval round number from existing `.harness/eval-report-*.md` files and write the new report as the next number.

## Additional Resources

### Reference Files
- **`references/custom-criteria.md`** — Adapting evaluation criteria for non-visual projects