Use to generate high-signal evaluation cases for PonyBunny changes, including success paths, failure modes, edge cases, and regression-sensitive behaviours.

2026-03-283

event-schema-design

ponybunny-ai/ponybunny

Use when defining or reviewing runtime events, lifecycle payloads, and event-order expectations for PonyBunny.

2026-03-283

harness-design

ponybunny-ai/ponybunny

Use when designing or reviewing PonyBunny as a harness-first system, especially around boundaries, evaluation flow, observability, and migration structure.

2026-03-283

harness-improvement-loop

ponybunny-ai/ponybunny

Use when turning repeated failures, weak evals, weak handoffs, or trace blind spots into concrete improvements to the development harness.

2026-03-283

name	harness-gap-analysis
description	Use when mapping PonyBunny's current state against harness-first best-practice gaps and turning those gaps into actionable engineering inputs.

Harness Gap Analysis

Use this skill when

reviewing an existing gap list
converting gap findings into engineering actions
prioritising harness-oriented migration work
deciding what should be fixed first

Goals

classify gaps clearly
identify likely root causes
connect gaps to affected subsystems
prioritise work rationally
prepare the gaps for planning

Process

List the identified gaps.
Group them by theme.
For each gap, identify the likely root cause.
Identify the affected subsystem or workflow.
Estimate migration priority.
Identify what evidence is needed to confirm the gap.
Recommend the next best owner or subagent.

Output contract

For each gap, return:

gap name
category
root cause hypothesis
affected area
priority
required evidence
recommended next step